// SPDX-License-Identifier: GPL-2.0

/*
 * CPU accounting code for task groups.
 *
 * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
 * (balbir@in.ibm.com).
 */

/* Time spent by the tasks of the CPU accounting group executing in ... */
enum cpuacct_stat_index {
        CPUACCT_STAT_USER,      /* ... user mode */
        CPUACCT_STAT_SYSTEM,    /* ... kernel mode */

        CPUACCT_STAT_NSTATS,
};

static const char * const cpuacct_stat_desc[] = {
        [CPUACCT_STAT_USER] = "user",
        [CPUACCT_STAT_SYSTEM] = "system",
};

/* track CPU usage of a group of tasks and its child groups */
struct cpuacct {
        struct cgroup_subsys_state      css;
        /* cpuusage holds pointer to a u64-type object on every CPU */
        u64 __percpu    *cpuusage;
        struct kernel_cpustat __percpu  *cpustat;
};

static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css)
{
        return css ? container_of(css, struct cpuacct, css) : NULL;
}

/* Return CPU accounting group to which this task belongs */
static inline struct cpuacct *task_ca(struct task_struct *tsk)
{
        return css_ca(task_css(tsk, cpuacct_cgrp_id));
}

static inline struct cpuacct *parent_ca(struct cpuacct *ca)
{
        return css_ca(ca->css.parent);
}

static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage);
static struct cpuacct root_cpuacct = {
        .cpustat        = &kernel_cpustat,
        .cpuusage       = &root_cpuacct_cpuusage,
};

/* Create a new CPU accounting group */
static struct cgroup_subsys_state *
cpuacct_css_alloc(struct cgroup_subsys_state *parent_css)
{
        struct cpuacct *ca;

        if (!parent_css)
                return &root_cpuacct.css;

        ca = kzalloc(sizeof(*ca), GFP_KERNEL);
        if (!ca)
                goto out;

        ca->cpuusage = alloc_percpu(u64);
        if (!ca->cpuusage)
                goto out_free_ca;

        ca->cpustat = alloc_percpu(struct kernel_cpustat);
        if (!ca->cpustat)
                goto out_free_cpuusage;

        return &ca->css;

out_free_cpuusage:
        free_percpu(ca->cpuusage);
out_free_ca:
        kfree(ca);
out:
        return ERR_PTR(-ENOMEM);
}

/* Destroy an existing CPU accounting group */
static void cpuacct_css_free(struct cgroup_subsys_state *css)
{
        struct cpuacct *ca = css_ca(css);

        free_percpu(ca->cpustat);
        free_percpu(ca->cpuusage);
        kfree(ca);
}

static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu,
                                 enum cpuacct_stat_index index)
{
        u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
        u64 *cpustat = per_cpu_ptr(ca->cpustat, cpu)->cpustat;
        u64 data;

        /*
         * We allow index == CPUACCT_STAT_NSTATS here to read
         * the sum of usages.
         */
        if (WARN_ON_ONCE(index > CPUACCT_STAT_NSTATS))
                return 0;

#ifndef CONFIG_64BIT
        /*
         * Take rq->lock to make 64-bit read safe on 32-bit platforms.
         */
        raw_spin_rq_lock_irq(cpu_rq(cpu));
#endif

        switch (index) {
        case CPUACCT_STAT_USER:
                data = cpustat[CPUTIME_USER] + cpustat[CPUTIME_NICE];
                break;
        case CPUACCT_STAT_SYSTEM:
                data = cpustat[CPUTIME_SYSTEM] + cpustat[CPUTIME_IRQ] +
                        cpustat[CPUTIME_SOFTIRQ];
                break;
        case CPUACCT_STAT_NSTATS:
                data = *cpuusage;
                break;
        }

#ifndef CONFIG_64BIT
        raw_spin_rq_unlock_irq(cpu_rq(cpu));
#endif

        return data;
}

static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu)
{
        u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
        u64 *cpustat = per_cpu_ptr(ca->cpustat, cpu)->cpustat;

        /* Don't allow to reset global kernel_cpustat */
        if (ca == &root_cpuacct)
                return;

#ifndef CONFIG_64BIT
        /*
         * Take rq->lock to make 64-bit write safe on 32-bit platforms.
         */
        raw_spin_rq_lock_irq(cpu_rq(cpu));
#endif
        *cpuusage = 0;
        cpustat[CPUTIME_USER] = cpustat[CPUTIME_NICE] = 0;
        cpustat[CPUTIME_SYSTEM] = cpustat[CPUTIME_IRQ] = 0;
        cpustat[CPUTIME_SOFTIRQ] = 0;

#ifndef CONFIG_64BIT
        raw_spin_rq_unlock_irq(cpu_rq(cpu));
#endif
}

/* Return total CPU usage (in nanoseconds) of a group */
static u64 __cpuusage_read(struct cgroup_subsys_state *css,
                           enum cpuacct_stat_index index)
{
        struct cpuacct *ca = css_ca(css);
        u64 totalcpuusage = 0;
        int i;

        for_each_possible_cpu(i)
                totalcpuusage += cpuacct_cpuusage_read(ca, i, index);

        return totalcpuusage;
}

static u64 cpuusage_user_read(struct cgroup_subsys_state *css,
                              struct cftype *cft)
{
        return __cpuusage_read(css, CPUACCT_STAT_USER);
}

static u64 cpuusage_sys_read(struct cgroup_subsys_state *css,
                             struct cftype *cft)
{
        return __cpuusage_read(css, CPUACCT_STAT_SYSTEM);
}

static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft)
{
        return __cpuusage_read(css, CPUACCT_STAT_NSTATS);
}

static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft,
                          u64 val)
{
        struct cpuacct *ca = css_ca(css);
        int cpu;

        /*
         * Only allow '0' here to do a reset.
         */
        if (val)
                return -EINVAL;

        for_each_possible_cpu(cpu)
                cpuacct_cpuusage_write(ca, cpu);

        return 0;
}

static int __cpuacct_percpu_seq_show(struct seq_file *m,
                                     enum cpuacct_stat_index index)
{
        struct cpuacct *ca = css_ca(seq_css(m));
        u64 percpu;
        int i;

        for_each_possible_cpu(i) {
                percpu = cpuacct_cpuusage_read(ca, i, index);
                seq_printf(m, "%llu ", (unsigned long long) percpu);
        }
        seq_printf(m, "\n");
        return 0;
}

static int cpuacct_percpu_user_seq_show(struct seq_file *m, void *V)
{
        return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_USER);
}

static int cpuacct_percpu_sys_seq_show(struct seq_file *m, void *V)
{
        return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_SYSTEM);
}

static int cpuacct_percpu_seq_show(struct seq_file *m, void *V)
{
        return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_NSTATS);
}

static int cpuacct_all_seq_show(struct seq_file *m, void *V)
{
        struct cpuacct *ca = css_ca(seq_css(m));
        int index;
        int cpu;

        seq_puts(m, "cpu");
        for (index = 0; index < CPUACCT_STAT_NSTATS; index++)
                seq_printf(m, " %s", cpuacct_stat_desc[index]);
        seq_puts(m, "\n");

        for_each_possible_cpu(cpu) {
                seq_printf(m, "%d", cpu);
                for (index = 0; index < CPUACCT_STAT_NSTATS; index++)
                        seq_printf(m, " %llu",
                                   cpuacct_cpuusage_read(ca, cpu, index));
                seq_puts(m, "\n");
        }
        return 0;
}

static int cpuacct_stats_show(struct seq_file *sf, void *v)
{
        struct cpuacct *ca = css_ca(seq_css(sf));
        struct task_cputime cputime;
        u64 val[CPUACCT_STAT_NSTATS];
        int cpu;
        int stat;

        memset(&cputime, 0, sizeof(cputime));
        for_each_possible_cpu(cpu) {
                u64 *cpustat = per_cpu_ptr(ca->cpustat, cpu)->cpustat;

                cputime.utime += cpustat[CPUTIME_USER];
                cputime.utime += cpustat[CPUTIME_NICE];
                cputime.stime += cpustat[CPUTIME_SYSTEM];
                cputime.stime += cpustat[CPUTIME_IRQ];
                cputime.stime += cpustat[CPUTIME_SOFTIRQ];

                cputime.sum_exec_runtime += *per_cpu_ptr(ca->cpuusage, cpu);
        }

        cputime_adjust(&cputime, &seq_css(sf)->cgroup->prev_cputime,
                &val[CPUACCT_STAT_USER], &val[CPUACCT_STAT_SYSTEM]);

        for (stat = 0; stat < CPUACCT_STAT_NSTATS; stat++) {
                seq_printf(sf, "%s %llu\n", cpuacct_stat_desc[stat],
                        nsec_to_clock_t(val[stat]));
        }

        return 0;
}

static struct cftype files[] = {
        {
                .name = "usage",
                .read_u64 = cpuusage_read,
                .write_u64 = cpuusage_write,
        },
        {
                .name = "usage_user",
                .read_u64 = cpuusage_user_read,
        },
        {
                .name = "usage_sys",
                .read_u64 = cpuusage_sys_read,
        },
        {
                .name = "usage_percpu",
                .seq_show = cpuacct_percpu_seq_show,
        },
        {
                .name = "usage_percpu_user",
                .seq_show = cpuacct_percpu_user_seq_show,
        },
        {
                .name = "usage_percpu_sys",
                .seq_show = cpuacct_percpu_sys_seq_show,
        },
        {
                .name = "usage_all",
                .seq_show = cpuacct_all_seq_show,
        },
        {
                .name = "stat",
                .seq_show = cpuacct_stats_show,
        },
        { }     /* terminate */
};

/*
 * charge this task's execution time to its accounting group.
 *
 * called with rq->lock held.
 */
void cpuacct_charge(struct task_struct *tsk, u64 cputime)
{
        unsigned int cpu = task_cpu(tsk);
        struct cpuacct *ca;

        lockdep_assert_rq_held(cpu_rq(cpu));

        for (ca = task_ca(tsk); ca; ca = parent_ca(ca))
                *per_cpu_ptr(ca->cpuusage, cpu) += cputime;
}

/*
 * Add user/system time to cpuacct.
 *
 * Note: it's the caller that updates the account of the root cgroup.
 */
void cpuacct_account_field(struct task_struct *tsk, int index, u64 val)
{
        struct cpuacct *ca;

        for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca))
                __this_cpu_add(ca->cpustat->cpustat[index], val);
}

struct cgroup_subsys cpuacct_cgrp_subsys = {
        .css_alloc      = cpuacct_css_alloc,
        .css_free       = cpuacct_css_free,
        .legacy_cftypes = files,
        .early_init     = true,
};