8 files changed, 1800 insertions, 4 deletions

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 33b63670bf09..52000010c62e 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -32,6 +32,8 @@ 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_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
 obj-$(CONFIG_MICROCODE)			+= microcode/
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index be6337156502..0282b0df004a 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -153,6 +153,7 @@ struct _cpuid4_info_regs {
 	union _cpuid4_leaf_eax eax;
 	union _cpuid4_leaf_ebx ebx;
 	union _cpuid4_leaf_ecx ecx;
+	unsigned int id;
 	unsigned long size;
 	struct amd_northbridge *nb;
 };
@@ -894,6 +895,8 @@ static void __cache_cpumap_setup(unsigned int cpu, int index,
 static void ci_leaf_init(struct cacheinfo *this_leaf,
 			 struct _cpuid4_info_regs *base)
 {
+	this_leaf->id = base->id;
+	this_leaf->attributes = CACHE_ID;
 	this_leaf->level = base->eax.split.level;
 	this_leaf->type = cache_type_map[base->eax.split.type];
 	this_leaf->coherency_line_size =
@@ -920,6 +923,22 @@ static int __init_cache_level(unsigned int cpu)
 	return 0;
 }
 
+/*
+ * The max shared threads number comes from CPUID.4:EAX[25-14] with input
+ * ECX as cache index. Then right shift apicid by the number's order to get
+ * cache id for this cache node.
+ */
+static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	unsigned long num_threads_sharing;
+	int index_msb;
+
+	num_threads_sharing = 1 + id4_regs->eax.split.num_threads_sharing;
+	index_msb = get_count_order(num_threads_sharing);
+	id4_regs->id = c->apicid >> index_msb;
+}
+
 static int __populate_cache_leaves(unsigned int cpu)
 {
 	unsigned int idx, ret;
@@ -931,6 +950,7 @@ static int __populate_cache_leaves(unsigned int cpu)
 		ret = cpuid4_cache_lookup_regs(idx, &id4_regs);
 		if (ret)
 			return ret;
+		get_cache_id(cpu, &id4_regs);
 		ci_leaf_init(this_leaf++, &id4_regs);
 		__cache_cpumap_setup(cpu, idx, &id4_regs);
 	}
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
new file mode 100644
index 000000000000..5a533fefefa0
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -0,0 +1,403 @@
+/*
+ * Resource Director Technology(RDT)
+ * - Cache Allocation code.
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Authors:
+ *    Fenghua Yu <fenghua.yu@intel.com>
+ *    Tony Luck <tony.luck@intel.com>
+ *    Vikas Shivappa <vikas.shivappa@intel.com>
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/cacheinfo.h>
+#include <linux/cpuhotplug.h>
+
+#include <asm/intel-family.h>
+#include <asm/intel_rdt.h>
+
+/* Mutex to protect rdtgroup access. */
+DEFINE_MUTEX(rdtgroup_mutex);
+
+DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid);
+
+#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
+
+struct rdt_resource rdt_resources_all[] = {
+	{
+		.name		= "L3",
+		.domains	= domain_init(RDT_RESOURCE_L3),
+		.msr_base	= IA32_L3_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 3,
+		.cbm_idx_multi	= 1,
+		.cbm_idx_offset	= 0
+	},
+	{
+		.name		= "L3DATA",
+		.domains	= domain_init(RDT_RESOURCE_L3DATA),
+		.msr_base	= IA32_L3_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 3,
+		.cbm_idx_multi	= 2,
+		.cbm_idx_offset	= 0
+	},
+	{
+		.name		= "L3CODE",
+		.domains	= domain_init(RDT_RESOURCE_L3CODE),
+		.msr_base	= IA32_L3_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 3,
+		.cbm_idx_multi	= 2,
+		.cbm_idx_offset	= 1
+	},
+	{
+		.name		= "L2",
+		.domains	= domain_init(RDT_RESOURCE_L2),
+		.msr_base	= IA32_L2_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 2,
+		.cbm_idx_multi	= 1,
+		.cbm_idx_offset	= 0
+	},
+};
+
+static int cbm_idx(struct rdt_resource *r, int closid)
+{
+	return closid * r->cbm_idx_multi + r->cbm_idx_offset;
+}
+
+/*
+ * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
+ * as they do not have CPUID enumeration support for Cache allocation.
+ * The check for Vendor/Family/Model is not enough to guarantee that
+ * the MSRs won't #GP fault because only the following SKUs support
+ * CAT:
+ *	Intel(R) Xeon(R)  CPU E5-2658  v3  @  2.20GHz
+ *	Intel(R) Xeon(R)  CPU E5-2648L v3  @  1.80GHz
+ *	Intel(R) Xeon(R)  CPU E5-2628L v3  @  2.00GHz
+ *	Intel(R) Xeon(R)  CPU E5-2618L v3  @  2.30GHz
+ *	Intel(R) Xeon(R)  CPU E5-2608L v3  @  2.00GHz
+ *	Intel(R) Xeon(R)  CPU E5-2658A v3  @  2.20GHz
+ *
+ * Probe by trying to write the first of the L3 cach mask registers
+ * and checking that the bits stick. Max CLOSids is always 4 and max cbm length
+ * 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)
+{
+	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);
+
+		/* If all the bits were set in MSR, return success */
+		if (l != max_cbm)
+			return false;
+
+		r->num_closid = 4;
+		r->cbm_len = 20;
+		r->max_cbm = max_cbm;
+		r->min_cbm_bits = 2;
+		r->capable = true;
+		r->enabled = true;
+
+		return true;
+	}
+
+	return false;
+}
+
+static void rdt_get_config(int idx, struct rdt_resource *r)
+{
+	union cpuid_0x10_1_eax eax;
+	union cpuid_0x10_1_edx edx;
+	u32 ebx, ecx;
+
+	cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full);
+	r->num_closid = edx.split.cos_max + 1;
+	r->cbm_len = eax.split.cbm_len + 1;
+	r->max_cbm = BIT_MASK(eax.split.cbm_len + 1) - 1;
+	r->capable = true;
+	r->enabled = true;
+}
+
+static void rdt_get_cdp_l3_config(int type)
+{
+	struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+	struct rdt_resource *r = &rdt_resources_all[type];
+
+	r->num_closid = r_l3->num_closid / 2;
+	r->cbm_len = r_l3->cbm_len;
+	r->max_cbm = r_l3->max_cbm;
+	r->capable = true;
+	/*
+	 * By default, CDP is disabled. CDP can be enabled by mount parameter
+	 * "cdp" during resctrl file system mount time.
+	 */
+	r->enabled = false;
+}
+
+static inline bool get_rdt_resources(void)
+{
+	bool ret = false;
+
+	if (cache_alloc_hsw_probe())
+		return true;
+
+	if (!boot_cpu_has(X86_FEATURE_RDT_A))
+		return false;
+
+	if (boot_cpu_has(X86_FEATURE_CAT_L3)) {
+		rdt_get_config(1, &rdt_resources_all[RDT_RESOURCE_L3]);
+		if (boot_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)) {
+		/* CPUID 0x10.2 fields are same format at 0x10.1 */
+		rdt_get_config(2, &rdt_resources_all[RDT_RESOURCE_L2]);
+		ret = true;
+	}
+
+	return ret;
+}
+
+static int get_cache_id(int cpu, int level)
+{
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
+	int i;
+
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == level)
+			return ci->info_list[i].id;
+	}
+
+	return -1;
+}
+
+void rdt_cbm_update(void *arg)
+{
+	struct msr_param *m = (struct msr_param *)arg;
+	struct rdt_resource *r = m->res;
+	int i, 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))
+			goto found;
+	}
+	pr_info_once("cpu %d not found in any domain for resource %s\n",
+		     cpu, r->name);
+
+	return;
+
+found:
+	for (i = m->low; i < m->high; i++) {
+		int idx = cbm_idx(r, i);
+
+		wrmsrl(r->msr_base + idx, d->cbm[i]);
+	}
+}
+
+/*
+ * rdt_find_domain - Find a domain in a resource that matches input resource id
+ *
+ * Search resource r's domain list to find the resource id. If the resource
+ * id is found in a domain, return the domain. Otherwise, if requested by
+ * 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 *d;
+	struct list_head *l;
+
+	if (id < 0)
+		return ERR_PTR(id);
+
+	list_for_each(l, &r->domains) {
+		d = list_entry(l, struct rdt_domain, list);
+		/* When id is found, return its domain. */
+		if (id == d->id)
+			return d;
+		/* Stop searching when finding id's position in sorted list. */
+		if (id < d->id)
+			break;
+	}
+
+	if (pos)
+		*pos = l;
+
+	return NULL;
+}
+
+/*
+ * domain_add_cpu - Add a cpu to a resource's domain list.
+ *
+ * If an existing domain in the resource r's domain list matches the cpu's
+ * resource id, add the cpu in the domain.
+ *
+ * Otherwise, a new domain is allocated and inserted into the right position
+ * in the domain list sorted by id in ascending order.
+ *
+ * The order in the domain list is visible to users when we print entries
+ * in the schemata file and schemata input is validated to have the same order
+ * as this list.
+ */
+static void domain_add_cpu(int cpu, struct rdt_resource *r)
+{
+	int i, id = get_cache_id(cpu, r->cache_level);
+	struct list_head *add_pos = NULL;
+	struct rdt_domain *d;
+
+	d = rdt_find_domain(r, id, &add_pos);
+	if (IS_ERR(d)) {
+		pr_warn("Could't find cache id for cpu %d\n", cpu);
+		return;
+	}
+
+	if (d) {
+		cpumask_set_cpu(cpu, &d->cpu_mask);
+		return;
+	}
+
+	d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu));
+	if (!d)
+		return;
+
+	d->id = id;
+
+	d->cbm = kmalloc_array(r->num_closid, sizeof(*d->cbm), GFP_KERNEL);
+	if (!d->cbm) {
+		kfree(d);
+		return;
+	}
+
+	for (i = 0; i < r->num_closid; i++) {
+		int idx = cbm_idx(r, i);
+
+		d->cbm[i] = r->max_cbm;
+		wrmsrl(r->msr_base + idx, d->cbm[i]);
+	}
+
+	cpumask_set_cpu(cpu, &d->cpu_mask);
+	list_add_tail(&d->list, add_pos);
+	r->num_domains++;
+}
+
+static void domain_remove_cpu(int cpu, struct rdt_resource *r)
+{
+	int id = get_cache_id(cpu, r->cache_level);
+	struct rdt_domain *d;
+
+	d = rdt_find_domain(r, id, NULL);
+	if (IS_ERR_OR_NULL(d)) {
+		pr_warn("Could't find cache id for cpu %d\n", cpu);
+		return;
+	}
+
+	cpumask_clear_cpu(cpu, &d->cpu_mask);
+	if (cpumask_empty(&d->cpu_mask)) {
+		r->num_domains--;
+		kfree(d->cbm);
+		list_del(&d->list);
+		kfree(d);
+	}
+}
+
+static void clear_closid(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);
+}
+
+static int intel_rdt_online_cpu(unsigned int cpu)
+{
+	struct rdt_resource *r;
+
+	mutex_lock(&rdtgroup_mutex);
+	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);
+	clear_closid(cpu);
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int intel_rdt_offline_cpu(unsigned int cpu)
+{
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+
+	mutex_lock(&rdtgroup_mutex);
+	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))
+			break;
+	}
+	clear_closid(cpu);
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int __init intel_rdt_late_init(void)
+{
+	struct rdt_resource *r;
+	int state, ret;
+
+	if (!get_rdt_resources())
+		return -ENODEV;
+
+	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				  "x86/rdt/cat:online:",
+				  intel_rdt_online_cpu, intel_rdt_offline_cpu);
+	if (state < 0)
+		return state;
+
+	ret = rdtgroup_init();
+	if (ret) {
+		cpuhp_remove_state(state);
+		return ret;
+	}
+
+	for_each_capable_rdt_resource(r)
+		pr_info("Intel RDT %s allocation detected\n", r->name);
+
+	return 0;
+}
+
+late_initcall(intel_rdt_late_init);
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
new file mode 100644
index 000000000000..8af04afdfcb9
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -0,0 +1,1115 @@
+/*
+ * User interface for Resource Alloction in Resource Director Technology(RDT)
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Author: Fenghua Yu <fenghua.yu@intel.com>
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/fs.h>
+#include <linux/sysfs.h>
+#include <linux/kernfs.h>
+#include <linux/seq_file.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/task_work.h>
+
+#include <uapi/linux/magic.h>
+
+#include <asm/intel_rdt.h>
+#include <asm/intel_rdt_common.h>
+
+DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
+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;
+
+/*
+ * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
+ * we can keep a bitmap of free CLOSIDs in a single integer.
+ *
+ * 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
+ *   group.
+ * + Context switch code can avoid extra memory references deciding which
+ *   CLOSID to load into the PQR_ASSOC MSR
+ * - We give up some options in configuring resource groups across multi-socket
+ *   systems.
+ * - Our choices on how to configure each resource become progressively more
+ *   limited as the number of resources grows.
+ */
+static int closid_free_map;
+
+static void closid_init(void)
+{
+	struct rdt_resource *r;
+	int rdt_min_closid = 32;
+
+	/* Compute rdt_min_closid across all resources */
+	for_each_enabled_rdt_resource(r)
+		rdt_min_closid = min(rdt_min_closid, r->num_closid);
+
+	closid_free_map = BIT_MASK(rdt_min_closid) - 1;
+
+	/* CLOSID 0 is always reserved for the default group */
+	closid_free_map &= ~1;
+}
+
+int closid_alloc(void)
+{
+	int closid = ffs(closid_free_map);
+
+	if (closid == 0)
+		return -ENOSPC;
+	closid--;
+	closid_free_map &= ~(1 << closid);
+
+	return closid;
+}
+
+static void closid_free(int closid)
+{
+	closid_free_map |= 1 << closid;
+}
+
+/* set uid and gid of rdtgroup dirs and files to that of the creator */
+static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
+{
+	struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
+				.ia_uid = current_fsuid(),
+				.ia_gid = current_fsgid(), };
+
+	if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
+	    gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
+		return 0;
+
+	return kernfs_setattr(kn, &iattr);
+}
+
+static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
+{
+	struct kernfs_node *kn;
+	int ret;
+
+	kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
+				  0, rft->kf_ops, rft, NULL, NULL);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret) {
+		kernfs_remove(kn);
+		return ret;
+	}
+
+	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;
+	struct rftype *rft = of->kn->priv;
+
+	if (rft->seq_show)
+		return rft->seq_show(of, m, arg);
+	return 0;
+}
+
+static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
+				   size_t nbytes, loff_t off)
+{
+	struct rftype *rft = of->kn->priv;
+
+	if (rft->write)
+		return rft->write(of, buf, nbytes, off);
+
+	return -EINVAL;
+}
+
+static struct kernfs_ops rdtgroup_kf_single_ops = {
+	.atomic_write_len	= PAGE_SIZE,
+	.write			= rdtgroup_file_write,
+	.seq_show		= rdtgroup_seqfile_show,
+};
+
+static int rdtgroup_cpus_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	if (rdtgrp)
+		seq_printf(s, "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask));
+	else
+		ret = -ENOENT;
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+/*
+ * 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
+ * preemption is disabled.
+ */
+static void rdt_update_cpu_closid(void *closid)
+{
+	if (closid)
+		this_cpu_write(cpu_closid, *(int *)closid);
+	/*
+	 * We cannot unconditionally write the MSR because the current
+	 * executing task might have its own closid selected. Just reuse
+	 * the context switch code.
+	 */
+	intel_rdt_sched_in();
+}
+
+/*
+ * 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.
+ */
+static void
+rdt_update_closid(const struct cpumask *cpu_mask, int *closid)
+{
+	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);
+	put_cpu();
+}
+
+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;
+	int ret;
+
+	if (!buf)
+		return -EINVAL;
+
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		return -ENOMEM;
+	if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) {
+		free_cpumask_var(tmpmask);
+		return -ENOMEM;
+	}
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	ret = cpumask_parse(buf, newmask);
+	if (ret)
+		goto unlock;
+
+	/* check that user didn't specify any offline cpus */
+	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
+	if (cpumask_weight(tmpmask)) {
+		ret = -EINVAL;
+		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);
+
+unlock:
+	rdtgroup_kn_unlock(of->kn);
+	free_cpumask_var(tmpmask);
+	free_cpumask_var(newmask);
+
+	return ret ?: nbytes;
+}
+
+struct task_move_callback {
+	struct callback_head	work;
+	struct rdtgroup		*rdtgrp;
+};
+
+static void move_myself(struct callback_head *head)
+{
+	struct task_move_callback *callback;
+	struct rdtgroup *rdtgrp;
+
+	callback = container_of(head, struct task_move_callback, work);
+	rdtgrp = callback->rdtgrp;
+
+	/*
+	 * If resource group was deleted before this task work callback
+	 * was invoked, then assign the task to root group and free the
+	 * resource group.
+	 */
+	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
+	    (rdtgrp->flags & RDT_DELETED)) {
+		current->closid = 0;
+		kfree(rdtgrp);
+	}
+
+	preempt_disable();
+	/* update PQR_ASSOC MSR to make resource group go into effect */
+	intel_rdt_sched_in();
+	preempt_enable();
+
+	kfree(callback);
+}
+
+static int __rdtgroup_move_task(struct task_struct *tsk,
+				struct rdtgroup *rdtgrp)
+{
+	struct task_move_callback *callback;
+	int ret;
+
+	callback = kzalloc(sizeof(*callback), GFP_KERNEL);
+	if (!callback)
+		return -ENOMEM;
+	callback->work.func = move_myself;
+	callback->rdtgrp = rdtgrp;
+
+	/*
+	 * Take a refcount, so rdtgrp cannot be freed before the
+	 * callback has been invoked.
+	 */
+	atomic_inc(&rdtgrp->waitcount);
+	ret = task_work_add(tsk, &callback->work, true);
+	if (ret) {
+		/*
+		 * Task is exiting. Drop the refcount and free the callback.
+		 * No need to check the refcount as the group cannot be
+		 * deleted before the write function unlocks rdtgroup_mutex.
+		 */
+		atomic_dec(&rdtgrp->waitcount);
+		kfree(callback);
+	} else {
+		tsk->closid = rdtgrp->closid;
+	}
+	return ret;
+}
+
+static int rdtgroup_task_write_permission(struct task_struct *task,
+					  struct kernfs_open_file *of)
+{
+	const struct cred *tcred = get_task_cred(task);
+	const struct cred *cred = current_cred();
+	int ret = 0;
+
+	/*
+	 * Even if we're attaching all tasks in the thread group, we only
+	 * need to check permissions on one of them.
+	 */
+	if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
+	    !uid_eq(cred->euid, tcred->uid) &&
+	    !uid_eq(cred->euid, tcred->suid))
+		ret = -EPERM;
+
+	put_cred(tcred);
+	return ret;
+}
+
+static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
+			      struct kernfs_open_file *of)
+{
+	struct task_struct *tsk;
+	int ret;
+
+	rcu_read_lock();
+	if (pid) {
+		tsk = find_task_by_vpid(pid);
+		if (!tsk) {
+			rcu_read_unlock();
+			return -ESRCH;
+		}
+	} else {
+		tsk = current;
+	}
+
+	get_task_struct(tsk);
+	rcu_read_unlock();
+
+	ret = rdtgroup_task_write_permission(tsk, of);
+	if (!ret)
+		ret = __rdtgroup_move_task(tsk, rdtgrp);
+
+	put_task_struct(tsk);
+	return ret;
+}
+
+static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+	pid_t pid;
+
+	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
+		return -EINVAL;
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	if (rdtgrp)
+		ret = rdtgroup_move_task(pid, rdtgrp, of);
+	else
+		ret = -ENOENT;
+
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret ?: nbytes;
+}
+
+static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
+{
+	struct task_struct *p, *t;
+
+	rcu_read_lock();
+	for_each_process_thread(p, t) {
+		if (t->closid == r->closid)
+			seq_printf(s, "%d\n", t->pid);
+	}
+	rcu_read_unlock();
+}
+
+static int rdtgroup_tasks_show(struct kernfs_open_file *of,
+			       struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (rdtgrp)
+		show_rdt_tasks(rdtgrp, s);
+	else
+		ret = -ENOENT;
+	rdtgroup_kn_unlock(of->kn);
+
+	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		= "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)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%d\n", r->num_closid);
+
+	return 0;
+}
+
+static int rdt_cbm_mask_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->max_cbm);
+
+	return 0;
+}
+
+static int rdt_min_cbm_bits_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->min_cbm_bits);
+
+	return 0;
+}
+
+/* rdtgroup information files for one cache resource. */
+static struct rftype res_info_files[] = {
+	{
+		.name		= "num_closids",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_num_closids_show,
+	},
+	{
+		.name		= "cbm_mask",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_cbm_mask_show,
+	},
+	{
+		.name		= "min_cbm_bits",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_min_cbm_bits_show,
+	},
+};
+
+static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
+{
+	struct kernfs_node *kn_subdir;
+	struct rdt_resource *r;
+	int ret;
+
+	/* create the directory */
+	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
+	if (IS_ERR(kn_info))
+		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);
+		if (ret)
+			goto out_destroy;
+		ret = rdtgroup_add_files(kn_subdir, res_info_files,
+					 ARRAY_SIZE(res_info_files));
+		if (ret)
+			goto out_destroy;
+		kernfs_activate(kn_subdir);
+	}
+
+	/*
+	 * This extra ref will be put in kernfs_remove() and guarantees
+	 * that @rdtgrp->kn is always accessible.
+	 */
+	kernfs_get(kn_info);
+
+	ret = rdtgroup_kn_set_ugid(kn_info);
+	if (ret)
+		goto out_destroy;
+
+	kernfs_activate(kn_info);
+
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn_info);
+	return ret;
+}
+
+static void l3_qos_cfg_update(void *arg)
+{
+	bool *enable = arg;
+
+	wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
+}
+
+static int set_l3_qos_cfg(struct rdt_resource *r, bool enable)
+{
+	cpumask_var_t cpu_mask;
+	struct rdt_domain *d;
+	int cpu;
+
+	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	list_for_each_entry(d, &r->domains, list) {
+		/* Pick one CPU from each domain instance to update MSR */
+		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+	}
+	cpu = get_cpu();
+	/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
+	if (cpumask_test_cpu(cpu, cpu_mask))
+		l3_qos_cfg_update(&enable);
+	/* Update QOS_CFG MSR on all other cpus in cpu_mask. */
+	smp_call_function_many(cpu_mask, l3_qos_cfg_update, &enable, 1);
+	put_cpu();
+
+	free_cpumask_var(cpu_mask);
+
+	return 0;
+}
+
+static int cdp_enable(void)
+{
+	struct rdt_resource *r_l3data = &rdt_resources_all[RDT_RESOURCE_L3DATA];
+	struct rdt_resource *r_l3code = &rdt_resources_all[RDT_RESOURCE_L3CODE];
+	struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+	int ret;
+
+	if (!r_l3->capable || !r_l3data->capable || !r_l3code->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;
+	}
+	return ret;
+}
+
+static void cdp_disable(void)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	r->enabled = r->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;
+		set_l3_qos_cfg(r, false);
+	}
+}
+
+static int parse_rdtgroupfs_options(char *data)
+{
+	char *token, *o = data;
+	int ret = 0;
+
+	while ((token = strsep(&o, ",")) != NULL) {
+		if (!*token)
+			return -EINVAL;
+
+		if (!strcmp(token, "cdp"))
+			ret = cdp_enable();
+	}
+
+	return ret;
+}
+
+/*
+ * We don't allow rdtgroup directories to