Merge branch 'x86-cache-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cache quality monitoring update from Thomas Gleixner:
 "This update provides a complete rewrite of the Cache Quality
  Monitoring (CQM) facility.

  The existing CQM support was duct taped into perf with a lot of issues
  and the attempts to fix those turned out to be incomplete and
  horrible.

  After lengthy discussions it was decided to integrate the CQM support
  into the Resource Director Technology (RDT) facility, which is the
  obvious choise as in hardware CQM is part of RDT. This allowed to add
  Memory Bandwidth Monitoring support on top.

  As a result the mechanisms for allocating cache/memory bandwidth and
  the corresponding monitoring mechanisms are integrated into a single
  management facility with a consistent user interface"

* 'x86-cache-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
  x86/intel_rdt: Turn off most RDT features on Skylake
  x86/intel_rdt: Add command line options for resource director technology
  x86/intel_rdt: Move special case code for Haswell to a quirk function
  x86/intel_rdt: Remove redundant ternary operator on return
  x86/intel_rdt/cqm: Improve limbo list processing
  x86/intel_rdt/mbm: Fix MBM overflow handler during CPU hotplug
  x86/intel_rdt: Modify the intel_pqr_state for better performance
  x86/intel_rdt/cqm: Clear the default RMID during hotcpu
  x86/intel_rdt: Show bitmask of shareable resource with other executing units
  x86/intel_rdt/mbm: Handle counter overflow
  x86/intel_rdt/mbm: Add mbm counter initialization
  x86/intel_rdt/mbm: Basic counting of MBM events (total and local)
  x86/intel_rdt/cqm: Add CPU hotplug support
  x86/intel_rdt/cqm: Add sched_in support
  x86/intel_rdt: Introduce rdt_enable_key for scheduling
  x86/intel_rdt/cqm: Add mount,umount support
  x86/intel_rdt/cqm: Add rmdir support
  x86/intel_rdt: Separate the ctrl bits from rmdir
  x86/intel_rdt/cqm: Add mon_data
  x86/intel_rdt: Prepare for RDT monitor data support
  ...

6 files changed, 2233 insertions, 267 deletions

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index cdf82492b770..e17942c131c8 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -33,7 +33,7 @@ obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
-obj-$(CONFIG_INTEL_RDT_A)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_schemata.o
+obj-$(CONFIG_INTEL_RDT)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o
 
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 5b366462f579..cd5fc61ba450 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -30,7 +30,8 @@
 #include <linux/cpuhotplug.h>
 
 #include <asm/intel-family.h>
-#include <asm/intel_rdt.h>
+#include <asm/intel_rdt_sched.h>
+#include "intel_rdt.h"
 
 #define MAX_MBA_BW	100u
 #define MBA_IS_LINEAR	0x4
@@ -38,7 +39,13 @@
 /* Mutex to protect rdtgroup access. */
 DEFINE_MUTEX(rdtgroup_mutex);
 
-DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid);
+/*
+ * The cached intel_pqr_state is strictly per CPU and can never be
+ * updated from a remote CPU. Functions which modify the state
+ * are called with interrupts disabled and no preemption, which
+ * is sufficient for the protection.
+ */
+DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
 
 /*
  * Used to store the max resource name width and max resource data width
@@ -46,6 +53,12 @@ DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid);
  */
 int max_name_width, max_data_width;
 
+/*
+ * Global boolean for rdt_alloc which is true if any
+ * resource allocation is enabled.
+ */
+bool rdt_alloc_capable;
+
 static void
 mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
 static void
@@ -54,7 +67,9 @@ cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
 
 struct rdt_resource rdt_resources_all[] = {
+	[RDT_RESOURCE_L3] =
 	{
+		.rid			= RDT_RESOURCE_L3,
 		.name			= "L3",
 		.domains		= domain_init(RDT_RESOURCE_L3),
 		.msr_base		= IA32_L3_CBM_BASE,
@@ -67,8 +82,11 @@ struct rdt_resource rdt_resources_all[] = {
 		},
 		.parse_ctrlval		= parse_cbm,
 		.format_str		= "%d=%0*x",
+		.fflags			= RFTYPE_RES_CACHE,
 	},
+	[RDT_RESOURCE_L3DATA] =
 	{
+		.rid			= RDT_RESOURCE_L3DATA,
 		.name			= "L3DATA",
 		.domains		= domain_init(RDT_RESOURCE_L3DATA),
 		.msr_base		= IA32_L3_CBM_BASE,
@@ -81,8 +99,11 @@ struct rdt_resource rdt_resources_all[] = {
 		},
 		.parse_ctrlval		= parse_cbm,
 		.format_str		= "%d=%0*x",
+		.fflags			= RFTYPE_RES_CACHE,
 	},
+	[RDT_RESOURCE_L3CODE] =
 	{
+		.rid			= RDT_RESOURCE_L3CODE,
 		.name			= "L3CODE",
 		.domains		= domain_init(RDT_RESOURCE_L3CODE),
 		.msr_base		= IA32_L3_CBM_BASE,
@@ -95,8 +116,11 @@ struct rdt_resource rdt_resources_all[] = {
 		},
 		.parse_ctrlval		= parse_cbm,
 		.format_str		= "%d=%0*x",
+		.fflags			= RFTYPE_RES_CACHE,
 	},
+	[RDT_RESOURCE_L2] =
 	{
+		.rid			= RDT_RESOURCE_L2,
 		.name			= "L2",
 		.domains		= domain_init(RDT_RESOURCE_L2),
 		.msr_base		= IA32_L2_CBM_BASE,
@@ -109,8 +133,11 @@ struct rdt_resource rdt_resources_all[] = {
 		},
 		.parse_ctrlval		= parse_cbm,
 		.format_str		= "%d=%0*x",
+		.fflags			= RFTYPE_RES_CACHE,
 	},
+	[RDT_RESOURCE_MBA] =
 	{
+		.rid			= RDT_RESOURCE_MBA,
 		.name			= "MB",
 		.domains		= domain_init(RDT_RESOURCE_MBA),
 		.msr_base		= IA32_MBA_THRTL_BASE,
@@ -118,6 +145,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.cache_level		= 3,
 		.parse_ctrlval		= parse_bw,
 		.format_str		= "%d=%*d",
+		.fflags			= RFTYPE_RES_MB,
 	},
 };
 
@@ -144,33 +172,28 @@ static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid)
  * is always 20 on hsw server parts. The minimum cache bitmask length
  * allowed for HSW server is always 2 bits. Hardcode all of them.
  */
-static inline bool cache_alloc_hsw_probe(void)
+static inline void cache_alloc_hsw_probe(void)
 {
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_data.x86 == 6 &&
-	    boot_cpu_data.x86_model == INTEL_FAM6_HASWELL_X) {
-		struct rdt_resource *r  = &rdt_resources_all[RDT_RESOURCE_L3];
-		u32 l, h, max_cbm = BIT_MASK(20) - 1;
-
-		if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0))
-			return false;
-		rdmsr(IA32_L3_CBM_BASE, l, h);
+	struct rdt_resource *r  = &rdt_resources_all[RDT_RESOURCE_L3];
+	u32 l, h, max_cbm = BIT_MASK(20) - 1;
 
-		/* If all the bits were set in MSR, return success */
-		if (l != max_cbm)
-			return false;
+	if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0))
+		return;
+	rdmsr(IA32_L3_CBM_BASE, l, h);
 
-		r->num_closid = 4;
-		r->default_ctrl = max_cbm;
-		r->cache.cbm_len = 20;
-		r->cache.min_cbm_bits = 2;
-		r->capable = true;
-		r->enabled = true;
+	/* If all the bits were set in MSR, return success */
+	if (l != max_cbm)
+		return;
 
-		return true;
-	}
+	r->num_closid = 4;
+	r->default_ctrl = max_cbm;
+	r->cache.cbm_len = 20;
+	r->cache.shareable_bits = 0xc0000;
+	r->cache.min_cbm_bits = 2;
+	r->alloc_capable = true;
+	r->alloc_enabled = true;
 
-	return false;
+	rdt_alloc_capable = true;
 }
 
 /*
@@ -213,15 +236,14 @@ static bool rdt_get_mem_config(struct rdt_resource *r)
 			return false;
 	}
 	r->data_width = 3;
-	rdt_get_mba_infofile(r);
 
-	r->capable = true;
-	r->enabled = true;
+	r->alloc_capable = true;
+	r->alloc_enabled = true;
 
 	return true;
 }
 
-static void rdt_get_cache_config(int idx, struct rdt_resource *r)
+static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
 {
 	union cpuid_0x10_1_eax eax;
 	union cpuid_0x10_x_edx edx;
@@ -231,10 +253,10 @@ static void rdt_get_cache_config(int idx, struct rdt_resource *r)
 	r->num_closid = edx.split.cos_max + 1;
 	r->cache.cbm_len = eax.split.cbm_len + 1;
 	r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
+	r->cache.shareable_bits = ebx & r->default_ctrl;
 	r->data_width = (r->cache.cbm_len + 3) / 4;
-	rdt_get_cache_infofile(r);
-	r->capable = true;
-	r->enabled = true;
+	r->alloc_capable = true;
+	r->alloc_enabled = true;
 }
 
 static void rdt_get_cdp_l3_config(int type)
@@ -246,12 +268,12 @@ static void rdt_get_cdp_l3_config(int type)
 	r->cache.cbm_len = r_l3->cache.cbm_len;
 	r->default_ctrl = r_l3->default_ctrl;
 	r->data_width = (r->cache.cbm_len + 3) / 4;
-	r->capable = true;
+	r->alloc_capable = true;
 	/*
 	 * By default, CDP is disabled. CDP can be enabled by mount parameter
 	 * "cdp" during resctrl file system mount time.
 	 */
-	r->enabled = false;
+	r->alloc_enabled = false;
 }
 
 static int get_cache_id(int cpu, int level)
@@ -300,6 +322,19 @@ cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
 		wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]);
 }
 
+struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
+{
+	struct rdt_domain *d;
+
+	list_for_each_entry(d, &r->domains, list) {
+		/* Find the domain that contains this CPU */
+		if (cpumask_test_cpu(cpu, &d->cpu_mask))
+			return d;
+	}
+
+	return NULL;
+}
+
 void rdt_ctrl_update(void *arg)
 {
 	struct msr_param *m = arg;
@@ -307,12 +342,10 @@ void rdt_ctrl_update(void *arg)
 	int cpu = smp_processor_id();
 	struct rdt_domain *d;
 
-	list_for_each_entry(d, &r->domains, list) {
-		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
-			r->msr_update(d, m, r);
-			return;
-		}
+	d = get_domain_from_cpu(cpu, r);
+	if (d) {
+		r->msr_update(d, m, r);
+		return;
 	}
 	pr_warn_once("cpu %d not found in any domain for resource %s\n",
 		     cpu, r->name);
@@ -326,8 +359,8 @@ void rdt_ctrl_update(void *arg)
  * caller, return the first domain whose id is bigger than the input id.
  * The domain list is sorted by id in ascending order.
  */
-static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
-					  struct list_head **pos)
+struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
+				   struct list_head **pos)
 {
 	struct rdt_domain *d;
 	struct list_head *l;
@@ -377,6 +410,44 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
 	return 0;
 }
 
+static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
+{
+	size_t tsize;
+
+	if (is_llc_occupancy_enabled()) {
+		d->rmid_busy_llc = kcalloc(BITS_TO_LONGS(r->num_rmid),
+					   sizeof(unsigned long),
+					   GFP_KERNEL);
+		if (!d->rmid_busy_llc)
+			return -ENOMEM;
+		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
+	}
+	if (is_mbm_total_enabled()) {
+		tsize = sizeof(*d->mbm_total);
+		d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+		if (!d->mbm_total) {
+			kfree(d->rmid_busy_llc);
+			return -ENOMEM;
+		}
+	}
+	if (is_mbm_local_enabled()) {
+		tsize = sizeof(*d->mbm_local);
+		d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+		if (!d->mbm_local) {
+			kfree(d->rmid_busy_llc);
+			kfree(d->mbm_total);
+			return -ENOMEM;
+		}
+	}
+
+	if (is_mbm_enabled()) {
+		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
+		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
+	}
+
+	return 0;
+}
+
 /*
  * domain_add_cpu - Add a cpu to a resource's domain list.
  *
@@ -412,14 +483,26 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 
 	d->id = id;
+	cpumask_set_cpu(cpu, &d->cpu_mask);
 
-	if (domain_setup_ctrlval(r, d)) {
+	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
+		kfree(d);
+		return;
+	}
+
+	if (r->mon_capable && domain_setup_mon_state(r, d)) {
 		kfree(d);
 		return;
 	}
 
-	cpumask_set_cpu(cpu, &d->cpu_mask);
 	list_add_tail(&d->list, add_pos);
+
+	/*
+	 * If resctrl is mounted, add
+	 * per domain monitor data directories.
+	 */
+	if (static_branch_unlikely(&rdt_mon_enable_key))
+		mkdir_mondata_subdir_allrdtgrp(r, d);
 }
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
@@ -435,19 +518,58 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 
 	cpumask_clear_cpu(cpu, &d->cpu_mask);
 	if (cpumask_empty(&d->cpu_mask)) {
+		/*
+		 * If resctrl is mounted, remove all the
+		 * per domain monitor data directories.
+		 */
+		if (static_branch_unlikely(&rdt_mon_enable_key))
+			rmdir_mondata_subdir_allrdtgrp(r, d->id);
 		kfree(d->ctrl_val);
+		kfree(d->rmid_busy_llc);
+		kfree(d->mbm_total);
+		kfree(d->mbm_local);
 		list_del(&d->list);
+		if (is_mbm_enabled())
+			cancel_delayed_work(&d->mbm_over);
+		if (is_llc_occupancy_enabled() &&  has_busy_rmid(r, d)) {
+			/*
+			 * When a package is going down, forcefully
+			 * decrement rmid->ebusy. There is no way to know
+			 * that the L3 was flushed and hence may lead to
+			 * incorrect counts in rare scenarios, but leaving
+			 * the RMID as busy creates RMID leaks if the
+			 * package never comes back.
+			 */
+			__check_limbo(d, true);
+			cancel_delayed_work(&d->cqm_limbo);
+		}
+
 		kfree(d);
+		return;
+	}
+
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3]) {
+		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(int cpu)
+static void clear_closid_rmid(int cpu)
 {
 	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
 
-	per_cpu(cpu_closid, cpu) = 0;
-	state->closid = 0;
-	wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0);
+	state->default_closid = 0;
+	state->default_rmid = 0;
+	state->cur_closid = 0;
+	state->cur_rmid = 0;
+	wrmsr(IA32_PQR_ASSOC, 0, 0);
 }
 
 static int intel_rdt_online_cpu(unsigned int cpu)
@@ -459,12 +581,23 @@ static int intel_rdt_online_cpu(unsigned int cpu)
 		domain_add_cpu(cpu, r);
 	/* The cpu is set in default rdtgroup after online. */
 	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
-	clear_closid(cpu);
+	clear_closid_rmid(cpu);
 	mutex_unlock(&rdtgroup_mutex);
 
 	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 intel_rdt_offline_cpu(unsigned int cpu)
 {
 	struct rdtgroup *rdtgrp;
@@ -474,10 +607,12 @@ static int intel_rdt_offline_cpu(unsigned int cpu)
 	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))
+		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
+			clear_childcpus(rdtgrp, cpu);
 			break;
+		}
 	}
-	clear_closid(cpu);
+	clear_closid_rmid(cpu);
 	mutex_unlock(&rdtgroup_mutex);
 
 	return 0;
@@ -492,7 +627,7 @@ static __init void rdt_init_padding(void)
 	struct rdt_resource *r;
 	int cl;
 
-	for_each_capable_rdt_resource(r) {
+	for_each_alloc_capable_rdt_resource(r) {
 		cl = strlen(r->name);
 		if (cl > max_name_width)
 			max_name_width = cl;
@@ -502,38 +637,153 @@ static __init void rdt_init_padding(void)
 	}
 }
 
-static __init bool get_rdt_resources(void)
+enum {
+	RDT_FLAG_CMT,
+	RDT_FLAG_MBM_TOTAL,
+	RDT_FLAG_MBM_LOCAL,
+	RDT_FLAG_L3_CAT,
+	RDT_FLAG_L3_CDP,
+	RDT_FLAG_L2_CAT,
+	RDT_FLAG_MBA,
+};
+
+#define RDT_OPT(idx, n, f)	\
+[idx] = {			\
+	.name = n,		\
+	.flag = f		\
+}
+
+struct rdt_options {
+	char	*name;
+	int	flag;
+	bool	force_off, force_on;
+};
+
+static struct rdt_options rdt_options[]  __initdata = {
+	RDT_OPT(RDT_FLAG_CMT,	    "cmt",	X86_FEATURE_CQM_OCCUP_LLC),
+	RDT_OPT(RDT_FLAG_MBM_TOTAL, "mbmtotal", X86_FEATURE_CQM_MBM_TOTAL),
+	RDT_OPT(RDT_FLAG_MBM_LOCAL, "mbmlocal", X86_FEATURE_CQM_MBM_LOCAL),
+	RDT_OPT(RDT_FLAG_L3_CAT,    "l3cat",	X86_FEATURE_CAT_L3),
+	RDT_OPT(RDT_FLAG_L3_CDP,    "l3cdp",	X86_FEATURE_CDP_L3),
+	RDT_OPT(RDT_FLAG_L2_CAT,    "l2cat",	X86_FEATURE_CAT_L2),
+	RDT_OPT(RDT_FLAG_MBA,	    "mba",	X86_FEATURE_MBA),
+};
+#define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options)
+
+static int __init set_rdt_options(char *str)
+{
+	struct rdt_options *o;
+	bool force_off;
+	char *tok;
+
+	if (*str == '=')
+		str++;
+	while ((tok = strsep(&str, ",")) != NULL) {
+		force_off = *tok == '!';
+		if (force_off)
+			tok++;
+		for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) {
+			if (strcmp(tok, o->name) == 0) {
+				if (force_off)
+					o->force_off = true;
+				else
+					o->force_on = true;
+				break;
+			}
+		}
+	}
+	return 1;
+}
+__setup("rdt", set_rdt_options);
+
+static bool __init rdt_cpu_has(int flag)
+{
+	bool ret = boot_cpu_has(flag);
+	struct rdt_options *o;
+
+	if (!ret)
+		return ret;
+
+	for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) {
+		if (flag == o->flag) {
+			if (o->force_off)
+				ret = false;
+			if (o->force_on)
+				ret = true;
+			break;
+		}
+	}
+	return ret;
+}
+
+static __init bool get_rdt_alloc_resources(void)
 {
 	bool ret = false;
 
-	if (cache_alloc_hsw_probe())
+	if (rdt_alloc_capable)
 		return true;
 
 	if (!boot_cpu_has(X86_FEATURE_RDT_A))
 		return false;
 
-	if (boot_cpu_has(X86_FEATURE_CAT_L3)) {
-		rdt_get_cache_config(1, &rdt_resources_all[RDT_RESOURCE_L3]);
-		if (boot_cpu_has(X86_FEATURE_CDP_L3)) {
+	if (rdt_cpu_has(X86_FEATURE_CAT_L3)) {
+		rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]);
+		if (rdt_cpu_has(X86_FEATURE_CDP_L3)) {
 			rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA);
 			rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE);
 		}
 		ret = true;
 	}
-	if (boot_cpu_has(X86_FEATURE_CAT_L2)) {
+	if (rdt_cpu_has(X86_FEATURE_CAT_L2)) {
 		/* CPUID 0x10.2 fields are same format at 0x10.1 */
-		rdt_get_cache_config(2, &rdt_resources_all[RDT_RESOURCE_L2]);
+		rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]);
 		ret = true;
 	}
 
-	if (boot_cpu_has(X86_FEATURE_MBA)) {
+	if (rdt_cpu_has(X86_FEATURE_MBA)) {
 		if (rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA]))
 			ret = true;
 	}
-
 	return ret;
 }
 
+static __init bool get_rdt_mon_resources(void)
+{
+	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC))
+		rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID);
+	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL))
+		rdt_mon_features |= (1 << QOS_L3_MBM_TOTAL_EVENT_ID);
+	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL))
+		rdt_mon_features |= (1 << QOS_L3_MBM_LOCAL_EVENT_ID);
+
+	if (!rdt_mon_features)
+		return false;
+
+	return !rdt_get_mon_l3_config(&rdt_resources_all[RDT_RESOURCE_L3]);
+}
+
+static __init void rdt_quirks(void)
+{
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_HASWELL_X:
+		if (!rdt_options[RDT_FLAG_L3_CAT].force_off)
+			cache_alloc_hsw_probe();
+		break;
+	case INTEL_FAM6_SKYLAKE_X:
+		if (boot_cpu_data.x86_mask <= 4)
+			set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat");
+	}
+}
+
+static __init bool get_rdt_resources(void)
+{
+	rdt_quirks();
+	rdt_alloc_capable = get_rdt_alloc_resources();
+	rdt_mon_capable = get_rdt_mon_resources();
+
+	return (rdt_mon_capable || rdt_alloc_capable);
+}
+
 static int __init intel_rdt_late_init(void)
 {
 	struct rdt_resource *r;
@@ -556,9 +806,12 @@ static int __init intel_rdt_late_init(void)
 		return ret;
 	}
 
-	for_each_capable_rdt_resource(r)
+	for_each_alloc_capable_rdt_resource(r)
 		pr_info("Intel RDT %s allocation detected\n", r->name);
 
+	for_each_mon_capable_rdt_resource(r)
+		pr_info("Intel RDT %s monitoring detected\n", r->name);
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
new file mode 100644
index 000000000000..ebaddaeef023
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -0,0 +1,440 @@
+#ifndef _ASM_X86_INTEL_RDT_H
+#define _ASM_X86_INTEL_RDT_H
+
+#include <linux/sched.h>
+#include <linux/kernfs.h>
+#include <linux/jump_label.h>
+
+#define IA32_L3_QOS_CFG		0xc81
+#define IA32_L3_CBM_BASE	0xc90
+#define IA32_L2_CBM_BASE	0xd10
+#define IA32_MBA_THRTL_BASE	0xd50
+
+#define L3_QOS_CDP_ENABLE	0x01ULL
+
+/*
+ * Event IDs are used to program IA32_QM_EVTSEL before reading event
+ * counter from IA32_QM_CTR
+ */
+#define QOS_L3_OCCUP_EVENT_ID		0x01
+#define QOS_L3_MBM_TOTAL_EVENT_ID	0x02
+#define QOS_L3_MBM_LOCAL_EVENT_ID	0x03
+
+#define CQM_LIMBOCHECK_INTERVAL	1000
+
+#define MBM_CNTR_WIDTH			24
+#define MBM_OVERFLOW_INTERVAL		1000
+
+#define RMID_VAL_ERROR			BIT_ULL(63)
+#define RMID_VAL_UNAVAIL		BIT_ULL(62)
+
+DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
+
+/**
+ * struct mon_evt - Entry in the event list of a resource
+ * @evtid:		event id
+ * @name:		name of the event
+ */
+struct mon_evt {
+	u32			evtid;
+	char			*name;
+	struct list_head	list;
+};
+
+/**
+ * struct mon_data_bits - Monitoring details for each event file
+ * @rid:               Resource id associated with the event file.
+ * @evtid:             Event id associated with the event file
+ * @domid:             The domain to which the event file belongs
+ */
+union mon_data_bits {
+	void *priv;
+	struct {
+		unsigned int rid	: 10;
+		unsigned int evtid	: 8;
+		unsigned int domid	: 14;
+	} u;
+};
+
+struct rmid_read {
+	struct rdtgroup		*rgrp;
+	struct rdt_domain	*d;
+	int			evtid;
+	bool			first;
+	u64			val;
+};
+
+extern unsigned int intel_cqm_threshold;
+extern bool rdt_alloc_capable;
+extern bool rdt_mon_capable;
+extern unsigned int rdt_mon_features;
+
+enum rdt_group_type {
+	RDTCTRL_GROUP = 0,
+	RDTMON_GROUP,
+	RDT_NUM_GROUP,
+};
+
+/**
+ * struct mongroup - store mon group's data in resctrl fs.
+ * @mon_data_kn		kernlfs node for the mon_data directory
+ * @parent:			parent rdtgrp
+ * @crdtgrp_list:		child rdtgroup node list
+ * @rmid:			rmid for this rdtgroup
+ */
+struct mongroup {
+	struct kernfs_node	*mon_data_kn;
+	struct rdtgroup		*parent;
+	struct list_head	crdtgrp_list;
+	u32			rmid;
+};
+
+/**
+ * struct rdtgroup - store rdtgroup's data in resctrl file system.
+ * @kn:				kernfs node
+ * @rdtgroup_list:		linked list for all rdtgroups
+ * @closid:			closid for this rdtgroup
+ * @cpu_mask:			CPUs assigned to this rdtgroup
+ * @flags:			status bits
+ * @waitcount:			how many cpus expect to find this
+ *				group when they acquire rdtgroup_mutex
+ * @type:			indicates type of this rdtgroup - either
+ *				monitor only or ctrl_mon group
+ * @mon:			mongroup related data
+ */
+struct rdtgroup {
+	struct kernfs_node	*kn;
+	struct list_head	rdtgroup_list;
+	u32			closid;
+	struct cpumask		cpu_mask;
+	int			flags;
+	atomic_t		waitcount;
+	enum rdt_group_type	type;
+	struct mongroup		mon;
+};
+
+/* rdtgroup.flags */
+#define	RDT_DELETED		1
+
+/* rftype.flags */
+#define RFTYPE_FLAGS_CPUS_LIST	1
+
+/*
+ * Define the file type flags for base and info directories.
+ */
+#define RFTYPE_INFO			BIT(0)
+#define RFTYPE_BASE			BIT(1)
+#define RF_CTRLSHIFT			4
+#define RF_MONSHIFT			5
+#define RFTYPE_CTRL			BIT(RF_CTRLSHIFT)
+#define RFTYPE_MON			BIT(RF_MONSHIFT)
+#define RFTYPE_RES_CACHE		BIT(8)
+#define RFTYPE_RES_MB			BIT(9)
+#define RF_CTRL_INFO			(RFTYPE_INFO | RFTYPE_CTRL)
+#define RF_MON_INFO			(RFTYPE_INFO | RFTYPE_MON)
+#define RF_CTRL_BASE			(RFTYPE_BASE | RFTYPE_CTRL)
+
+/* List of all resource groups */
+extern struct list_head rdt_all_groups;
+
+extern int max_name_width, max_data_width;
+
+int __init rdtgroup_init(void);
+
+/**
+ * struct rftype - describe each file in the resctrl file system
+ * @name:	File name
+ * @mode:	Access mode
+ * @kf_ops:	File operations
+ * @flags:	File specific RFTYPE_FLAGS_* flags
+ * @fflags:	File specific RF_* or RFTYPE_* flags
+ * @seq_show:	Show content of the file
+ * @write:	Write to the file
+ */
+struct rftype {
+	char			*name;
+	umode_t			mode;
+	struct kernfs_ops	*kf_ops;
+	unsigned long		flags;
+	unsigned long		fflags;
+
+	int (*seq_show)(struct kernfs_open_file *of,
+			struct seq_file *sf, void *v);
+	/*
+	 * write() is the generic write callback which maps directly to
+	 * kernfs write operation and overrides all other operations.
+	 * Maximum write size is determined by ->max_write_len.
+	 */
+	ssize_t (*write)(struct kernfs_open_file *of,
+			 char *buf, size_t nbytes, loff_t off);
+};
+
+/**
+ * struct mbm_state - status for each MBM counter in each domain
+ * @chunks:	Total data moved (multiply by rdt_group.mon_scale to get bytes)
+ * @prev_msr	Value of IA32_QM_CTR for this RMID last time we read it
+ */
+struct mbm_state {
+	u64	chunks;
+	u64	prev_msr;
+};
+
+/**
+ * struct rdt_domain - group of cpus sharing an RDT resource
+ * @list:	all instances of this resource
+ * @id:		unique id for this instance
+ * @cpu_mask:	which cpus share this resource
+ * @rmid_busy_llc:
+ *		bitmap of which limbo RMIDs are above threshold
+ * @mbm_total:	saved state for MBM total bandwidth
+ * @mbm_local:	saved state for MBM local bandwidth
+ * @mbm_over:	worker to periodically read MBM h/w counters
+ * @cqm_limbo:	worker to periodically read CQM h/w counters
+ * @mbm_work_cpu:
+ *		worker cpu for MBM h/w counters
+ * @cqm_work_cpu:
+ *		worker cpu for CQM h/w counters
+ * @ctrl_val:	array of cache or mem ctrl values (indexed by CLOSID)
+ * @new_ctrl:	new ctrl value to be loaded
+ * @have_new_ctrl: did user provide new_ctrl for this domain
+ */
+struct rdt_domain {
+	struct list_head	list;
+	int			id;
+	struct cpumask		cpu_mask;
+	unsigned long		*rmid_busy_llc;
+	struct mbm_state	*mbm_total;
+	struct mbm_state	*mbm_local;
+	struct delayed_work	mbm_over;
+	struct delayed_work	cqm_limbo;
+	int			mbm_work_cpu;
+	int			cqm_work_cpu;
+	u32			*ctrl_val;
+	u32			new_ctrl;
+	bool			have_new_ctrl;
+};
+
+/**
+ * struct msr_param - set a range of MSRs from a domain
+ * @res:       The resource to use
+ * @low:       Beginning index from base MSR
+ * @high:      End index
+ */
+struct msr_param {
+	struct rdt_resource	*res;
+	int			low;
+	int			high;
+};
+
+/**
+ * struct rdt_cache - Cache allocation related data
+ * @cbm_len:		Length of the cache bit mask
+ * @min_cbm_bits:	Minimum number of consecutive bits to be set
+ * @cbm_idx_mult:	Multiplier of CBM index
+ * @cbm_idx_offset:	Offset of CBM index. CBM index is computed by:
+ *			closid * cbm_idx_multi + cbm_idx_offset
+ *			in a cache bit mask
+ * @shareable_bits:	Bitmask of shareable resource with other
+ *			executing entities
+ */
+struct rdt_cache {
+	unsigned int	cbm_len;
+	unsigned int	min_cbm_bits;
+	unsigned int	cbm_idx_mult;
+	unsigned int	cbm_idx_offset;
+	unsigned int	shareable_bits;
+};
+
+/**
+ * struct rdt_membw - Memory bandwidth allocation related data
+ * @max_delay:		Max throttle delay. Delay is the hardware
+ *			representation for memory bandwidth.
+ * @min_bw:		Minimum memory bandwidth percentage user can request
+ * @bw_gran:		Granularity at which the memory bandwidth is allocated
+ * @delay_linear:	True if memory B/W delay is in linear scale
+ * @mb_map:		Mapping of memory B/W percentage to memory B/W delay
+ */
+struct rdt_membw {
+	u32		max_delay;
+	u32		min_bw;
+	u32		bw_gran;
+	u32		delay_linear;
+	u32		*mb_map;
+};
+
+static inline bool is_llc_occupancy_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID));
+}
+
+static inline bool is_mbm_total_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID));
+}
+
+static inline bool is_mbm_local_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID));
+}
+
+static inline bool is_mbm_enabled(void)
+{
+	return (is_mbm_total_enabled() || is_mbm_local_enabled());
+}
+
+static inline bool is_mbm_event(int e)
+{
+	return (e >= QOS_L3_MBM_TOTAL_EVENT_ID &&
+		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
+}
+
+/**
+ * struct rdt_resource - attributes of an RDT resource
+ * @rid:		The index of the resource
+ * @alloc_enabled:	Is allocation enabled on this machine
+ * @mon_enabled:		Is monitoring enabled for this feature
+ * @alloc_capable:	Is allocation available on this machine
+ * @mon_capable:		Is monitor feature available on this machine
+ * @name:		Name to use in "schemata" file
+ * @num_closid:		Number of CLOSIDs available
+ * @cache_level:	Which cache level defines scope of this resource
+ * @default_ctrl:	Specifies default cache cbm or memory B/W percent.
+ * @msr_base:		Base MSR address for CBMs
+ * @msr_update:		Function pointer to update QOS MSRs
+ * @data_width:		Character width of data when displaying
+ * @domains:		All domains for this resource
+ * @cache:		Cache allocation related data
+ * @format_str:		Per resource format string to show domain value
+ * @parse_ctrlval:	Per resource function pointer to parse control values
+ * @evt_list:			List of monitoring events
+ * @num_rmid:			Number of RMIDs available
+ * @mon_scale:			cqm counter * mon_scale = occupancy in bytes
+ * @fflags:			flags to choose base and info files
+ */
+struct rdt_resource {
+	int			rid;
+	bool			alloc_enabled;
+	bool			mon_enabled;
+	bool			alloc_capable;
+	bool			mon_capable;
+	char			*name;
+	int			num_closid;
+	int			cache_level;
+	u32			default_ctrl;
+	unsigned int		msr_base;
+	void (*msr_update)	(struct rdt_domain *d, struct msr_param *m,
+				 struct rdt_resource *r);
+	int			data_width;
+	struct list_head	domains;
+	struct rdt_cache	cache;
+	struct rdt_membw	membw;
+	const char		*format_str;
+	int (*parse_ctrlval)	(char *buf, struct rdt_resource *r,
+				 struct rdt_domain *d);
+	struct list_head	evt_list;
+	int			num_rmid;
+	unsigned int		mon_scale;
+	unsigned long		fflags;
+};
+
+int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d);
+int parse_bw(char *buf, struct rdt_resource *r,  struct rdt_domain *d);
+
+extern struct mutex rdtgroup_mutex;
+
+extern struct rdt_resource rdt_resources_all[];
+extern struct rdtgroup rdtgroup_default;
+DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
+
+int __init rdtgroup_init(void);
+
+enum {
+	RDT_RESOURCE_L3,
+	RDT_RESOURCE_L3DATA,
+	RDT_RESOURCE_L3CODE,
+	RDT_RESOURCE_L2,
+	RDT_RESOURCE_MBA,
+
+	/* Must be the last */
+	RDT_NUM_RESOURCES,
+};
+
+#define for_each_capable_rdt_resource(r)				      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++)							      \
+		if (r->alloc_capable || r->mon_capable)
+
+#define for_each_alloc_capable_rdt_resource(r)				      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++)							      \
+		if (r->alloc_capable)
+
+#define for_each_mon_capable_rdt_resource(r)				      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++)							      \
+		if (r->mon_capable)
+
+#define for_each_alloc_enabled_rdt_resource(r)				      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++)							      \
+		if (r->alloc_enabled)
+
+#define for_each_mon_enabled_rdt_resource(r)				      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++)							      \
+		if (r->mon_enabled)
+
+/* CPUID.(EAX=10H, ECX=ResID=1).EAX */
+union cpuid_0x10_1_eax {
+	struct {
+		unsigned int cbm_len:5;
+	} split;
+	unsigned int full;
+};
+
+/* CPUID.(EAX=10H, ECX=ResID=3).EAX */
+union cpuid_0x10_3_eax {
+	struct {
+		unsigned int max_delay:12;
+	} split;
+	unsigned int full;
+};
+
+/* CPUID.(EAX=10H, ECX=ResID).EDX */
+union cpuid_0x10_x_edx {
+	struct {
+		unsigned int cos_max:16;
+	} split;
+	unsigned int full;
+};
+
+void rdt_ctrl_update(void *arg);
+struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
+void rdtgroup_kn_unlock(struct kernfs_node *kn);
+struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
+				   struct list_head **pos);
+ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off);
+int rdtgroup_schemata_show(struct kernfs_open_file *of,
+			   struct seq_file *s, void *v);
+struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
+int alloc_rmid(void);
+void free_rmid(u32 rmid);
+int rdt_get_mon_l3_config(struct rdt_resource *r);
+void mon_event_count(void *info);
+int rdtgroup_mondata_show(struct seq_file *m, void *arg);
+void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+				    unsigned int dom_id);
+void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+				    struct rdt_domain *d);
+void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
+		    struct rdtgroup *rdtgrp, int evtid, int first);
+void mbm_setup_overflow_handler(struct rdt_domain *dom,
+				unsigned long delay_ms);
+void mbm_handle_overflow(struct work_struct *work);
+void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
+void cqm_handle_limbo(struct work_struct *work);
+bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
+void __check_limbo(struct rdt_domain *d, bool force_free);
+
+#endif /* _ASM_X86_INTEL_RDT_H */
diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 406d7a6532f9..f6ea94f8954a 100644
--- a/arch/x86/kernel/cpu/intel_rdt_schemata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -26,7 +26,7 @@
 #include <linux/kernfs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
-#include <asm/intel_rdt.h>
+#include "intel_rdt.h"
 
 /*
  * Check whether MBA bandwidth percentage value is correct. The value is
@@ -192,7 +192,7 @@ static int rdtgroup_parse_resource(char *resname, char *tok, int closid)
 {
 	struct rdt_resource *r;
 
-	for_each_enabled_rdt_resource(r) {
+	for_each_alloc_enabled_rdt_resource(r) {
 		if (!strcmp(resname, r->name) && closid < r->num_closid)
 			return parse_line(tok, r);
 	}
@@ -221,7 +221,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 
 	closid = rdtgrp->closid;
 
-	for_each_enabled_rdt_resource(r) {
+	for_each_alloc_enabled_rdt_resource(r) {
 		list_for_each_entry(dom, &r->domains, list)
 			dom->have_new_ctrl = false;
 	}
@@ -237,7 +237,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 			goto out;
 	}
 
-	for_each_enabled_rdt_resource(r) {
+	for_each_alloc_enabled_rdt_resource(r) {
 		ret = update_domains(r, closid);
 		if (ret)
 			goto out;
@@ -269,12 +269,13 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 {
 	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
-	int closid, ret = 0;
+	int ret = 0;
+	u32 closid;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (rdtgrp) {
 		closid = rdtgrp->closid;
-		for_each_enabled_rdt_resource(r) {
+		for_each_alloc_enabled_rdt_resource(r) {
 			if (closid < r->num_closid)
 				show_doms(s, r, closid);
 		}
@@ -284,3 +285,57 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 	rdtgroup_kn_unlock(of->kn);
 	return ret;
 }
+
+void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
+		    struct rdtgroup *rdtgrp, int evtid, int first)
+{
+	/*
+	 * setup the parameters to send to the IPI to read the data.
+	 */
+	rr->rgrp = rdtgrp;
+	rr->evtid = evtid;
+	rr->d = d;
+	rr->val = 0;
+	rr->first = first;
+
+	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+}
+
+int rdtgroup_mondata_show(struct seq_file *m, void *arg)
+{
+	struct kernfs_open_file *of = m->private;
+	u32 resid, evtid, domid;
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	union mon_data_bits md;
+	struct rdt_domain *d;
+	struct rmid_read rr;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	md.priv = of->kn->priv;
+	resid = md.u.rid;
+	domid = md.u.domid;
+	evtid = md.u.evtid;
+
+	r = &rdt_resources_all[resid];
+	d = rdt_find_domain(r, domid, NULL);
+	if (!d) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	mon_event_read(&rr, d, rdtgrp, evtid, false);
+
+	if (rr.val & RMID_VAL_ERROR)
+		seq_puts(m, "Error\n");
+	else if (rr.val & RMID_VAL_UNAVAIL)
+		seq_puts(m, "Unavailable\n");
+	else
+		seq_printf(m, "%llu\n", rr.val * r->mon_scale);
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+	return ret;
+}
diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c
new file mode 100644
index 000000000000..30827510094b
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c
@@ -0,0 +1,499 @@
+/*
+ * Resource Director Technology(RDT)
+ * - Monitoring code
+ *
+ * Copyright (C) 2017 Intel Corporation
+ *
+ * Author:
+ *    Vikas Shivappa <vikas.shivappa@intel.com>
+ *
+ * This replaces the cqm.c based on perf but we reuse a lot of
+ * code and datastructures originally from Peter Zijlstra and Matt Fleming.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * More information about RDT be found in the Intel (R) x86 Architecture
+ * Software Developer Manual June 2016, volume 3, section 17.17.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <asm/cpu_device_id.h>
+#include "intel_rdt.h"
+
+#define MSR_IA32_QM_CTR		0x0c8e
+#define MSR_IA32_QM_EVTSEL		0x0c8d
+
+struct rmid_entry {
+	u32				rmid;
+	int				busy;
+	struct list_head		list;
+};
+
+/**
+ * @rmid_free_lru    A least recently used list of free RMIDs
+ *     These RMIDs are guaranteed to have an occupancy less than the
+ *     threshold occupancy
+ */
+static LIST_HEAD(rmid_free_lru);
+
+/**
+ * @rmid_limbo_count     count of currently unused but (potentially)
+ *     dirty RMIDs.
+ *     This counts RMIDs that no one is currently using but that
+ *     may have a occupancy value > intel_cqm_threshold. User can change
+ *     the threshold occupancy value.
+ */
+unsigned int rmid_limbo_count;
+
+/**
+ * @rmid_entry - The entry in the limbo and free lists.
+ */
+static struct rmid_entry	*rmid_ptrs;
+
+/*
+ * Global boolean for rdt_monitor which is true if any
+ * resource monitoring is enabled.
+ */
+bool rdt_mon_capable;
+
+/*
+ * Global to indicate which monitoring events are enabled.
+ */
+unsigned int rdt_mon_features;
+
+/*
+ * This is the threshold cache occupancy at which we will consider an
+ * RMID available for re-allocation.
+ */
+unsigned int intel_cqm_threshold;
+
+static inline struct rmid_entry *__rmid_entry(u32 rmid)
+{
+	struct rmid_entry *entry;
+
+	entry = &rmid_ptrs[rmid];
+	WARN_ON(entry->rmid != rmid);
+
+	return entry;
+}
+
+static u64 __rmid_read(u32 rmid, u32 eventid)
+{
+	u64 val;
+
+	/*
+	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
+	 * with a valid event code for supported resource type and the bits
+	 * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
+	 * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
+	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
+	 * are error bits.
+	 */
+	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+	rdmsrl(MSR_IA32_QM_CTR, val);
+
+	return val;
+}
+
+static bool rmid_dirty(struct rmid_entry *entry)
+{
+	u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
+
+	return val >= intel_cqm_threshold;
+}
+
+/*
+ * 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
+ * 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)
+{
+	struct rmid_entry *entry;
+	struct rdt_resource *r;
+	u32 crmid = 1, nrmid;
+
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	/*
+	 * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
+	 * are marked as busy for occupancy < threshold. If the occupancy
+	 * is less than the threshold decrement the busy counter of the
+	 * 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)
+			break;
+
+		entry = __rmid_entry(nrmid);
+		if (force_free || !rmid_dirty(entry)) {
+			clear_bit(entry->rmid, d->rmid_busy_llc);
+			if (!--entry->busy) {
+				rmid_limbo_count--;
+				list_add_tail(&entry->list, &rmid_free_lru);
+			}
+		}
+		crmid = nrmid + 1;
+	}
+}
+
+bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d)
+{
+	return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid;
+}
+
+/*
+ * 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.
+ */
+int alloc_rmid(void)
+{
+	struct rmid_entry *entry;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (list_empty(&rmid_free_lru))
+		return rmid_limbo_count ? -EBUSY : -ENOSPC;
+
+	entry = list_first_entry(&rmid_free_lru,
+				 struct rmid_entry, list);
+	list_del(&entry->list);
+
+	return entry->rmid;
+}
+
+static void add_rmid_to_limbo(struct rmid_entry *entry)
+{
+	struct rdt_resource *r;
+	struct rdt_domain *d;
+	int cpu;
+	u64 val;
+
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	entry->busy = 0;
+	cpu = get_cpu();
+	list_for_each_entry(d, &r->domains, list) {
+		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
+			val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
+			if (val <= intel_cqm_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);
+		entry->busy++;
+	}
+	put_cpu();
+
+	if (entry->busy)
+		rmid_limbo_count++;
+	else
+		list_add_tail(&entry->list, &rmid_free_lru);
+}
+
+void free_rmid(u32 rmid)
+{
+	struct rmid_entry *entry;
+
+	if (!rmid)
+		return;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	entry = __rmid_entry(rmid);
+
+	if (is_llc_occupancy_enabled())
+		add_rmid_to_limbo(entry);
+	else
+		list_add_tail(&entry->list, &rmid_free_lru);
+}
+
+static int __mon_event_count(u32 rmid, struct rmid_read *rr)
+{
+	u64 chunks, shift, tval;
+	struct mbm_state *m;
+
+	tval = __rmid_read(rmid, rr->evtid);
+	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
+		rr->val = tval;
+		return -EINVAL;
+	}
+	switch (rr->evtid) {
+	case QOS_L3_OCCUP_EVENT_ID:
+		rr->val += tval;
+		return 0;
+	case QOS_L3_MBM_TOTAL_EVENT_ID:
+		m = &rr->d->mbm_total[rmid];
+		break;
+	case QOS_L3_MBM_LOCAL_EVENT_ID:
+		m = &rr->d->mbm_local[rmid];
+		break;
+	default:
+		/*
+		 * Code would never reach here because
+		 * an invalid event id would fail the __rmid_read.
+		 */
+		return -EINVAL;
+	}
+
+	if (rr->first) {
+		m->prev_msr = tval;
+		m->chunks = 0;
+		return 0;
+	}
+
+	shift = 64 - MBM_CNTR_WIDTH;
+	chunks = (tval << shift) - (m->prev_msr << shift);
+	chunks >>= shift;
+	m->chunks += chunks;
+	m->prev_msr = tval;
+
+	rr->val += m->chunks;
+	return 0;
+}
+
+/*
+ * This is called via IPI to read the CQM/MBM counters
+ * on a domain.
+ */
+void mon_event_count(void *info)
+{
+	struct rdtgroup *rdtgrp, *entry;
+	struct rmid_read *rr = info;
+	struct list_head *head;
+
+	rdtgrp = rr->rgrp;
+
+	if (__mon_event_count(rdtgrp->mon.rmid, rr))
+		return;
+
+	/*
+	 * For Ctrl groups read data from child monitor groups.
+	 */
+	head = &rdtgrp->mon.crdtgrp_list;
+
+	if (rdtgrp->type == RDTCTRL_GROUP) {
+		list_for_each_entry(entry, head, mon.crdtgrp_list) {
+			if (__mon_event_count(entry->mon.rmid, rr))
+				return;
+		}
+	}
+}
+
+static void mbm_update(struct rdt_domain *d, int rmid)
+{
+	struct rmid_read rr;
+
+	rr.first = false;
+	rr.d = d;
+
+	/*
+	 * This is protected from concurrent reads from user
+	 * as both the user and we hold the global mutex.
+	 */
+	if (is_mbm_total_enabled()) {
+		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
+		__mon_event_count(rmid, &rr);
+	}
+	if (is_mbm_local_enabled()) {
+		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
+		__mon_event_count(rmid, &rr);
+	}
+}
+
+/*
+ * Handler to scan the limbo list and move the RMIDs
+ * to free list whose occupancy < threshold_occupancy.
+ */
+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;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+	d = get_domain_from_cpu(cpu, r);
+
+	if (!d) {
+		pr_warn_once("Failure to get domain for limbo worker\n");
+		goto out_unlock;
+	}
+
+	__check_limbo(d, false);
+
+	if (has_busy_rmid(r, d))
+		schedule_delayed_work_on(cpu, &d->cqm_limbo, delay);
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+{
+	unsigned long delay = msecs_to_jiffies(delay_ms);
+	struct rdt_resource *r;
+	int cpu;
+
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	cpu = cpumask_any(&dom->cpu_mask);
+	dom->cqm_work_cpu = cpu;
+
+	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_domain *d;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	if (!static_branch_likely(&rdt_enable_key))
+		goto out_unlock;
+
+	d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]);
+	if (!d)
+		goto out_unlock;
+
+	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
+		mbm_update(d, prgrp->mon.rmid);
+
+		head = &prgrp->mon.crdtgrp_list;
+		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
+			mbm_update(d, crgrp->mon.rmid);
+	}
+
+	schedule_delayed_work_on(cpu, &d->mbm_over, delay);
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
+{
+	unsigned long delay = msecs_to_jiffies(delay_ms);
+	int cpu;
+
+	if (!static_branch_likely(&rdt_enable_key))
+		return;
+	cpu = cpumask_any(&dom->cpu_mask);
+	dom->mbm_work_cpu = cpu;
+	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
+}
+
+static int dom_data_init(struct rdt_resource *r)
+{
+	struct rmid_entry *entry = NULL;
+	int i, nr_rmids;
+
+	nr_rmids = r->num_rmid;
+	rmid_ptrs = kcalloc(nr_rmids, sizeof(struct rmid_entry), GFP_KERNEL);
+	if (!rmid_ptrs)
+		return -ENOMEM;
+
+	for (i = 0; i < nr_rmids; i++) {
+		entry = &rmid_ptrs[i];
+		INIT_LIST_HEAD(&entry->list);
+
+		entry->rmid = i;
+		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.
+	 */
+	entry = __rmid_entry(0);
+	list_del(&entry->list);
+
+	return 0;
+}
+
+static struct mon_evt llc_occupancy_event = {
+	.name		= "llc_occupancy",
+	.evtid		= QOS_L3_OCCUP_EVENT_ID,
+};
+
+static struct mon_evt mbm_total_event = {
+	.name		= "mbm_total_bytes",
+	.evtid		= QOS_L3_MBM_TOTAL_EVENT_ID,
+};
+
+static struct mon_evt mbm_local_event = {
+	.name		= "mbm_local_bytes",
+	.evtid		= QOS_L3_MBM_LOCAL_EVENT_ID,
+};
+
+/*
+ * Initialize the event list for the resource.
+ *
+ * Note that MBM events are also part of RDT_RESOURCE_L3 resource
+ * because as per the SDM the total and local memory bandwidth
+ * are enumerated as part of L3 monitoring.
+ */
+static void l3_mon_evt_init(struct rdt_resource *r)
+{
+	INIT_LIST_HEAD(&r->evt_list);
+
+	if (is_llc_occupancy_enabled())
+		list_add_tail(&llc_occupancy_event.list, &r->evt_list);
+	if (is_mbm_total_enabled())
+		list_add_tail(&mbm_total_event.list, &r->evt_list);
+	if (is_mbm_local_enabled())
+		list_add_tail(&mbm_local_event.list, &r->evt_list);
+}
+
+int rdt_get_mon_l3_config(struct rdt_resource *r)
+{
+	int ret;
+
+	r->mon_scale = boot_cpu_data.x86_cache_occ_scale;
+	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
+
+	/*
+	 * A reasonable upper limit on the max threshold is the number
+	 * of lines tagged per RMID if all RMIDs have the same number of
+	 * lines tagged in the LLC.
+	 *
+	 * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC.
+	 */
+	intel_cqm_threshold = boot_cpu_data.x86_cache_size * 1024 / r->num_rmid;
+
+	/* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */
+	intel_cqm_threshold /= r->mon_scale;
+
+	ret = dom_data_init(r);
+	if (ret)
+		return ret;
+
+	l3_mon_evt_init(r);
+
+	r->mon_capable = true;
+	r->mon_enabled = true;
+
+	return 0;
+}
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 9257bd9dc664..a869d4a073c5 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -32,17 +32,25 @@
 
 #include <uapi/linux/magic.h>
 
-#include <asm/intel_rdt.h>
-#include <asm/intel_rdt_common.h>
+#include <asm/intel_rdt_sched.h>
+#include "intel_rdt.h"
 
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
-struct kernfs_root *rdt_root;
+DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
+DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
+static struct kernfs_root *rdt_root;
 struct rdtgroup rdtgroup_default;
 LIST_HEAD(rdt_all_groups);
 
 /* Kernel fs node for "info" directory under root */
 static struct kernfs_node *kn_info;
 
+/* Kernel fs node for "mon_groups" directory under root */
+static struct kernfs_node *kn_mongrp;
+
+/* Kernel fs node for "mon_data" directory under root */
+static struct kernfs_node *kn_mondata;
+
 /*
  * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
  * we can keep a bitmap of free CLOSIDs in a single integer.
@@ -66,7 +74,7 @@ static void closid_init(void)
 	int rdt_min_closid = 32;
 
 	/* Compute rdt_min_closid across all resources */
-	for_each_enabled_rdt_resource(r)
+	for_each_alloc_enabled_rdt_resource(r)
 		rdt_min_closid = min(rdt_min_closid, r->num_closid);
 
 	closid_free_map = BIT_MASK(rdt_min_closid) - 1;
@@ -75,9 +83,9 @@ static void closid_init(void)
 	closid_free_map &= ~1;
 }
 
-int closid_alloc(void)
+static int closid_alloc(void)
 {
-	int closid = ffs(closid_free_map);
+	u32 closid = ffs(closid_free_map);
 
 	if (closid == 0)
 		return -ENOSPC;
@@ -125,28 +133,6 @@ static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
 	return 0;
 }
 
-static int rdtgroup_add_files(struct kernfs_node *kn, struct rftype *rfts,
-			      int len)
-{
-	struct rftype *rft;
-	int ret;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	for (rft = rfts; rft < rfts + len; rft++) {
-		ret = rdtgroup_add_file(kn, rft);
-		if (ret)
-			goto error;
-	}
-
-	return 0;
-error:
-	pr_warn("Failed to add %s, err=%d\n", rft->name, ret);
-	while (--rft >= rfts)
-		kernfs_remove_by_name(kn, rft->name);
-	return ret;
-}
-
 static int rdtgroup_seqfile_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
@@ -174,6 +160,11 @@ static struct kernfs_ops rdtgroup_kf_single_ops = {
 	.seq_show		= rdtgroup_seqfile_show,
 };
 
+static struct kernfs_ops kf_mondata_ops = {
+	.atomic_write_len	= PAGE_SIZE,
+	.seq_show		= rdtgroup_mondata_show,
+};
+
 static bool is_cpu_list(struct kernfs_open_file *of)
 {
 	struct rftype *rft = of->kn->priv;
@@ -203,13 +194,18 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 /*
  * This is safe against intel_rdt_sched_in() called from __switch_to()
  * because __switch_to() is executed with interrupts disabled. A local call
- * from rdt_update_closid() is proteced against __switch_to() because
+ * from update_closid_rmid() is proteced against __switch_to() because
  * preemption is disabled.
  */
-static void rdt_update_cpu_closid(void *closid)
+static void update_cpu_closid_rmid(void *info)
 {
-	if (closid)
-		this_cpu_write(cpu_closid, *(int *)closid);
+	struct rdtgroup *r = info;
+
+	if (r) {
+		this_cpu_write(pqr_state.default_closid, r->closid);
+		this_cpu_write(pqr_state.default_rmid, r->mon.rmid);
+	}
+
 	/*
 	 * We cannot unconditionally write the MSR because the current
 	 * executing task might have its own closid selected. Just reuse
@@ -221,28 +217,128 @@ static void rdt_update_cpu_closid(void *closid)
 /*
  * Update the PGR_ASSOC MSR on all cpus in @cpu_mask,
  *
- * Per task closids must have been set up before calling this function.
- *
- * The per cpu closids are updated with the smp function call, when @closid
- * is not NULL. If @closid is NULL then all affected percpu closids must
- * have been set up before calling this function.
+ * Per task closids/rmids must have been set up before calling this function.
  */
 static void
-rdt_update_closid(const struct cpumask *cpu_mask, int *closid)
+update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r)
 {
 	int cpu = get_cpu();
 
 	if (cpumask_test_cpu(cpu, cpu_mask))
-		rdt_update_cpu_closid(closid);
-	smp_call_function_many(cpu_mask, rdt_update_cpu_closid, closid, 1);
+		update_cpu_closid_rmid(r);
+	smp_call_function_many(cpu_mask, update_cpu_closid_rmid, r, 1);
 	put_cpu();
 }
 
+static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
+			  cpumask_var_t tmpmask)
+{
+	struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp;
+	struct list_head *head;
+
+	/* Check whether cpus belong to parent ctrl group */
+	cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
+	if (cpumask_weight(tmpmask))
+		return -EINVAL;
+
+	/* Check whether cpus are dropped from this group */
+	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
+	if (cpumask_weight(tmpmask)) {
+		/* Give any dropped cpus to parent rdtgroup */
+		cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask);
+		update_closid_rmid(tmpmask, prgrp);
+	}
+
+	/*
+	 * If we added cpus, remove them from previous group that owned them
+	 * and update per-cpu rmid
+	 */
+	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
+	if (cpumask_weight(tmpmask)) {
+		head = &prgrp->mon.crdtgrp_list;
+		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
+			if (crgrp == rdtgrp)
+				continue;
+			cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask,
+				       tmpmask);
+		}
+		update_closid_rmid(tmpmask, rdtgrp);
+	}
+
+	/* Done pushing/pulling - update this group with new mask */
+	cpumask_copy(&rdtgrp->cpu_mask, newmask);
+
+	return 0;
+}
+
+static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m)
+{
+	struct rdtgroup *crgrp;
+
+	cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m);
+	/* update the child mon group masks as well*/
+	list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list)
+		cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask);
+}
+
+static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
+			   cpumask_var_t tmpmask, cpumask_var_t tmpmask1)
+{
+	struct rdtgroup *r, *crgrp;
+	struct list_head *head;
+
+	/* Check whether cpus are dropped from this group */
+	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
+	if (cpumask_weight(tmpmask)) {
+		/* Can't drop from default group */
+		if (rdtgrp == &rdtgroup_default)
+			return -EINVAL;
+
+		/* Give any dropped cpus to rdtgroup_default */
+		cpumask_or(&rdtgroup_default.cpu_mask,
+			   &rdtgroup_default.cpu_mask, tmpmask);
+		update_closid_rmid(tmpmask, &rdtgroup_default);
+	}
+
+	/*
+	 * If we added cpus, remove them from previous group and
+	 * the prev group's child groups that owned them
+	 * and update per-cpu closid/rmid.
+	 */
+	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
+	if (cpumask_weight(tmpmask)) {
+		list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
+			if (r == rdtgrp)
+				continue;
+			cpumask_and(tmpmask1, &r->cpu_mask, tmpmask);
+			if (cpumask_weight(tmpmask1))
+				cpumask_rdtgrp_clear(r, tmpmask1);
+		}
+		update_closid_rmid(tmpmask, rdtgrp);
+	}
+
+	/* Done pushing/pulling - update this group with new mask */
+	cpumask_copy(&rdtgrp->cpu_mask, newmask);
+
+	/*
+	 * Clear child mon group masks since there is a new parent mask
+	 * now and update the rmid for the cpus the child lost.
+	 */
+	head = &rdtgrp->mon.crdtgrp_list;
+	list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
+		cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask);
+		update_closid_rmid(tmpmask, rdtgrp);
+		cpumask_clear(&crgrp->cpu_mask);
+	}
+
+	return 0;
+}
+
 static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 				   char *buf, size_t nbytes, loff_t off)
 {
-	cpumask_var_t tmpmask, newmask;
-	struct rdtgroup *rdtgrp, *r;
+	cpumask_var_t tmpmask, newmask, tmpmask1;
+	struct rdtgroup *rdtgrp;
 	int ret;
 
 	if (!buf)
@@ -254,6 +350,11 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 		free_cpumask_var(tmpmask);
 		return -ENOMEM;
 	}
+	if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) {
+		free_cpumask_var(tmpmask);
+		free_cpumask_var(newmask);
+		return -ENOMEM;
+	}
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
@@ -276,41 +377,18 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 		goto unlock;
 	}
 
-	/* Check whether cpus are dropped from this group */
-	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
-	if (cpumask_weight(tmpmask)) {
-		/* Can't drop from default group */
-		if (rdtgrp == &rdtgroup_default) {
-			ret = -EINVAL;
-			goto unlock;
-		}
-		/* Give any dropped cpus to rdtgroup_default */
-		cpumask_or(&rdtgroup_default.cpu_mask,
-			   &rdtgroup_default.cpu_mask, tmpmask);
-		rdt_update_closid(tmpmask, &rdtgroup_default.closid);
-	}
-
-	/*
-	 * If we added cpus, remove them from previous group that owned them
-	 * and update per-cpu closid
-	 */
-	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
-	if (cpumask_weight(tmpmask)) {
-		list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
-			if (r == rdtgrp)
-				continue;
-			cpumask_andnot(&r->cpu_mask, &r->cpu_mask, tmpmask);
-		}
-		rdt_update_closid(tmpmask, &rdtgrp->closid);
-	}
-
-	/* Done pushing/pulling - update this group with new mask */
-	cpumask_copy(&rdtgrp->cpu_mask, newmask);
+	if (rdtgrp->type == RDTCTRL_GROUP)
+		ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1);
+	else if (rdtgrp->type == RDTMON_GROUP)
+		ret = cpus_mon_write(rdtgrp, newmask, tmpmask);
+	else
+		ret = -EINVAL;
 
 unlock:
 	rdtgroup_kn_unlock(of->kn);
 	free_cpumask_var(tmpmask);
 	free_cpumask_var(newmask);
+	free_cpumask_var(tmpmask1);
 
 	return ret ?: nbytes;
 }
@@ -336,6 +414,7 @@ static void move_myself(struct callback_head *head)
 	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
 	    (rdtgrp->flags & RDT_DELETED)) {
 		current->closid = 0;
+		current->rmid = 0;
 		kfree(rdtgrp);
 	}
 
@@ -374,7 +453,20 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 		atomic_dec(&rdtgrp->waitcount);
 		kfree(callback);
 	} else {
-		tsk->closid = rdtgrp->closid;
+		/*
+		 * For ctrl_mon groups move both closid and rmid.
+		 * For monitor groups, can move the tasks only from
+		 * their parent CTRL group.
+		 */
+		if (rdtgrp->type == RDTCTRL_GROUP) {
+			tsk->closid = rdtgrp->closid;
+			tsk->rmid = rdtgrp->mon.rmid;
+		} else if (rdtgrp->type == RDTMON_GROUP) {
+			if (rdtgrp->mon.parent->closid == tsk->closid)
+				tsk->rmid = rdtgrp->mon.rmid;
+			else
+				ret = -EINVAL;
+		}
 	}
 	return ret;
 }
@@ -454,7 +546,8 @@ static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
 
 	rcu_read_lock();
 	for_each_process_thread(p, t) {
-		if (t->closid == r->closid)
+		if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
+		    (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid))
 			seq_printf(s, "%d\n", t->pid);
 	}
 	rcu_read_unlock();
@@ -476,39 +569,6 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of,
 	return ret;
 }
 
-/* Files in each rdtgroup */
-static struct rftype rdtgroup_base_files[] = {
-	{
-		.name		= "cpus",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_cpus_write,
-		.seq_show	= rdtgroup_cpus_show,
-	},
-	{
-		.name		= "cpus_list",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_cpus_write,
-		.seq_show	= rdtgroup_cpus_show,
-		.flags		= RFTYPE_FLAGS_CPUS_LIST,
-	},
-	{
-		.name		= "tasks",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_tasks_write,
-		.seq_show	= rdtgroup_tasks_show,
-	},
-	{
-		.name		= "schemata",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_schemata_write,
-		.seq_show	= rdtgroup_schemata_show,
-	},
-};
-
 static int rdt_num_closids_show(struct kernfs_open_file *of,
 				struct seq_file *seq, void *v)
 {
@@ -536,6 +596,15 @@ static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+static int rdt_shareable_bits_show(struct kernfs_open_file *of,
+				   struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%x\n", r->cache.shareable_bits);
+	return 0;
+}
+
 static int rdt_min_bw_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
@@ -545,6 +614,28 @@ static int rdt_min_bw_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+static int rdt_num_rmids_show(struct kernfs_open_file *of,
+			      struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%d\n", r->num_rmid);
+
+	return 0;
+}
+
+static int rdt_mon_features_show(struct kernfs_open_file *of,
+				 struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+	struct mon_evt *mevt;
+
+	list_for_each_entry(mevt, &r->evt_list, list)
+		seq_printf(seq, "%s\n", mevt->name);
+
+	return 0;
+}
+
 static int rdt_bw_gran_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
@@ -563,74 +654,200 @@ static int rdt_delay_linear_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+static int max_threshold_occ_show(struct kernfs_open_file *of,
+				  struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%u\n", intel_cqm_threshold * r->mon_scale);
+
+	return 0;
+}
+
+static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
+				       char *buf, size_t nbytes, loff_t off)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+	unsigned int bytes;
+	int ret;
+
+	ret = kstrtouint(buf, 0, &bytes);
+	if (ret)
+		return ret;
+
+	if (bytes > (boot_cpu_data.x86_cache_size * 1024))
+		return -EINVAL;
+
+	intel_cqm_threshold = bytes / r->mon_scale;
+
+	return nbytes;
+}
+
 /* rdtgroup information files for one cache resource. */
-static struct rftype res_cache_info_files[] = {
+static struct rftype res_common_files[] = {
 	{
 		.name		= "num_closids",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
 		.seq_show	= rdt_num_closids_show,
+		.fflags		= RF_CTRL_INFO,
+	},
+	{
+		.name		= "mon_features",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_mon_features_show,
+		.fflags		= RF_MON_INFO,
+	},
+	{
+		.name		= "num_rmids",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_num_rmids_show,
+		.fflags		= RF_MON_INFO,
 	},
 	{
 		.name		= "cbm_mask",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
 		.seq_show	= rdt_default_ctrl_show,
+		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
 	},
 	{
 		.name		= "min_cbm_bits",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
 		.seq_show	= rdt_min_cbm_bits_show,
+		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
 	},
-};
-
-/* rdtgroup information files for memory bandwidth. */
-static struct rftype res_mba_info_files[] = {
 	{
-		.name		= "num_closids",
+		.name		= "shareable_bits",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_num_closids_show,
+		.seq_show	= rdt_shareable_bits_show,
+		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
 	},
 	{
 		.name		= "min_bandwidth",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
 		.seq_show	= rdt_min_bw_show,
+		.fflags		= RF_CTRL_INFO | RFTYPE_RES_MB,
 	},
 	{
 		.name		= "bandwidth_gran",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
 		.seq_show	= rdt_bw_gran_show,
+		.fflags		= RF_CTRL_INFO | RFTYPE_RES_MB,
 	},
 	{
 		.name		= "delay_linear",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
 		.seq_show	= rdt_delay_linear_show,
+		.fflags		= RF_CTRL_INFO | RFTYPE_RES_MB,
+	},
+	{
+		.name		= "max_threshold_occupancy",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= max_threshold_occ_write,
+		.seq_show	= max_threshold_occ_show,
+		.fflags		= RF_MON_INFO | RFTYPE_RES_CACHE,
+	},
+	{
+		.name		= "cpus",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_cpus_write,
+		.seq_show	= rdtgroup_cpus_show,
+		.fflags		= RFTYPE_BASE,
+	},
+	{
+		.name		= "cpus_list",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_cpus_write,
+		.seq_show	= rdtgroup_cpus_show,
+		.flags		= RFTYPE_FLAGS_CPUS_LIST,
+		.fflags		= RFTYPE_BASE,
+	},
+	{
+		.name		= "tasks",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_tasks_write,
+		.seq_show	= rdtgroup_tasks_show,
+		.fflags		= RFTYPE_BASE,
+	},
+	{
+		.name		= "schemata",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_schemata_write,
+		.seq_show	= rdtgroup_schemata_show,
+		.fflags		= RF_CTRL_BASE,
 	},
 };
 
-void rdt_get_mba_infofile(struct rdt_resource *r)
+static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
 {
-	r->info_files = res_mba_info_files;
-	r->nr_info_files = ARRAY_SIZE(res_mba_info_files);
+	struct rftype *rfts, *rft;
+	int ret, len;
+
+	rfts = res_common_files;
+	len = ARRAY_SIZE(res_common_files);
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	for (rft = rfts; rft < rfts + len; rft++) {
+		if ((fflags & rft->fflags) == rft->fflags) {
+			ret = rdtgroup_add_file(kn, rft);
+			if (ret)
+				goto error;
+		}
+	}
+
+	return 0;
+error:
+	pr_warn("Failed to add %s, err=%d\n", rft->name, ret);
+	while (--rft >= rfts) {
+		if ((fflags & rft->fflags) == rft->fflags)
+			kernfs_remove_by_name(kn, rft->name);
+	}
+	return ret;
 }
 
-void rdt_get_cache_infofile(struct rdt_resource *r)
+static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name,
+				      unsigned long fflags)
 {
-	r->info_files = res_cache_info_files;
-	r->nr_info_files = ARRAY_SIZE(res_cache_info_files);
+	struct kernfs_node *kn_subdir;
+	int ret;
+
+	kn_subdir = kernfs_create_dir(kn_info, name,
+				      kn_info->mode, r);
+	if (IS_ERR(kn_subdir))
+		return PTR_ERR(kn_subdir);
+
+	kernfs_get(kn_subdir);
+	ret = rdtgroup_kn_set_ugid(kn_subdir);
+	if (ret)
+		return ret;
+
+	ret = rdtgroup_add_files(kn_subdir, fflags);
+	if (!ret)
+		kernfs_activate(kn_subdir);
+
+	return ret;
 }
 
 static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 {
-	struct kernfs_node *kn_subdir;
-	struct rftype *res_info_files;
 	struct rdt_resource *r;
-	int ret, len;
+	unsigned long fflags;
+	char name[32];
+	int ret;
 
 	/* create the directory */
 	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
@@ -638,25 +855,19 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 		return PTR_ERR(kn_info);
 	kernfs_get(kn_info);
 
-	for_each_enabled_rdt_resource(r) {
-		kn_subdir = kernfs_create_dir(kn_info, r->name,
-					      kn_info->mode, r);
-		if (IS_ERR(kn_subdir)) {
-			ret = PTR_ERR(kn_subdir);
-			goto out_destroy;
-		}
-		kernfs_get(kn_subdir);
-		ret = rdtgroup_kn_set_ugid(kn_subdir);
+	for_each_alloc_enabled_rdt_resource(r) {
+		fflags =  r->fflags | RF_CTRL_INFO;
+		ret = rdtgroup_mkdir_info_resdir(r, r->name, fflags);
 		if (ret)
 			goto out_destroy;
+	}
 
-		res_info_files = r->info_files;
-		len = r->nr_info_files;
-
-		ret = rdtgroup_add_files(kn_subdir, res_info_files, len);
+	for_each_mon_enabled_rdt_resource(r) {
+		fflags =  r->fflags | RF_MON_INFO;
+		sprintf(name, "%s_MON", r->name);
+		ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
 		if (ret)
 			goto out_destroy;
-		kernfs_activate(kn_subdir);
 	}
 
 	/*
@@ -678,6 +889,39 @@ out_destroy:
 	return ret;
 }
 
+static int
+mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp,
+		    char *name, struct kernfs_node **dest_kn)
+{
+	struct kernfs_node *kn;
+	int ret;
+
+	/* create the directory */
+	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
+
+	if (dest_kn)
+		*dest_kn = kn;
+
+	/*
+	 * This extra ref will be put in kernfs_remove() and guarantees
+	 * that @rdtgrp->kn is always accessible.
+	 */
+	kernfs_get(kn);
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret)
+		goto out_destroy;
+
+	kernfs_activate(kn);
+
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn);
+	return ret;
+}
 static void l3_qos_cfg_update(void *arg)
 {
 	bool *enable = arg;
@@ -718,14 +962,15 @@ static int cdp_enable(void)
 	struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
 	int ret;
 
-	if (!r_l3->capable || !r_l3data->capable || !r_l3code->capable)
+	if (!r_l3->alloc_capable || !r_l3data->alloc_capable ||
+	    !r_l3code->alloc_capable)
 		return -EINVAL;
 
 	ret = set_l3_qos_cfg(r_l3, true);
 	if (!ret) {
-		r_l3->enabled = false;
-		r_l3data->enabled = true;
-		r_l3code->enabled = true;
+		r_l3->alloc_enabled = false;
+		r_l3data->alloc_enabled = true;
+		r_l3code->alloc_enabled = true;
 	}
 	return ret;
 }
@@ -734,11 +979,11 @@ static void cdp_disable(void)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
 
-	r->enabled = r->capable;
+	r->alloc_enabled = r->alloc_capable;
 
-	if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) {
-		rdt_resources_all[RDT_RESOURCE_L3DATA].enabled = false;
-		rdt_resources_all[RDT_RESOURCE_L3CODE].enabled = false;
+	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) {
+		rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled = false;
+		rdt_resources_all[RDT_RESOURCE_L3CODE].alloc_enabled = false;
 		set_l3_qos_cfg(r, false);
 	}
 }
@@ -823,10 +1068,16 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
 	}
 }
 
+static int mkdir_mondata_all(struct kernfs_node *parent_kn,
+			     struct rdtgroup *prgrp,
+			     struct kernfs_node **mon_data_kn);
+
 static struct dentry *rdt_mount(struct file_system_type *fs_type,
 				int flags, const char *unused_dev_name,
 				void *data)
 {
+	struct rdt_domain *dom;
+	struct rdt_resource *r;
 	struct dentry *dentry;
 	int ret;
 
@@ -853,15 +1104,54 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 		goto out_cdp;
 	}
 
+	if (rdt_mon_capable) {
+		ret = mongroup_create_dir(rdtgroup_default.kn,
+					  NULL, "mon_groups",
+					  &kn_mongrp);
+		if (ret) {
+			dentry = ERR_PTR(ret);
+			goto out_info;
+		}
+		kernfs_get(kn_mongrp);
+
+		ret = mkdir_mondata_all(rdtgroup_default.kn,
+					&rdtgroup_default, &kn_mondata);
+		if (ret) {
+			dentry = ERR_PTR(ret);
+			goto out_mongrp;
+		}
+		kernfs_get(kn_mondata);
+		rdtgroup_default.mon.mon_data_kn = kn_mondata;
+	}
+
 	dentry = kernfs_mount(fs_type, flags, rdt_root,
 			      RDTGROUP_SUPER_MAGIC, NULL);
 	if (IS_ERR(dentry))
-		goto out_destroy;
+		goto out_mondata;
+
+	if (rdt_alloc_capable)
+		static_branch_enable(&rdt_alloc_enable_key);
+	if (rdt_mon_capable)
+		static_branch_enable(&rdt_mon_enable_key);
+
+	if (rdt_alloc_capable || rdt_mon_capable)
+		static_branch_enable(&rdt_enable_key);
+
+	if (is_mbm_enabled()) {
+		r = &rdt_resources_all[RDT_RESOURCE_L3];
+		list_for_each_entry(dom, &r->domains, list)
+			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
+	}
 
-	static_branch_enable(&rdt_enable_key);
 	goto out;
 
-out_destroy:
+out_mondata:
+	if (rdt_mon_capable)
+		kernfs_remove(kn_mondata);
+out_mongrp:
+	if (rdt_mon_capable)
+		kernfs_remove(kn_mongrp);
+out_info:
 	kernfs_remove(kn_info);
 out_cdp:
 	cdp_disable();
@@ -909,6 +1199,18 @@ static int reset_all_ctrls(struct rdt_resource *r)
 	return 0;
 }
 
+static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
+{
+	return (rdt_alloc_capable &&
+		(r->type == RDTCTRL_GROUP) && (t->closid == 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));
+}
+
 /*
  * Move tasks from one to the other group. If @from is NULL, then all tasks
  * in the systems are moved unconditionally (used for teardown).
@@ -924,8 +1226,11 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
 
 	read_lock(&tasklist_lock);
 	for_each_process_thread(p, t) {
-		if (!from || t->closid == from->closid) {
+		if (!from || is_closid_match(t, from) ||
+		    is_rmid_match(t, from)) {
 			t->closid = to->closid;
+			t->rmid = to->mon.rmid;
+
 #ifdef CONFIG_SMP
 			/*
 			 * This is safe on x86 w/o barriers as the ordering
@@ -944,6 +1249,19 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
 	read_unlock(&tasklist_lock);
 }
 
+static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
+{
+	struct rdtgroup *sentry, *stmp;
+	struct list_head *head;
+
+	head = &rdtgrp->mon.crdtgrp_list;
+	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
+		free_rmid(sentry->mon.rmid);
+		list_del(&sentry->mon.crdtgrp_list);
+		kfree(sentry);
+	}
+}
+
 /*
  * Forcibly remove all of subdirectories under root.
  */
@@ -955,6 +1273,9 @@ static void rmdir_all_sub(void)
 	rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);
 
 	list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
+		/* Free any child rmids */
+		free_all_child_rdtgrp(rdtgrp);
+
 		/* Remove each rdtgroup other than root */
 		if (rdtgrp == &rdtgroup_default)
 			continue;
@@ -967,16 +1288,20 @@ static void rmdir_all_sub(void)
 		cpumask_or(&rdtgroup_default.cpu_mask,
 			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
 
+		free_rmid(rdtgrp->mon.rmid);
+
 		kernfs_remove(rdtgrp->kn);
 		list_del(&rdtgrp->rdtgroup_list);
 		kfree(rdtgrp);
 	}
 	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
 	get_online_cpus();
-	rdt_update_closid(cpu_online_mask, &rdtgroup_default.closid);
+	update_closid_rmid(cpu_online_mask, &rdtgroup_default);
 	put_online_cpus();
 
 	kernfs_remove(kn_info);
+	kernfs_remove(kn_mongrp);
+	kernfs_remove(kn_mondata);
 }
 
 static void rdt_kill_sb(struct super_block *sb)
@@ -986,10 +1311,12 @@ static void rdt_kill_sb(struct super_block *sb)
 	mutex_lock(&rdtgroup_mutex);
 
 	/*Put everything back to default values. */
-	for_each_enabled_rdt_resource(r)
+	for_each_alloc_enabled_rdt_resource(r)
 		reset_all_ctrls(r);
 	cdp_disable();
 	rmdir_all_sub();
+	static_branch_disable(&rdt_alloc_enable_key);
+	static_branch_disable(&rdt_mon_enable_key);
 	static_branch_disable(&rdt_enable_key);
 	kernfs_kill_sb(sb);
 	mutex_unlock(&rdtgroup_mutex);
@@ -1001,46 +1328,223 @@ static struct file_system_type rdt_fs_type = {
 	.kill_sb = rdt_kill_sb,
 };
 
-static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
-			  umode_t mode)
+static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
+		       void *priv)
 {
-	struct rdtgroup *parent, *rdtgrp;
 	struct kernfs_node *kn;
-	int ret, closid;
+	int ret = 0;
 
-	/* Only allow mkdir in the root directory */
-	if (parent_kn != rdtgroup_default.kn)
-		return -EPERM;
+	kn = __kernfs_create_file(parent_kn, name, 0444, 0,
+				  &kf_mondata_ops, priv, NULL, NULL);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
 
-	/* Do not accept '\n' to avoid unparsable situation. */
-	if (strchr(name, '\n'))
-		return -EINVAL;
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret) {
+		kernfs_remove(kn);
+		return ret;
+	}
 
-	parent = rdtgroup_kn_lock_live(parent_kn);
-	if (!parent) {
-		ret = -ENODEV;
-		goto out_unlock;
+	return ret;
+}
+
+/*
+ * Remove all subdirectories of mon_data of ctrl_mon groups
+ * and monitor groups with given domain id.
+ */
+void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, unsigned int dom_id)
+{
+	struct rdtgroup *prgrp, *crgrp;
+	char name[32];
+
+	if (!r->mon_enabled)
+		return;
+
+	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
+		sprintf(name, "mon_%s_%02d", r->name, dom_id);
+		kernfs_remove_by_name(prgrp->mon.mon_data_kn, name);
+
+		list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list)
+			kernfs_remove_by_name(crgrp->mon.mon_data_kn, name);
 	}
+}
 
-	ret = closid_alloc();
-	if (ret < 0)
+static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
+				struct rdt_domain *d,
+				struct rdt_resource *r, struct rdtgroup *prgrp)
+{
+	union mon_data_bits priv;
+	struct kernfs_node *kn;
+	struct mon_evt *mevt;
+	struct rmid_read rr;
+	char name[32];
+	int ret;
+
+	sprintf(name, "mon_%s_%02d", r->name, d->id);
+	/* create the directory */
+	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
+
+	/*
+	 * This extra ref will be put in kernfs_remove() and guarantees
+	 * that kn is always accessible.
+	 */
+	kernfs_get(kn);
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret)
+		goto out_destroy;
+
+	if (WARN_ON(list_empty(&r->evt_list))) {
+		ret = -EPERM;
+		goto out_destroy;
+	}
+
+	priv.u.rid = r->rid;
+	priv.u.domid = d->id;
+	list_for_each_entry(mevt, &r->evt_list, list) {
+		priv.u.evtid = mevt->evtid;
+		ret = mon_addfile(kn, mevt->name, priv.priv);
+		if (ret)
+			goto out_destroy;
+
+		if (is_mbm_event(mevt->evtid))
+			mon_event_read(&rr, d, prgrp, mevt->evtid, true);
+	}
+	kernfs_activate(kn);
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn);
+	return ret;
+}
+
+/*
+ * Add all subdirectories of mon_data for "ctrl_mon" groups
+ * and "monitor" groups with given domain id.
+ */
+void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+				    struct rdt_domain *d)
+{
+	struct kernfs_node *parent_kn;
+	struct rdtgroup *prgrp, *crgrp;
+	struct list_head *head;
+
+	if (!r->mon_enabled)
+		return;
+
+	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
+		parent_kn = prgrp->mon.mon_data_kn;
+		mkdir_mondata_subdir(parent_kn, d, r, prgrp);
+
+		head = &prgrp->mon.crdtgrp_list;
+		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
+			parent_kn = crgrp->mon.mon_data_kn;
+			mkdir_mondata_subdir(parent_kn, d, r, crgrp);
+		}
+	}
+}
+
+static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
+				       struct rdt_resource *r,
+				       struct rdtgroup *prgrp)
+{
+	struct rdt_domain *dom;
+	int ret;
+
+	list_for_each_entry(dom, &r->domains, list) {
+		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * This creates a directory mon_data which contains the monitored data.
+ *
+ * mon_data has one directory for each domain whic are named
+ * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data
+ * with L3 domain looks as below:
+ * ./mon_data:
+ * mon_L3_00
+ * mon_L3_01
+ * mon_L3_02
+ * ...
+ *
+ * Each domain directory has one file per event:
+ * ./mon_L3_00/:
+ * llc_occupancy
+ *
+ */
+static int mkdir_mondata_all(struct kernfs_node *parent_kn,
+			     struct rdtgroup *prgrp,
+			     struct kernfs_node **dest_kn)
+{
+	struct rdt_resource *r;
+	struct kernfs_node *kn;
+	int ret;
+
+	/*
+	 * Create the mon_data directory first.
+	 */
+	ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn);
+	if (ret)
+		return ret;
+
+	if (dest_kn)
+		*dest_kn = kn;
+
+	/*
+	 * Create the subdirectories for each domain. Note that all events
+	 * in a domain like L3 are grouped into a resource whose domain is L3
+	 */
+	for_each_mon_enabled_rdt_resource(r) {
+		ret = mkdir_mondata_subdir_alldom(kn, r, prgrp);
+		if (ret)
+			goto out_destroy;
+	}
+
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn);
+	return ret;
+}
+
+static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
+			     struct kernfs_node *prgrp_kn,
+			     const char *name, umode_t mode,
+			     enum rdt_group_type rtype, struct rdtgroup **r)
+{
+	struct rdtgroup *prdtgrp, *rdtgrp;
+	struct kernfs_node *kn;
+	uint files = 0;
+	int ret;
+
+	prdtgrp = rdtgroup_kn_lock_live(prgrp_kn);
+	if (!prdtgrp) {
+		ret = -ENODEV;
 		goto out_unlock;
-	closid = ret;
+	}
 
 	/* allocate the rdtgroup. */
 	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
 	if (!rdtgrp) {
 		ret = -ENOSPC;
-		goto out_closid_free;
+		goto out_unlock;
 	}
-	rdtgrp->closid = closid;
-	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
+	*r = rdtgrp;
+	rdtgrp->mon.parent = prdtgrp;
+	rdtgrp->type = rtype;
+	INIT_LIST_HEAD(&rdtgrp->mon.crdtgrp_list);
 
 	/* kernfs creates the directory for rdtgrp */
-	kn = kernfs_create_dir(parent->kn, name, mode, rdtgrp);
+	kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp);
 	if (IS_ERR(kn)) {
 		ret = PTR_ERR(kn);
-		goto out_cancel_ref;
+		goto out_free_rgrp;
 	}
 	rdtgrp->kn = kn;
 
@@ -1056,43 +1560,211 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 	if (ret)
 		goto out_destroy;
 
-	ret = rdtgroup_add_files(kn, rdtgroup_base_files,
-				 ARRAY_SIZE(rdtgroup_base_files));
+	files = RFTYPE_BASE | RFTYPE_CTRL;
+	files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype);
+	ret = rdtgroup_add_files(kn, files);
 	if (ret)
 		goto out_destroy;
 
+	if (rdt_mon_capable) {
+		ret = alloc_rmid();
+		if (ret < 0)
+			goto out_destroy;
+		rdtgrp->mon.rmid = ret;
+
+		ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
+		if (ret)
+			goto out_idfree;
+	}
 	kernfs_activate(kn);
 
-	ret = 0;
-	goto out_unlock;
+	/*
+	 * The caller unlocks the prgrp_kn upon success.
+	 */
+	return 0;
 
+out_idfree:
+	free_rmid(rdtgrp->mon.rmid);
 out_destroy:
 	kernfs_remove(rdtgrp->kn);
-out_cancel_ref:
-	list_del(&rdtgrp->rdtgroup_list);
+out_free_rgrp:
 	kfree(rdtgrp);
-out_closid_free:
-	closid_free(closid);
 out_unlock:
-	rdtgroup_kn_unlock(parent_kn);
+	rdtgroup_kn_unlock(prgrp_kn);
 	return ret;
 }
 
-static int rdtgroup_rmdir(struct kernfs_node *kn)
+static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
+{
+	kernfs_remove(rgrp->kn);
+	free_rmid(rgrp->mon.rmid);
+	kfree(rgrp);
+}
+
+/*
+ * Create a monitor group under "mon_groups" directory of a control
+ * and monitor group(ctrl_mon). This is a resource group
+ * to monitor a subset of tasks and cpus in its parent ctrl_mon group.
+ */
+static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
+			      struct kernfs_node *prgrp_kn,
+			      const char *name,
+			      umode_t mode)
+{
+	struct rdtgroup *rdtgrp, *prgrp;
+	int ret;
+
+	ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTMON_GROUP,
+				&rdtgrp);
+	if (ret)
+		return ret;
+
+	prgrp = rdtgrp->mon.parent;
+	rdtgrp->closid = prgrp->closid;
+
+	/*
+	 * 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);
+
+	rdtgroup_kn_unlock(prgrp_kn);
+	return ret;
+}
+
+/*
+ * These are rdtgroups created under the root directory. Can be used
+ * to allocate and monitor resources.
+ */
+static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
+				   struct kernfs_node *prgrp_kn,
+				   const char *name, umode_t mode)
 {
-	int ret, cpu, closid = rdtgroup_default.closid;
 	struct rdtgroup *rdtgrp;
-	cpumask_var_t tmpmask;
+	struct kernfs_node *kn;
+	u32 closid;
+	int ret;
 
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
-		return -ENOMEM;
+	ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTCTRL_GROUP,
+				&rdtgrp);
+	if (ret)
+		return ret;
 
-	rdtgrp = rdtgroup_kn_lock_live(kn);
-	if (!rdtgrp) {
-		ret = -EPERM;
-		goto out;
+	kn = rdtgrp->kn;
+	ret = closid_alloc();
+	if (ret < 0)
+		goto out_common_fail;
+	closid = ret;
+
+	rdtgrp->closid = closid;
+	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
+
+	if (rdt_mon_capable) {
+		/*
+		 * Create an empty mon_groups directory to hold the subset
+		 * of tasks and cpus to monitor.
+		 */
+		ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL);
+		if (ret)
+			goto out_id_free;
 	}
 
+	goto out_unlock;
+
+out_id_free:
+	closid_free(closid);
+	list_del(&rdtgrp->rdtgroup_list);
+out_common_fail:
+	mkdir_rdt_prepare_clean(rdtgrp);
+out_unlock:
+	rdtgroup_kn_unlock(prgrp_kn);
+	return ret;
+}
+
+/*
+ * We allow creating mon groups only with in a directory called "mon_groups"
+ * which is present in every ctrl_mon group. Check if this is a valid
+ * "mon_groups" directory.
+ *
+ * 1. The directory should be named "mon_groups".
+ * 2. The mon group itself should "not" be named "mon_groups".
+ *   This makes sure "mon_groups" directory always has a ctrl_mon group
+ *   as parent.
+ */
+static bool is_mon_groups(struct kernfs_node *kn, const char *name)
+{
+	return (!strcmp(kn->name, "mon_groups") &&
+		strcmp(name, "mon_groups"));
+}
+
+static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
+			  umode_t mode)
+{
+	/* Do not accept '\n' to avoid unparsable situation. */
+	if (strchr(name, '\n'))
+		return -EINVAL;
+
+	/*
+	 * If the parent directory is the root directory and RDT
+	 * allocation is supported, add a control and monitoring
+	 * subdirectory
+	 */
+	if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn)
+		return rdtgroup_mkdir_ctrl_mon(parent_kn, 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))
+		return rdtgroup_mkdir_mon(parent_kn, parent_kn->parent, name, mode);
+
+	return -EPERM;
+}
+
+static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
+			      cpumask_var_t tmpmask)
+{
+	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
+	int cpu;
+
+	/* Give any tasks back to the parent group */
+	rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask);
+
+	/* Update per cpu rmid of the moved CPUs first */
+	for_each_cpu(cpu, &rdtgrp->cpu_mask)
+		per_cpu(pqr_state.default_rmid, cpu) = prdtgrp->mon.rmid;
+	/*
+	 * Update the MSR on moved CPUs and CPUs which have moved
+	 * task running on them.
+	 */
+	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
+	update_closid_rmid(tmpmask, NULL);
+
+	rdtgrp->flags = RDT_DELETED;
+	free_rmid(rdtgrp->mon.rmid);
+
+	/*
+	 * Remove the rdtgrp from the parent ctrl_mon group's list
+	 */
+	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
+	list_del(&rdtgrp->mon.crdtgrp_list);
+
+	/*
+	 * one extra hold on this, will drop when we kfree(rdtgrp)
+	 * in rdtgroup_kn_unlock()
+	 */
+	kernfs_get(kn);
+	kernfs_remove(rdtgrp->kn);
+
+	return 0;
+}
+
+static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
+			       cpumask_var_t tmpmask)
+{
+	int cpu;
+
 	/* Give any tasks back to the default group */
 	rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask);
 
@@ -1100,18 +1772,28 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	cpumask_or(&rdtgroup_default.cpu_mask,
 		   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
 
-	/* Update per cpu closid of the moved CPUs first */
-	for_each_cpu(cpu, &rdtgrp->cpu_mask)
-		per_cpu(cpu_closid, cpu) = closid;
+	/* Update per cpu closid and rmid of the moved CPUs first */
+	for_each_cpu(cpu, &rdtgrp->cpu_mask) {
+		per_cpu(pqr_state.default_closid, cpu) = rdtgroup_default.closid;
+		per_cpu(pqr_state.default_rmid, cpu) = rdtgroup_default.mon.rmid;
+	}
+
 	/*
 	 * Update the MSR on moved CPUs and CPUs which have moved
 	 * task running on them.
 	 */
 	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
-	rdt_update_closid(tmpmask, NULL);
+	update_closid_rmid(tmpmask, NULL);
 
 	rdtgrp->flags = RDT_DELETED;
 	closid_free(rdtgrp->closid);
+	free_rmid(rdtgrp->mon.rmid);
+
+	/*
+	 * Free all the child monitor group rmids.
+	 */
+	free_all_child_rdtgrp(rdtgrp);
+
 	list_del(&rdtgrp->rdtgroup_list);
 
 	/*
@@ -1120,7 +1802,41 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	 */
 	kernfs_get(kn);
 	kernfs_remove(rdtgrp->kn);
-	ret = 0;
+
+	return 0;
+}
+
+static int rdtgroup_rmdir(struct kernfs_node *kn)
+{
+	struct kernfs_node *parent_kn = kn->parent;
+	struct rdtgroup *rdtgrp;
+	cpumask_var_t tmpmask;
+	int ret = 0;
+
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		return -ENOMEM;
+
+	rdtgrp = rdtgroup_kn_lock_live(kn);
+	if (!rdtgrp) {
+		ret = -EPERM;
+		goto out;
+	}
+
+	/*
+	 * If the rdtgroup is a ctrl_mon group and parent directory
+	 * is the root directory, remove the ctrl_mon group.
+	 *
+	 * If the rdtgroup is a mon group and parent directory
+	 * is a valid "mon_groups" directory, remove the mon group.
+	 */
+	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn)
+		ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask);
+	else if (rdtgrp->type == RDTMON_GROUP &&
+		 is_mon_groups(parent_kn, kn->name))
+		ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask);
+	else
+		ret = -EPERM;
+
 out:
 	rdtgroup_kn_unlock(kn);
 	free_cpumask_var(tmpmask);
@@ -1129,7 +1845,7 @@ out:
 
 static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
 {
-	if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled)
+	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled)
 		seq_puts(seq, ",cdp");
 	return 0;
 }
@@ -1153,10 +1869,13 @@ static int __init rdtgroup_setup_root(void)
 	mutex_lock(&rdtgroup_mutex);
 
 	rdtgroup_default.closid = 0;
+	rdtgroup_default.mon.rmid = 0;
+	rdtgroup_default.type = RDTCTRL_GROUP;
+	INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list);
+
 	list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);
 
-	ret = rdtgroup_add_files(rdt_root->kn, rdtgroup_base_files,
-				 ARRAY_SIZE(rdtgroup_base_files));
+	ret = rdtgroup_add_files(rdt_root->kn, RF_CTRL_BASE);
 	if (ret) {
 		kernfs_destroy_root(rdt_root);
 		goto out;