intel_rdt_rdtgroup.c

/*
 * 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/signal.h>
#include <linux/sched/task.h>
#include <linux/slab.h>
#include <linux/task_work.h>

#include <uapi/linux/magic.h>

#include <asm/intel_rdt_sched.h>
#include "intel_rdt.h"

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;

/*
 * 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_alloc_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;
}

static int closid_alloc(void)
{
	u32 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_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 bool is_cpu_list(struct kernfs_open_file *of)
{
	struct rftype *rft = of->kn->priv;

	return rft->flags & RFTYPE_FLAGS_CPUS_LIST;
}

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, is_cpu_list(of) ? "%*pbl\n" : "%*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;
	}

	if (is_cpu_list(of))
		ret = cpulist_parse(buf, newmask);
	else
		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;
		current->rmid = 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 {
		/*
		 * 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;
}

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 ((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();
}

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;
}

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_default_ctrl_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->default_ctrl);
	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, "%u\n", r->cache.min_cbm_bits);
	return 0;
}

static int rdt_min_bw_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", r->membw.min_bw);
	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)
{
	struct rdt_resource *r = of->kn->parent->priv;

	seq_printf(seq, "%u\n", r->membw.bw_gran);
	return 0;
}

static int rdt_delay_linear_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", r->membw.delay_linear);
	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 ret ?: nbytes;
}

/* rdtgroup information files for one cache resource. */
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,
	},
	{
		.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,
	},
};

static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
{
	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;
}

static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name,
				      unsigned long fflags)
{
	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 rdt_resource *r;
	unsigned long fflags;
	char name[32];
	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_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;
	}

	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;
	}

	/*
	 * 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 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;

	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->alloc_capable || !r_l3data->alloc_capable ||
	    !r_l3code->alloc_capable)
		return -EINVAL;

	ret = set_l3_qos_cfg(r_l3, true);
	if (!ret) {
		r_l3->alloc_enabled = false;
		r_l3data->alloc_enabled = true;
		r_l3code->alloc_enabled = true;
	}
	return ret;
}

static void cdp_disable(void)
{
	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];

	r->alloc_enabled = r->alloc_capable;

	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);
	}
}

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 be created anywhere
 * except the root directory. Thus when looking for the rdtgroup
 * structure for a kernfs node we are either looking at a directory,
 * in which case the rdtgroup structure is pointed at by the "priv"
 * field, otherwise we have a file, and need only look to the parent
 * to find the rdtgroup.
 */
static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn)
{
	if (kernfs_type(kn) == KERNFS_DIR) {
		/*
		 * All the resource directories use "kn->priv"
		 * to point to the "struct rdtgroup" for the
		 * resource. "info" and its subdirectories don't
		 * have rdtgroup structures, so return NULL here.
		 */
		if (kn == kn_info || kn->parent == kn_info)
			return NULL;
		else
			return kn->priv;
	} else {
		return kn->parent->priv;
	}
}

struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn)
{
	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);

	if (!rdtgrp)
		return NULL;

	atomic_inc(&rdtgrp->waitcount);
	kernfs_break_active_protection(kn);

	mutex_lock(&rdtgroup_mutex);

	/* Was this group deleted while we waited? */
	if (rdtgrp->flags & RDT_DELETED)
		return NULL;

	return rdtgrp;
}

void rdtgroup_kn_unlock(struct kernfs_node *kn)
{
	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);

	if (!rdtgrp)
		return;

	mutex_unlock(&rdtgroup_mutex);

	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
	    (rdtgrp->flags & RDT_DELETED)) {
		kernfs_unbreak_active_protection(kn);
		kernfs_put(rdtgrp->kn);
		kfree(rdtgrp);
	} else {
		kernfs_unbreak_active_protection(kn);
	}
}

static struct dentry *rdt_mount(struct file_system_type *fs_type,
				int flags, const char *unused_dev_name,
				void *data)
{
	struct dentry *dentry;
	int ret;

	mutex_lock(&rdtgroup_mutex);
	/*
	 * resctrl file system can only be mounted once.
	 */
	if (static_branch_unlikely(&rdt_alloc_enable_key)) {
		dentry = ERR_PTR(-EBUSY);
		goto out;
	}

	ret = parse_rdtgroupfs_options(data);
	if (ret) {
		dentry = ERR_PTR(ret);
		goto out_cdp;
	}

	closid_init();

	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
	if (ret) {
		dentry = ERR_PTR(ret);
		goto out_cdp;
	}

	dentry = kernfs_mount(fs_type, flags, rdt_root,
			      RDTGROUP_SUPER_MAGIC, NULL);
	if (IS_ERR(dentry))
		goto out_destroy;

	static_branch_enable(&rdt_alloc_enable_key);
	goto out;

out_destroy:
	kernfs_remove(kn_info);
out_cdp:
	cdp_disable();
out:
	mutex_unlock(&rdtgroup_mutex);

	return dentry;
}

static int reset_all_ctrls(struct rdt_resource *r)
{
	struct msr_param msr_param;
	cpumask_var_t cpu_mask;
	struct rdt_domain *d;
	int i, cpu;

	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
		return -ENOMEM;

	msr_param.res = r;
	msr_param.low = 0;
	msr_param.high = r->num_closid;

	/*
	 * Disable resource control for this resource by setting all
	 * CBMs in all domains to the maximum mask value. Pick one CPU
	 * from each domain to update the MSRs below.
	 */
	list_for_each_entry(d, &r->domains, list) {
		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);

		for (i = 0; i < r->num_closid; i++)
			d->ctrl_val[i] = r->default_ctrl;
	}
	cpu = get_cpu();
	/* Update CBM on this cpu if it's in cpu_mask. */
	if (cpumask_test_cpu(cpu, cpu_mask))
		rdt_ctrl_update(&msr_param);
	/* Update CBM on all other cpus in cpu_mask. */
	smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
	put_cpu();

	free_cpumask_var(cpu_mask);

	return 0;
}

/*
 * Move tasks from one to the other group. If @from is NULL, then all tasks
 * in the systems are moved unconditionally (used for teardown).
 *
 * If @mask is not NULL the cpus on which moved tasks are running are set
 * in that mask so the update smp function call is restricted to affected
 * cpus.
 */
static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
				 struct cpumask *mask)
{
	struct task_struct *p, *t;

	read_lock(&tasklist_lock);
	for_each_process_thread(p, t) {
		if (!from || t->closid == from->closid) {
			t->closid = to->closid;
#ifdef CONFIG_SMP
			/*
			 * This is safe on x86 w/o barriers as the ordering
			 * of writing to task_cpu() and t->on_cpu is
			 * reverse to the reading here. The detection is
			 * inaccurate as tasks might move or schedule
			 * before the smp function call takes place. In
			 * such a case the function call is pointless, but
			 * there is no other side effect.
			 */
			if (mask && t->on_cpu)
				cpumask_set_cpu(task_cpu(t), mask);
#endif
		}
	}
	read_unlock(&tasklist_lock);
}

/*
 * Forcibly remove all of subdirectories under root.
 */
static void rmdir_all_sub(void)
{
	struct rdtgroup *rdtgrp, *tmp;

	/* Move all tasks to the default resource group */
	rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);

	list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
		/* Remove each rdtgroup other than root */
		if (rdtgrp == &rdtgroup_default)
			continue;

		/*
		 * Give any CPUs back to the default group. We cannot copy
		 * cpu_online_mask because a CPU might have executed the
		 * offline callback already, but is still marked online.
		 */
		cpumask_or(&rdtgroup_default.cpu_mask,
			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);

		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);
	put_online_cpus();

	kernfs_remove(kn_info);
}

static void rdt_kill_sb(struct super_block *sb)
{
	struct rdt_resource *r;

	mutex_lock(&rdtgroup_mutex);

	/*Put everything back to default values. */
	for_each_alloc_enabled_rdt_resource(r)
		reset_all_ctrls(r);
	cdp_disable();
	rmdir_all_sub();
	static_branch_disable(&rdt_alloc_enable_key);
	kernfs_kill_sb(sb);
	mutex_unlock(&rdtgroup_mutex);
}

static struct file_system_type rdt_fs_type = {
	.name    = "resctrl",
	.mount   = rdt_mount,
	.kill_sb = rdt_kill_sb,
};

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;
	}

	/* allocate the rdtgroup. */
	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
	if (!rdtgrp) {
		ret = -ENOSPC;
		goto out_unlock;
	}
	*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);
	if (IS_ERR(kn)) {
		ret = PTR_ERR(kn);
		goto out_free_rgrp;
	}
	rdtgrp->kn = kn;

	/*
	 * kernfs_remove() will drop the reference count on "kn" which
	 * will free it. But we still need it to stick around for the
	 * rdtgroup_kn_unlock(kn} call below. Take one extra reference
	 * here, which will be dropped inside rdtgroup_kn_unlock().
	 */
	kernfs_get(kn);

	ret = rdtgroup_kn_set_ugid(kn);
	if (ret)
		goto out_destroy;

	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;
	}
	kernfs_activate(kn);

	/*
	 * The caller unlocks the prgrp_kn upon success.
	 */
	return 0;

out_destroy:
	kernfs_remove(rdtgrp->kn);
out_free_rgrp:
	kfree(rdtgrp);
out_unlock:
	rdtgroup_kn_unlock(prgrp_kn);
	return ret;
}

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)
{
	struct rdtgroup *rdtgrp;
	struct kernfs_node *kn;
	u32 closid;
	int ret;

	ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTCTRL_GROUP,
				&rdtgrp);
	if (ret)
		return ret;

	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(struct kernfs_node *kn)
{
	int ret, cpu, closid = rdtgroup_default.closid;
	struct rdtgroup *rdtgrp;
	cpumask_var_t tmpmask;

	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
		return -ENOMEM;

	rdtgrp = rdtgroup_kn_lock_live(kn);
	if (!rdtgrp) {
		ret = -EPERM;
		goto out;
	}

	/* Give any tasks back to the default group */
	rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask);

	/* Give any CPUs back to the default group */
	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 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);

	rdtgrp->flags = RDT_DELETED;
	closid_free(rdtgrp->closid);
	list_del(&rdtgrp->rdtgroup_list);

	/*
	 * one extra hold on this, will drop when we kfree(rdtgrp)
	 * in rdtgroup_kn_unlock()
	 */
	kernfs_get(kn);
	kernfs_remove(rdtgrp->kn);
	ret = 0;
out:
	rdtgroup_kn_unlock(kn);
	free_cpumask_var(tmpmask);
	return ret;
}

static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
{
	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled)
		seq_puts(seq, ",cdp");
	return 0;
}

static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
	.mkdir		= rdtgroup_mkdir,
	.rmdir		= rdtgroup_rmdir,
	.show_options	= rdtgroup_show_options,
};

static int __init rdtgroup_setup_root(void)
{
	int ret;

	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
				      KERNFS_ROOT_CREATE_DEACTIVATED,
				      &rdtgroup_default);
	if (IS_ERR(rdt_root))
		return PTR_ERR(rdt_root);

	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, RF_CTRL_BASE);
	if (ret) {
		kernfs_destroy_root(rdt_root);
		goto out;
	}

	rdtgroup_default.kn = rdt_root->kn;
	kernfs_activate(rdtgroup_default.kn);

out:
	mutex_unlock(&rdtgroup_mutex);

	return ret;
}

/*
 * rdtgroup_init - rdtgroup initialization
 *
 * Setup resctrl file system including set up root, create mount point,
 * register rdtgroup filesystem, and initialize files under root directory.
 *
 * Return: 0 on success or -errno
 */
int __init rdtgroup_init(void)
{
	int ret = 0;

	ret = rdtgroup_setup_root();
	if (ret)
		return ret;

	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
	if (ret)
		goto cleanup_root;

	ret = register_filesystem(&rdt_fs_type);
	if (ret)
		goto cleanup_mountpoint;

	return 0;

cleanup_mountpoint:
	sysfs_remove_mount_point(fs_kobj, "resctrl");
cleanup_root:
	kernfs_destroy_root(rdt_root);

	return ret;
}