path: root/fs/resctrl/pseudo_lock.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Resource Director Technology (RDT)
 *
 * Pseudo-locking support built on top of Cache Allocation Technology (CAT)
 *
 * Copyright (C) 2018 Intel Corporation
 *
 * Author: Reinette Chatre <reinette.chatre@intel.com>
 */

#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt

#include <linux/cacheinfo.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/debugfs.h>
#include <linux/kthread.h>
#include <linux/mman.h>
#include <linux/pm_qos.h>
#include <linux/resctrl.h>
#include <linux/slab.h>
#include <linux/uaccess.h>

#include "internal.h"

/*
 * Major number assigned to and shared by all devices exposing
 * pseudo-locked regions.
 */
static unsigned int pseudo_lock_major;

static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0);

static char *pseudo_lock_devnode(const struct device *dev, umode_t *mode)
{
	const struct rdtgroup *rdtgrp;

	rdtgrp = dev_get_drvdata(dev);
	if (mode)
		*mode = 0600;
	guard(mutex)(&rdtgroup_mutex);
	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdt_kn_name(rdtgrp->kn));
}

static const struct class pseudo_lock_class = {
	.name = "pseudo_lock",
	.devnode = pseudo_lock_devnode,
};

/**
 * pseudo_lock_minor_get - Obtain available minor number
 * @minor: Pointer to where new minor number will be stored
 *
 * A bitmask is used to track available minor numbers. Here the next free
 * minor number is marked as unavailable and returned.
 *
 * Return: 0 on success, <0 on failure.
 */
static int pseudo_lock_minor_get(unsigned int *minor)
{
	unsigned long first_bit;

	first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS);

	if (first_bit == MINORBITS)
		return -ENOSPC;

	__clear_bit(first_bit, &pseudo_lock_minor_avail);
	*minor = first_bit;

	return 0;
}

/**
 * pseudo_lock_minor_release - Return minor number to available
 * @minor: The minor number made available
 */
static void pseudo_lock_minor_release(unsigned int minor)
{
	__set_bit(minor, &pseudo_lock_minor_avail);
}

/**
 * region_find_by_minor - Locate a pseudo-lock region by inode minor number
 * @minor: The minor number of the device representing pseudo-locked region
 *
 * When the character device is accessed we need to determine which
 * pseudo-locked region it belongs to. This is done by matching the minor
 * number of the device to the pseudo-locked region it belongs.
 *
 * Minor numbers are assigned at the time a pseudo-locked region is associated
 * with a cache instance.
 *
 * Return: On success return pointer to resource group owning the pseudo-locked
 *         region, NULL on failure.
 */
static struct rdtgroup *region_find_by_minor(unsigned int minor)
{
	struct rdtgroup *rdtgrp, *rdtgrp_match = NULL;

	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
		if (rdtgrp->plr && rdtgrp->plr->minor == minor) {
			rdtgrp_match = rdtgrp;
			break;
		}
	}
	return rdtgrp_match;
}

/**
 * struct pseudo_lock_pm_req - A power management QoS request list entry
 * @list:	Entry within the @pm_reqs list for a pseudo-locked region
 * @req:	PM QoS request
 */
struct pseudo_lock_pm_req {
	struct list_head list;
	struct dev_pm_qos_request req;
};

static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr)
{
	struct pseudo_lock_pm_req *pm_req, *next;

	list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) {
		dev_pm_qos_remove_request(&pm_req->req);
		list_del(&pm_req->list);
		kfree(pm_req);
	}
}

/**
 * pseudo_lock_cstates_constrain - Restrict cores from entering C6
 * @plr: Pseudo-locked region
 *
 * To prevent the cache from being affected by power management entering
 * C6 has to be avoided. This is accomplished by requesting a latency
 * requirement lower than lowest C6 exit latency of all supported
 * platforms as found in the cpuidle state tables in the intel_idle driver.
 * At this time it is possible to do so with a single latency requirement
 * for all supported platforms.
 *
 * Since Goldmont is supported, which is affected by X86_BUG_MONITOR,
 * the ACPI latencies need to be considered while keeping in mind that C2
 * may be set to map to deeper sleep states. In this case the latency
 * requirement needs to prevent entering C2 also.
 *
 * Return: 0 on success, <0 on failure
 */
static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
{
	struct pseudo_lock_pm_req *pm_req;
	int cpu;
	int ret;

	for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
		if (!pm_req) {
			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
			ret = -ENOMEM;
			goto out_err;
		}
		ret = dev_pm_qos_add_request(get_cpu_device(cpu),
					     &pm_req->req,
					     DEV_PM_QOS_RESUME_LATENCY,
					     30);
		if (ret < 0) {
			rdt_last_cmd_printf("Failed to add latency req CPU%d\n",
					    cpu);
			kfree(pm_req);
			ret = -1;
			goto out_err;
		}
		list_add(&pm_req->list, &plr->pm_reqs);
	}

	return 0;

out_err:
	pseudo_lock_cstates_relax(plr);
	return ret;
}

/**
 * pseudo_lock_region_clear - Reset pseudo-lock region data
 * @plr: pseudo-lock region
 *
 * All content of the pseudo-locked region is reset - any memory allocated
 * freed.
 *
 * Return: void
 */
static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
{
	plr->size = 0;
	plr->line_size = 0;
	kfree(plr->kmem);
	plr->kmem = NULL;
	plr->s = NULL;
	if (plr->d)
		plr->