cpuset.c

linux 2.6.19 kernel source code before patching

	start = buf + buflen;

	*--start = '\0';
	for (;;) {
		int len = cs->dentry->d_name.len;
		if ((start -= len) < buf)
			return -ENAMETOOLONG;
		memcpy(start, cs->dentry->d_name.name, len);
		cs = cs->parent;
		if (!cs)
			break;
		if (!cs->parent)
			continue;
		if (--start < buf)
			return -ENAMETOOLONG;
		*start = '/';
	}
	memmove(buf, start, buf + buflen - start);
	return 0;
}

/*
 * Notify userspace when a cpuset is released, by running
 * /sbin/cpuset_release_agent with the name of the cpuset (path
 * relative to the root of cpuset file system) as the argument.
 *
 * Most likely, this user command will try to rmdir this cpuset.
 *
 * This races with the possibility that some other task will be
 * attached to this cpuset before it is removed, or that some other
 * user task will 'mkdir' a child cpuset of this cpuset.  That's ok.
 * The presumed 'rmdir' will fail quietly if this cpuset is no longer
 * unused, and this cpuset will be reprieved from its death sentence,
 * to continue to serve a useful existence.  Next time it's released,
 * we will get notified again, if it still has 'notify_on_release' set.
 *
 * The final arg to call_usermodehelper() is 0, which means don't
 * wait.  The separate /sbin/cpuset_release_agent task is forked by
 * call_usermodehelper(), then control in this thread returns here,
 * without waiting for the release agent task.  We don't bother to
 * wait because the caller of this routine has no use for the exit
 * status of the /sbin/cpuset_release_agent task, so no sense holding
 * our caller up for that.
 *
 * When we had only one cpuset mutex, we had to call this
 * without holding it, to avoid deadlock when call_usermodehelper()
 * allocated memory.  With two locks, we could now call this while
 * holding manage_mutex, but we still don't, so as to minimize
 * the time manage_mutex is held.
 */

static void cpuset_release_agent(const char *pathbuf)
{
	char *argv[3], *envp[3];
	int i;

	if (!pathbuf)
		return;

	i = 0;
	argv[i++] = "/sbin/cpuset_release_agent";
	argv[i++] = (char *)pathbuf;
	argv[i] = NULL;

	i = 0;
	/* minimal command environment */
	envp[i++] = "HOME=/";
	envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
	envp[i] = NULL;

	call_usermodehelper(argv[0], argv, envp, 0);
	kfree(pathbuf);
}

/*
 * Either cs->count of using tasks transitioned to zero, or the
 * cs->children list of child cpusets just became empty.  If this
 * cs is notify_on_release() and now both the user count is zero and
 * the list of children is empty, prepare cpuset path in a kmalloc'd
 * buffer, to be returned via ppathbuf, so that the caller can invoke
 * cpuset_release_agent() with it later on, once manage_mutex is dropped.
 * Call here with manage_mutex held.
 *
 * This check_for_release() routine is responsible for kmalloc'ing
 * pathbuf.  The above cpuset_release_agent() is responsible for
 * kfree'ing pathbuf.  The caller of these routines is responsible
 * for providing a pathbuf pointer, initialized to NULL, then
 * calling check_for_release() with manage_mutex held and the address
 * of the pathbuf pointer, then dropping manage_mutex, then calling
 * cpuset_release_agent() with pathbuf, as set by check_for_release().
 */

static void check_for_release(struct cpuset *cs, char **ppathbuf)
{
	if (notify_on_release(cs) && atomic_read(&cs->count) == 0 &&
	    list_empty(&cs->children)) {
		char *buf;

		buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
		if (!buf)
			return;
		if (cpuset_path(cs, buf, PAGE_SIZE) < 0)
			kfree(buf);
		else
			*ppathbuf = buf;
	}
}

/*
 * Return in *pmask the portion of a cpusets's cpus_allowed that
 * are online.  If none are online, walk up the cpuset hierarchy
 * until we find one that does have some online cpus.  If we get
 * all the way to the top and still haven't found any online cpus,
 * return cpu_online_map.  Or if passed a NULL cs from an exit'ing
 * task, return cpu_online_map.
 *
 * One way or another, we guarantee to return some non-empty subset
 * of cpu_online_map.
 *
 * Call with callback_mutex held.
 */

static void guarantee_online_cpus(const struct cpuset *cs, cpumask_t *pmask)
{
	while (cs && !cpus_intersects(cs->cpus_allowed, cpu_online_map))
		cs = cs->parent;
	if (cs)
		cpus_and(*pmask, cs->cpus_allowed, cpu_online_map);
	else
		*pmask = cpu_online_map;
	BUG_ON(!cpus_intersects(*pmask, cpu_online_map));
}

/*
 * Return in *pmask the portion of a cpusets's mems_allowed that
 * are online.  If none are online, walk up the cpuset hierarchy
 * until we find one that does have some online mems.  If we get
 * all the way to the top and still haven't found any online mems,
 * return node_online_map.
 *
 * One way or another, we guarantee to return some non-empty subset
 * of node_online_map.
 *
 * Call with callback_mutex held.
 */

static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
{
	while (cs && !nodes_intersects(cs->mems_allowed, node_online_map))
		cs = cs->parent;
	if (cs)
		nodes_and(*pmask, cs->mems_allowed, node_online_map);
	else
		*pmask = node_online_map;
	BUG_ON(!nodes_intersects(*pmask, node_online_map));
}

/**
 * cpuset_update_task_memory_state - update task memory placement
 *
 * If the current tasks cpusets mems_allowed changed behind our
 * backs, update current->mems_allowed, mems_generation and task NUMA
 * mempolicy to the new value.
 *
 * Task mempolicy is updated by rebinding it relative to the
 * current->cpuset if a task has its memory placement changed.
 * Do not call this routine if in_interrupt().
 *
 * Call without callback_mutex or task_lock() held.  May be
 * called with or without manage_mutex held.  Thanks in part to
 * 'the_top_cpuset_hack', the tasks cpuset pointer will never
 * be NULL.  This routine also might acquire callback_mutex and
 * current->mm->mmap_sem during call.
 *
 * Reading current->cpuset->mems_generation doesn't need task_lock
 * to guard the current->cpuset derefence, because it is guarded
 * from concurrent freeing of current->cpuset by attach_task(),
 * using RCU.
 *
 * The rcu_dereference() is technically probably not needed,
 * as I don't actually mind if I see a new cpuset pointer but
 * an old value of mems_generation.  However this really only
 * matters on alpha systems using cpusets heavily.  If I dropped
 * that rcu_dereference(), it would save them a memory barrier.
 * For all other arch's, rcu_dereference is a no-op anyway, and for
 * alpha systems not using cpusets, another planned optimization,
 * avoiding the rcu critical section for tasks in the root cpuset
 * which is statically allocated, so can't vanish, will make this
 * irrelevant.  Better to use RCU as intended, than to engage in
 * some cute trick to save a memory barrier that is impossible to
 * test, for alpha systems using cpusets heavily, which might not
 * even exist.
 *
 * This routine is needed to update the per-task mems_allowed data,
 * within the tasks context, when it is trying to allocate memory
 * (in various mm/mempolicy.c routines) and notices that some other
 * task has been modifying its cpuset.
 */

void cpuset_update_task_memory_state(void)
{
	int my_cpusets_mem_gen;
	struct task_struct *tsk = current;
	struct cpuset *cs;

	if (tsk->cpuset == &top_cpuset) {
		/* Don't need rcu for top_cpuset.  It's never freed. */
		my_cpusets_mem_gen = top_cpuset.mems_generation;
	} else {
		rcu_read_lock();
		cs = rcu_dereference(tsk->cpuset);
		my_cpusets_mem_gen = cs->mems_generation;
		rcu_read_unlock();
	}

	if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
		mutex_lock(&callback_mutex);
		task_lock(tsk);
		cs = tsk->cpuset;	/* Maybe changed when task not locked */
		guarantee_online_mems(cs, &tsk->mems_allowed);
		tsk->cpuset_mems_generation = cs->mems_generation;
		if (is_spread_page(cs))
			tsk->flags |= PF_SPREAD_PAGE;
		else
			tsk->flags &= ~PF_SPREAD_PAGE;
		if (is_spread_slab(cs))
			tsk->flags |= PF_SPREAD_SLAB;
		else
			tsk->flags &= ~PF_SPREAD_SLAB;
		task_unlock(tsk);
		mutex_unlock(&callback_mutex);
		mpol_rebind_task(tsk, &tsk->mems_allowed);
	}
}

/*
 * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q?
 *
 * One cpuset is a subset of another if all its allowed CPUs and
 * Memory Nodes are a subset of the other, and its exclusive flags
 * are only set if the other's are set.  Call holding manage_mutex.
 */

static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
{
	return	cpus_subset(p->cpus_allowed, q->cpus_allowed) &&
		nodes_subset(p->mems_allowed, q->mems_allowed) &&
		is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
		is_mem_exclusive(p) <= is_mem_exclusive(q);
}

/*
 * validate_change() - Used to validate that any proposed cpuset change
 *		       follows the structural rules for cpusets.
 *
 * If we replaced the flag and mask values of the current cpuset
 * (cur) with those values in the trial cpuset (trial), would
 * our various subset and exclusive rules still be valid?  Presumes
 * manage_mutex held.
 *
 * 'cur' is the address of an actual, in-use cpuset.  Operations
 * such as list traversal that depend on the actual address of the
 * cpuset in the list must use cur below, not trial.
 *
 * 'trial' is the address of bulk structure copy of cur, with
 * perhaps one or more of the fields cpus_allowed, mems_allowed,
 * or flags changed to new, trial values.
 *
 * Return 0 if valid, -errno if not.
 */

static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
{
	struct cpuset *c, *par;

	/* Each of our child cpusets must be a subset of us */
	list_for_each_entry(c, &cur->children, sibling) {
		if (!is_cpuset_subset(c, trial))
			return -EBUSY;
	}

	/* Remaining checks don't apply to root cpuset */
	if (cur == &top_cpuset)
		return 0;

	par = cur->parent;

	/* We must be a subset of our parent cpuset */
	if (!is_cpuset_subset(trial, par))
		return -EACCES;

	/* If either I or some sibling (!= me) is exclusive, we can't overlap */
	list_for_each_entry(c, &par->children, sibling) {
		if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
		    c != cur &&
		    cpus_intersects(trial->cpus_allowed, c->cpus_allowed))
			return -EINVAL;
		if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
		    c != cur &&
		    nodes_intersects(trial->mems_allowed, c->mems_allowed))
			return -EINVAL;
	}

	return 0;
}

/*
 * For a given cpuset cur, partition the system as follows
 * a. All cpus in the parent cpuset's cpus_allowed that are not part of any
 *    exclusive child cpusets
 * b. All cpus in the current cpuset's cpus_allowed that are not part of any
 *    exclusive child cpusets
 * Build these two partitions by calling partition_sched_domains
 *
 * Call with manage_mutex held.  May nest a call to the
 * lock_cpu_hotplug()/unlock_cpu_hotplug() pair.
 * Must not be called holding callback_mutex, because we must
 * not call lock_cpu_hotplug() while holding callback_mutex.
 */

static void update_cpu_domains(struct cpuset *cur)
{
	struct cpuset *c, *par = cur->parent;
	cpumask_t pspan, cspan;

	if (par == NULL || cpus_empty(cur->cpus_allowed))
		return;

	/*
	 * Get all cpus from parent's cpus_allowed not part of exclusive
	 * children
	 */
	pspan = par->cpus_allowed;
	list_for_each_entry(c, &par->children, sibling) {
		if (is_cpu_exclusive(c))
			cpus_andnot(pspan, pspan, c->cpus_allowed);
	}
	if (!is_cpu_exclusive(cur)) {
		cpus_or(pspan, pspan, cur->cpus_allowed);
		if (cpus_equal(pspan, cur->cpus_allowed))
			return;
		cspan = CPU_MASK_NONE;
	} else {
		if (cpus_empty(pspan))
			return;
		cspan = cur->cpus_allowed;
		/*
		 * Get all cpus from current cpuset's cpus_allowed not part
		 * of exclusive children
		 */
		list_for_each_entry(c, &cur->children, sibling) {
			if (is_cpu_exclusive(c))
				cpus_andnot(cspan, cspan, c->cpus_allowed);
		}
	}

	lock_cpu_hotplug();
	partition_sched_domains(&pspan, &cspan);
	unlock_cpu_hotplug();
}

/*
 * Call with manage_mutex held.  May take callback_mutex during call.
 */

static int update_cpumask(struct cpuset *cs, char *buf)
{
	struct cpuset trialcs;
	int retval, cpus_unchanged;

	/* top_cpuset.cpus_allowed tracks cpu_online_map; it's read-only */
	if (cs == &top_cpuset)
		return -EACCES;

	trialcs = *cs;

	/*
	 * We allow a cpuset's cpus_allowed to be empty; if it has attached
	 * tasks, we'll catch it later when we validate the change and return
	 * -ENOSPC.
	 */
	if (!buf[0] || (buf[0] == '\n' && !buf[1])) {
		cpus_clear(trialcs.cpus_allowed);
	} else {
		retval = cpulist_parse(buf, trialcs.cpus_allowed);
		if (retval < 0)
			return retval;
	}
	cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map);
	/* cpus_allowed cannot be empty for a cpuset with attached tasks. */
	if (atomic_read(&cs->count) && cpus_empty(trialcs.cpus_allowed))
		return -ENOSPC;
	retval = validate_change(cs, &trialcs);
	if (retval < 0)
		return retval;
	cpus_unchanged = cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed);
	mutex_lock(&callback_mutex);
	cs->cpus_allowed = trialcs.cpus_allowed;
	mutex_unlock(&callback_mutex);
	if (is_cpu_exclusive(cs) && !cpus_unchanged)
		update_cpu_domains(cs);
	return 0;
}

/*
 * cpuset_migrate_mm
 *
 *    Migrate memory region from one set of nodes to another.
 *
 *    Temporarilly set tasks mems_allowed to target nodes of migration,
 *    so that the migration code can allocate pages on these nodes.
 *
 *    Call holding manage_mutex, so our current->cpuset won't change
 *    during this call, as manage_mutex holds off any attach_task()
 *    calls.  Therefore we don't need to take task_lock around the
 *    call to guarantee_online_mems(), as we know no one is changing
 *    our tasks cpuset.
 *
 *    Hold callback_mutex around the two modifications of our tasks
 *    mems_allowed to synchronize with cpuset_mems_allowed().
 *
 *    While the mm_struct we are migrating is typically from some
 *    other task, the task_struct mems_allowed that we are hacking
 *    is for our current task, which must allocate new pages for that
 *    migrating memory region.
 *
 *    We call cpuset_update_task_memory_state() before hacking
 *    our tasks mems_allowed, so that we are assured of being in
 *    sync with our tasks cpuset, and in particular, callbacks to
 *    cpuset_update_task_memory_state() from nested page allocations
 *    won't see any mismatch of our cpuset and task mems_generation
 *    values, so won't overwrite our hacked tasks mems_allowed
 *    nodemask.
 */

static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
							const nodemask_t *to)
{
	struct task_struct *tsk = current;

	cpuset_update_task_memory_state();

	mutex_lock(&callback_mutex);
	tsk->mems_allowed = *to;
	mutex_unlock(&callback_mutex);