cpuset.c

Kernel code of linux kernel

		mmput(mm);
	}

}

/* The various types of files and directories in a cpuset file system */

typedef enum {
	FILE_MEMORY_MIGRATE,
	FILE_CPULIST,
	FILE_MEMLIST,
	FILE_CPU_EXCLUSIVE,
	FILE_MEM_EXCLUSIVE,
	FILE_MEM_HARDWALL,
	FILE_SCHED_LOAD_BALANCE,
	FILE_SCHED_RELAX_DOMAIN_LEVEL,
	FILE_MEMORY_PRESSURE_ENABLED,
	FILE_MEMORY_PRESSURE,
	FILE_SPREAD_PAGE,
	FILE_SPREAD_SLAB,
} cpuset_filetype_t;

static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
{
	int retval = 0;
	struct cpuset *cs = cgroup_cs(cgrp);
	cpuset_filetype_t type = cft->private;

	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;

	switch (type) {
	case FILE_CPU_EXCLUSIVE:
		retval = update_flag(CS_CPU_EXCLUSIVE, cs, val);
		break;
	case FILE_MEM_EXCLUSIVE:
		retval = update_flag(CS_MEM_EXCLUSIVE, cs, val);
		break;
	case FILE_MEM_HARDWALL:
		retval = update_flag(CS_MEM_HARDWALL, cs, val);
		break;
	case FILE_SCHED_LOAD_BALANCE:
		retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val);
		break;
	case FILE_MEMORY_MIGRATE:
		retval = update_flag(CS_MEMORY_MIGRATE, cs, val);
		break;
	case FILE_MEMORY_PRESSURE_ENABLED:
		cpuset_memory_pressure_enabled = !!val;
		break;
	case FILE_MEMORY_PRESSURE:
		retval = -EACCES;
		break;
	case FILE_SPREAD_PAGE:
		retval = update_flag(CS_SPREAD_PAGE, cs, val);
		cs->mems_generation = cpuset_mems_generation++;
		break;
	case FILE_SPREAD_SLAB:
		retval = update_flag(CS_SPREAD_SLAB, cs, val);
		cs->mems_generation = cpuset_mems_generation++;
		break;
	default:
		retval = -EINVAL;
		break;
	}
	cgroup_unlock();
	return retval;
}

static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val)
{
	int retval = 0;
	struct cpuset *cs = cgroup_cs(cgrp);
	cpuset_filetype_t type = cft->private;

	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;

	switch (type) {
	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
		retval = update_relax_domain_level(cs, val);
		break;
	default:
		retval = -EINVAL;
		break;
	}
	cgroup_unlock();
	return retval;
}

/*
 * Common handling for a write to a "cpus" or "mems" file.
 */
static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
				const char *buf)
{
	int retval = 0;

	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;

	switch (cft->private) {
	case FILE_CPULIST:
		retval = update_cpumask(cgroup_cs(cgrp), buf);
		break;
	case FILE_MEMLIST:
		retval = update_nodemask(cgroup_cs(cgrp), buf);
		break;
	default:
		retval = -EINVAL;
		break;
	}
	cgroup_unlock();
	return retval;
}

/*
 * These ascii lists should be read in a single call, by using a user
 * buffer large enough to hold the entire map.  If read in smaller
 * chunks, there is no guarantee of atomicity.  Since the display format
 * used, list of ranges of sequential numbers, is variable length,
 * and since these maps can change value dynamically, one could read
 * gibberish by doing partial reads while a list was changing.
 * A single large read to a buffer that crosses a page boundary is
 * ok, because the result being copied to user land is not recomputed
 * across a page fault.
 */

static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
{
	cpumask_t mask;

	mutex_lock(&callback_mutex);
	mask = cs->cpus_allowed;
	mutex_unlock(&callback_mutex);

	return cpulist_scnprintf(page, PAGE_SIZE, mask);
}

static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
{
	nodemask_t mask;

	mutex_lock(&callback_mutex);
	mask = cs->mems_allowed;
	mutex_unlock(&callback_mutex);

	return nodelist_scnprintf(page, PAGE_SIZE, mask);
}

static ssize_t cpuset_common_file_read(struct cgroup *cont,
				       struct cftype *cft,
				       struct file *file,
				       char __user *buf,
				       size_t nbytes, loff_t *ppos)
{
	struct cpuset *cs = cgroup_cs(cont);
	cpuset_filetype_t type = cft->private;
	char *page;
	ssize_t retval = 0;
	char *s;

	if (!(page = (char *)__get_free_page(GFP_TEMPORARY)))
		return -ENOMEM;

	s = page;

	switch (type) {
	case FILE_CPULIST:
		s += cpuset_sprintf_cpulist(s, cs);
		break;
	case FILE_MEMLIST:
		s += cpuset_sprintf_memlist(s, cs);
		break;
	default:
		retval = -EINVAL;
		goto out;
	}
	*s++ = '\n';

	retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
out:
	free_page((unsigned long)page);
	return retval;
}

static u64 cpuset_read_u64(struct cgroup *cont, struct cftype *cft)
{
	struct cpuset *cs = cgroup_cs(cont);
	cpuset_filetype_t type = cft->private;
	switch (type) {
	case FILE_CPU_EXCLUSIVE:
		return is_cpu_exclusive(cs);
	case FILE_MEM_EXCLUSIVE:
		return is_mem_exclusive(cs);
	case FILE_MEM_HARDWALL:
		return is_mem_hardwall(cs);
	case FILE_SCHED_LOAD_BALANCE:
		return is_sched_load_balance(cs);
	case FILE_MEMORY_MIGRATE:
		return is_memory_migrate(cs);
	case FILE_MEMORY_PRESSURE_ENABLED:
		return cpuset_memory_pressure_enabled;
	case FILE_MEMORY_PRESSURE:
		return fmeter_getrate(&cs->fmeter);
	case FILE_SPREAD_PAGE:
		return is_spread_page(cs);
	case FILE_SPREAD_SLAB:
		return is_spread_slab(cs);
	default:
		BUG();
	}

	/* Unreachable but makes gcc happy */
	return 0;
}

static s64 cpuset_read_s64(struct cgroup *cont, struct cftype *cft)
{
	struct cpuset *cs = cgroup_cs(cont);
	cpuset_filetype_t type = cft->private;
	switch (type) {
	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
		return cs->relax_domain_level;
	default:
		BUG();
	}

	/* Unrechable but makes gcc happy */
	return 0;
}


/*
 * for the common functions, 'private' gives the type of file
 */

static struct cftype files[] = {
	{
		.name = "cpus",
		.read = cpuset_common_file_read,
		.write_string = cpuset_write_resmask,
		.max_write_len = (100U + 6 * NR_CPUS),
		.private = FILE_CPULIST,
	},

	{
		.name = "mems",
		.read = cpuset_common_file_read,
		.write_string = cpuset_write_resmask,
		.max_write_len = (100U + 6 * MAX_NUMNODES),
		.private = FILE_MEMLIST,
	},

	{
		.name = "cpu_exclusive",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_CPU_EXCLUSIVE,
	},

	{
		.name = "mem_exclusive",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEM_EXCLUSIVE,
	},

	{
		.name = "mem_hardwall",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEM_HARDWALL,
	},

	{
		.name = "sched_load_balance",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_SCHED_LOAD_BALANCE,
	},

	{
		.name = "sched_relax_domain_level",
		.read_s64 = cpuset_read_s64,
		.write_s64 = cpuset_write_s64,
		.private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
	},

	{
		.name = "memory_migrate",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEMORY_MIGRATE,
	},

	{
		.name = "memory_pressure",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_MEMORY_PRESSURE,
	},

	{
		.name = "memory_spread_page",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_SPREAD_PAGE,
	},

	{
		.name = "memory_spread_slab",
		.read_u64 = cpuset_read_u64,
		.write_u64 = cpuset_write_u64,
		.private = FILE_SPREAD_SLAB,
	},
};

static struct cftype cft_memory_pressure_enabled = {
	.name = "memory_pressure_enabled",
	.read_u64 = cpuset_read_u64,
	.write_u64 = cpuset_write_u64,
	.private = FILE_MEMORY_PRESSURE_ENABLED,
};

static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
{
	int err;

	err = cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
	if (err)
		return err;
	/* memory_pressure_enabled is in root cpuset only */
	if (!cont->parent)
		err = cgroup_add_file(cont, ss,
				      &cft_memory_pressure_enabled);
	return err;
}

/*
 * post_clone() is called at the end of cgroup_clone().
 * 'cgroup' was just created automatically as a result of
 * a cgroup_clone(), and the current task is about to
 * be moved into 'cgroup'.
 *
 * Currently we refuse to set up the cgroup - thereby
 * refusing the task to be entered, and as a result refusing
 * the sys_unshare() or clone() which initiated it - if any
 * sibling cpusets have exclusive cpus or mem.
 *
 * If this becomes a problem for some users who wish to
 * allow that scenario, then cpuset_post_clone() could be
 * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
 * (and likewise for mems) to the new cgroup. Called with cgroup_mutex
 * held.
 */
static void cpuset_post_clone(struct cgroup_subsys *ss,
			      struct cgroup *cgroup)
{
	struct cgroup *parent, *child;
	struct cpuset *cs, *parent_cs;

	parent = cgroup->parent;
	list_for_each_entry(child, &parent->children, sibling) {
		cs = cgroup_cs(child);
		if (is_mem_exclusive(cs) || is_cpu_exclusive(cs))
			return;
	}
	cs = cgroup_cs(cgroup);
	parent_cs = cgroup_cs(parent);

	cs->mems_allowed = parent_cs->mems_allowed;
	cs->cpus_allowed = parent_cs->cpus_allowed;
	return;
}

/*
 *	cpuset_create - create a cpuset
 *	ss:	cpuset cgroup subsystem
 *	cont:	control group that the new cpuset will be part of
 */

static struct cgroup_subsys_state *cpuset_create(
	struct cgroup_subsys *ss,
	struct cgroup *cont)
{
	struct cpuset *cs;
	struct cpuset *parent;

	if (!cont->parent) {
		/* This is early initialization for the top cgroup */
		top_cpuset.mems_generation = cpuset_mems_generation++;
		return &top_cpuset.css;
	}
	parent = cgroup_cs(cont->parent);
	cs = kmalloc(sizeof(*cs), GFP_KERNEL);
	if (!cs)
		return ERR_PTR(-ENOMEM);

	cpuset_update_task_memory_state();
	cs->flags = 0;
	if (is_spread_page(parent))
		set_bit(CS_SPREAD_PAGE, &cs->flags);
	if (is_spread_slab(parent))
		set_bit(CS_SPREAD_SLAB, &cs->flags);
	set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
	cpus_clear(cs->cpus_allowed);
	nodes_clear(cs->mems_allowed);
	cs->mems_generation = cpuset_mems_generation++;
	fmeter_init(&cs->fmeter);
	cs->relax_domain_level = -1;

	cs->parent = parent;
	number_of_cpusets++;
	return &cs->css ;
}

/*
 * If the cpuset being removed has its flag 'sched_load_balance'
 * enabled, then simulate turning sched_load_balance off, which
 * will call async_rebuild_sched_domains().
 */

static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
{
	struct cpuset *cs = cgroup_cs(cont);

	cpuset_update_task_memory_state();

	if (is_sched_load_balance(cs))
		update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);

	number_of_cpusets--;
	kfree(cs);
}

struct cgroup_subsys cpuset_subsys = {
	.name = "cpuset",
	.create = cpuset_create,
	.destroy = cpuset_destroy,
	.can_attach = cpuset_can_attach,
	.attach = cpuset_attach,
	.populate = cpuset_populate,
	.post_clone = cpuset_post_clone,
	.subsys_id = cpuset_subsys_id,
	.early_init = 1,
};