cpuset.c

linux 2.6.19 kernel source code before patching

	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);

	mutex_lock(&callback_mutex);
	guarantee_online_mems(tsk->cpuset, &tsk->mems_allowed);
	mutex_unlock(&callback_mutex);
}

/*
 * Handle user request to change the 'mems' memory placement
 * of a cpuset.  Needs to validate the request, update the
 * cpusets mems_allowed and mems_generation, and for each
 * task in the cpuset, rebind any vma mempolicies and if
 * the cpuset is marked 'memory_migrate', migrate the tasks
 * pages to the new memory.
 *
 * Call with manage_mutex held.  May take callback_mutex during call.
 * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
 * lock each such tasks mm->mmap_sem, scan its vma's and rebind
 * their mempolicies to the cpusets new mems_allowed.
 */

static int update_nodemask(struct cpuset *cs, char *buf)
{
	struct cpuset trialcs;
	nodemask_t oldmem;
	struct task_struct *g, *p;
	struct mm_struct **mmarray;
	int i, n, ntasks;
	int migrate;
	int fudge;
	int retval;

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

	trialcs = *cs;

	/*
	 * We allow a cpuset's mems_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])) {
		nodes_clear(trialcs.mems_allowed);
	} else {
		retval = nodelist_parse(buf, trialcs.mems_allowed);
		if (retval < 0)
			goto done;
	}
	nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, node_online_map);
	oldmem = cs->mems_allowed;
	if (nodes_equal(oldmem, trialcs.mems_allowed)) {
		retval = 0;		/* Too easy - nothing to do */
		goto done;
	}
	/* mems_allowed cannot be empty for a cpuset with attached tasks. */
	if (atomic_read(&cs->count) && nodes_empty(trialcs.mems_allowed)) {
		retval = -ENOSPC;
		goto done;
	}
	retval = validate_change(cs, &trialcs);
	if (retval < 0)
		goto done;

	mutex_lock(&callback_mutex);
	cs->mems_allowed = trialcs.mems_allowed;
	cs->mems_generation = cpuset_mems_generation++;
	mutex_unlock(&callback_mutex);

	set_cpuset_being_rebound(cs);		/* causes mpol_copy() rebind */

	fudge = 10;				/* spare mmarray[] slots */
	fudge += cpus_weight(cs->cpus_allowed);	/* imagine one fork-bomb/cpu */
	retval = -ENOMEM;

	/*
	 * Allocate mmarray[] to hold mm reference for each task
	 * in cpuset cs.  Can't kmalloc GFP_KERNEL while holding
	 * tasklist_lock.  We could use GFP_ATOMIC, but with a
	 * few more lines of code, we can retry until we get a big
	 * enough mmarray[] w/o using GFP_ATOMIC.
	 */
	while (1) {
		ntasks = atomic_read(&cs->count);	/* guess */
		ntasks += fudge;
		mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
		if (!mmarray)
			goto done;
		write_lock_irq(&tasklist_lock);		/* block fork */
		if (atomic_read(&cs->count) <= ntasks)
			break;				/* got enough */
		write_unlock_irq(&tasklist_lock);	/* try again */
		kfree(mmarray);
	}

	n = 0;

	/* Load up mmarray[] with mm reference for each task in cpuset. */
	do_each_thread(g, p) {
		struct mm_struct *mm;

		if (n >= ntasks) {
			printk(KERN_WARNING
				"Cpuset mempolicy rebind incomplete.\n");
			continue;
		}
		if (p->cpuset != cs)
			continue;
		mm = get_task_mm(p);
		if (!mm)
			continue;
		mmarray[n++] = mm;
	} while_each_thread(g, p);
	write_unlock_irq(&tasklist_lock);

	/*
	 * Now that we've dropped the tasklist spinlock, we can
	 * rebind the vma mempolicies of each mm in mmarray[] to their
	 * new cpuset, and release that mm.  The mpol_rebind_mm()
	 * call takes mmap_sem, which we couldn't take while holding
	 * tasklist_lock.  Forks can happen again now - the mpol_copy()
	 * cpuset_being_rebound check will catch such forks, and rebind
	 * their vma mempolicies too.  Because we still hold the global
	 * cpuset manage_mutex, we know that no other rebind effort will
	 * be contending for the global variable cpuset_being_rebound.
	 * It's ok if we rebind the same mm twice; mpol_rebind_mm()
	 * is idempotent.  Also migrate pages in each mm to new nodes.
	 */
	migrate = is_memory_migrate(cs);
	for (i = 0; i < n; i++) {
		struct mm_struct *mm = mmarray[i];

		mpol_rebind_mm(mm, &cs->mems_allowed);
		if (migrate)
			cpuset_migrate_mm(mm, &oldmem, &cs->mems_allowed);
		mmput(mm);
	}

	/* We're done rebinding vma's to this cpusets new mems_allowed. */
	kfree(mmarray);
	set_cpuset_being_rebound(NULL);
	retval = 0;
done:
	return retval;
}

/*
 * Call with manage_mutex held.
 */

static int update_memory_pressure_enabled(struct cpuset *cs, char *buf)
{
	if (simple_strtoul(buf, NULL, 10) != 0)
		cpuset_memory_pressure_enabled = 1;
	else
		cpuset_memory_pressure_enabled = 0;
	return 0;
}

/*
 * update_flag - read a 0 or a 1 in a file and update associated flag
 * bit:	the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
 *				CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE,
 *				CS_SPREAD_PAGE, CS_SPREAD_SLAB)
 * cs:	the cpuset to update
 * buf:	the buffer where we read the 0 or 1
 *
 * Call with manage_mutex held.
 */

static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
{
	int turning_on;
	struct cpuset trialcs;
	int err, cpu_exclusive_changed;

	turning_on = (simple_strtoul(buf, NULL, 10) != 0);

	trialcs = *cs;
	if (turning_on)
		set_bit(bit, &trialcs.flags);
	else
		clear_bit(bit, &trialcs.flags);

	err = validate_change(cs, &trialcs);
	if (err < 0)
		return err;
	cpu_exclusive_changed =
		(is_cpu_exclusive(cs) != is_cpu_exclusive(&trialcs));
	mutex_lock(&callback_mutex);
	cs->flags = trialcs.flags;
	mutex_unlock(&callback_mutex);

	if (cpu_exclusive_changed)
                update_cpu_domains(cs);
	return 0;
}

/*
 * Frequency meter - How fast is some event occurring?
 *
 * These routines manage a digitally filtered, constant time based,
 * event frequency meter.  There are four routines:
 *   fmeter_init() - initialize a frequency meter.
 *   fmeter_markevent() - called each time the event happens.
 *   fmeter_getrate() - returns the recent rate of such events.
 *   fmeter_update() - internal routine used to update fmeter.
 *
 * A common data structure is passed to each of these routines,
 * which is used to keep track of the state required to manage the
 * frequency meter and its digital filter.
 *
 * The filter works on the number of events marked per unit time.
 * The filter is single-pole low-pass recursive (IIR).  The time unit
 * is 1 second.  Arithmetic is done using 32-bit integers scaled to
 * simulate 3 decimal digits of precision (multiplied by 1000).
 *
 * With an FM_COEF of 933, and a time base of 1 second, the filter
 * has a half-life of 10 seconds, meaning that if the events quit
 * happening, then the rate returned from the fmeter_getrate()
 * will be cut in half each 10 seconds, until it converges to zero.
 *
 * It is not worth doing a real infinitely recursive filter.  If more
 * than FM_MAXTICKS ticks have elapsed since the last filter event,
 * just compute FM_MAXTICKS ticks worth, by which point the level
 * will be stable.
 *
 * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid
 * arithmetic overflow in the fmeter_update() routine.
 *
 * Given the simple 32 bit integer arithmetic used, this meter works
 * best for reporting rates between one per millisecond (msec) and
 * one per 32 (approx) seconds.  At constant rates faster than one
 * per msec it maxes out at values just under 1,000,000.  At constant
 * rates between one per msec, and one per second it will stabilize
 * to a value N*1000, where N is the rate of events per second.
 * At constant rates between one per second and one per 32 seconds,
 * it will be choppy, moving up on the seconds that have an event,
 * and then decaying until the next event.  At rates slower than
 * about one in 32 seconds, it decays all the way back to zero between
 * each event.
 */

#define FM_COEF 933		/* coefficient for half-life of 10 secs */
#define FM_MAXTICKS ((time_t)99) /* useless computing more ticks than this */
#define FM_MAXCNT 1000000	/* limit cnt to avoid overflow */
#define FM_SCALE 1000		/* faux fixed point scale */

/* Initialize a frequency meter */
static void fmeter_init(struct fmeter *fmp)
{
	fmp->cnt = 0;
	fmp->val = 0;
	fmp->time = 0;
	spin_lock_init(&fmp->lock);
}

/* Internal meter update - process cnt events and update value */
static void fmeter_update(struct fmeter *fmp)
{
	time_t now = get_seconds();
	time_t ticks = now - fmp->time;

	if (ticks == 0)
		return;

	ticks = min(FM_MAXTICKS, ticks);
	while (ticks-- > 0)
		fmp->val = (FM_COEF * fmp->val) / FM_SCALE;
	fmp->time = now;

	fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE;
	fmp->cnt = 0;
}

/* Process any previous ticks, then bump cnt by one (times scale). */
static void fmeter_markevent(struct fmeter *fmp)
{
	spin_lock(&fmp->lock);
	fmeter_update(fmp);
	fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE);
	spin_unlock(&fmp->lock);
}

/* Process any previous ticks, then return current value. */
static int fmeter_getrate(struct fmeter *fmp)
{
	int val;

	spin_lock(&fmp->lock);
	fmeter_update(fmp);
	val = fmp->val;
	spin_unlock(&fmp->lock);
	return val;
}

/*
 * Attack task specified by pid in 'pidbuf' to cpuset 'cs', possibly
 * writing the path of the old cpuset in 'ppathbuf' if it needs to be
 * notified on release.
 *
 * Call holding manage_mutex.  May take callback_mutex and task_lock of
 * the task 'pid' during call.
 */

static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
{
	pid_t pid;
	struct task_struct *tsk;
	struct cpuset *oldcs;
	cpumask_t cpus;
	nodemask_t from, to;
	struct mm_struct *mm;
	int retval;

	if (sscanf(pidbuf, "%d", &pid) != 1)
		return -EIO;
	if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
		return -ENOSPC;

	if (pid) {
		read_lock(&tasklist_lock);

		tsk = find_task_by_pid(pid);
		if (!tsk || tsk->flags & PF_EXITING) {
			read_unlock(&tasklist_lock);
			return -ESRCH;
		}

		get_task_struct(tsk);
		read_unlock(&tasklist_lock);

		if ((current->euid) && (current->euid != tsk->uid)
		    && (current->euid != tsk->suid)) {
			put_task_struct(tsk);
			return -EACCES;
		}
	} else {
		tsk = current;
		get_task_struct(tsk);
	}

	retval = security_task_setscheduler(tsk, 0, NULL);
	if (retval) {
		put_task_struct(tsk);
		return retval;
	}

	mutex_lock(&callback_mutex);

	task_lock(tsk);
	oldcs = tsk->cpuset;
	/*
	 * After getting 'oldcs' cpuset ptr, be sure still not exiting.
	 * If 'oldcs' might be the top_cpuset due to the_top_cpuset_hack
	 * then fail this attach_task(), to avoid breaking top_cpuset.count.
	 */
	if (tsk->flags & PF_EXITING) {
		task_unlock(tsk);
		mutex_unlock(&callback_mutex);
		put_task_struct(tsk);
		return -ESRCH;
	}
	atomic_inc(&cs->count);
	rcu_assign_pointer(tsk->cpuset, cs);
	task_unlock(tsk);

	guarantee_online_cpus(cs, &cpus);
	set_cpus_allowed(tsk, cpus);

	from = oldcs->mems_allowed;
	to = cs->mems_allowed;

	mutex_unlock(&callback_mutex);

	mm = get_task_mm(tsk);
	if (mm) {
		mpol_rebind_mm(mm, &to);
		if (is_memory_migrate(cs))
			cpuset_migrate_mm(mm, &from, &to);
		mmput(mm);
	}

	put_task_struct(tsk);
	synchronize_rcu();
	if (atomic_dec_and_test(&oldcs->count))
		check_for_release(oldcs, ppathbuf);
	return 0;
}

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

typedef enum {
	FILE_ROOT,
	FILE_DIR,
	FILE_MEMORY_MIGRATE,
	FILE_CPULIST,
	FILE_MEMLIST,
	FILE_CPU_EXCLUSIVE,
	FILE_MEM_EXCLUSIVE,
	FILE_NOTIFY_ON_RELEASE,
	FILE_MEMORY_PRESSURE_ENABLED,
	FILE_MEMORY_PRESSURE,
	FILE_SPREAD_PAGE,
	FILE_SPREAD_SLAB,
	FILE_TASKLIST,
} cpuset_filetype_t;

static ssize_t cpuset_common_file_write(struct file *file,
					const char __user *userbuf,
					size_t nbytes, loff_t *unused_ppos)
{
	struct cpuset *cs = __d_cs(file->f_path.dentry->d_parent);
	struct cftype *cft = __d_cft(file->f_path.dentry);
	cpuset_filetype_t type = cft->private;
	char *buffer;
	char *pathbuf = NULL;
	int retval = 0;

	/* Crude upper limit on largest legitimate cpulist user might write. */
	if (nbytes > 100 + 6 * max(NR_CPUS, MAX_NUMNODES))
		return -E2BIG;

	/* +1 for nul-terminator */
	if ((buffer = kmalloc(nbytes + 1, GFP_KERNEL)) == 0)
		return -ENOMEM;

	if (copy_from_user(buffer, userbuf, nbytes)) {
		retval = -EFAULT;
		goto out1;
	}
	buffer[nbytes] = 0;	/* nul-terminate */

	mutex_lock(&manage_mutex);

	if (is_removed(cs)) {
		retval = -ENODEV;
		goto out2;
	}

	switch (type) {
	case FILE_CPULIST:
		retval = update_cpumask(cs, buffer);
		break;
	case FILE_MEMLIST:
		retval = update_nodemask(cs, buffer);