glock.c

linux 内核源代码

		}
	}

	if (gh->gh_flags & LM_FLAG_PRIORITY)
		list_add(&gh->gh_list, &gl->gl_waiters3);
	else
		list_add_tail(&gh->gh_list, &gl->gl_waiters3);
}

/**
 * gfs2_glock_nq - enqueue a struct gfs2_holder onto a glock (acquire a glock)
 * @gh: the holder structure
 *
 * if (gh->gh_flags & GL_ASYNC), this never returns an error
 *
 * Returns: 0, GLR_TRYFAILED, or errno on failure
 */

int gfs2_glock_nq(struct gfs2_holder *gh)
{
	struct gfs2_glock *gl = gh->gh_gl;
	struct gfs2_sbd *sdp = gl->gl_sbd;
	int error = 0;

restart:
	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
		set_bit(HIF_ABORTED, &gh->gh_iflags);
		return -EIO;
	}

	set_bit(HIF_PROMOTE, &gh->gh_iflags);

	spin_lock(&gl->gl_spin);
	add_to_queue(gh);
	run_queue(gl);
	spin_unlock(&gl->gl_spin);

	if (!(gh->gh_flags & GL_ASYNC)) {
		error = glock_wait_internal(gh);
		if (error == GLR_CANCELED) {
			msleep(100);
			goto restart;
		}
	}

	return error;
}

/**
 * gfs2_glock_poll - poll to see if an async request has been completed
 * @gh: the holder
 *
 * Returns: 1 if the request is ready to be gfs2_glock_wait()ed on
 */

int gfs2_glock_poll(struct gfs2_holder *gh)
{
	struct gfs2_glock *gl = gh->gh_gl;
	int ready = 0;

	spin_lock(&gl->gl_spin);

	if (test_bit(HIF_HOLDER, &gh->gh_iflags))
		ready = 1;
	else if (list_empty(&gh->gh_list)) {
		if (gh->gh_error == GLR_CANCELED) {
			spin_unlock(&gl->gl_spin);
			msleep(100);
			if (gfs2_glock_nq(gh))
				return 1;
			return 0;
		} else
			ready = 1;
	}

	spin_unlock(&gl->gl_spin);

	return ready;
}

/**
 * gfs2_glock_wait - wait for a lock acquisition that ended in a GLR_ASYNC
 * @gh: the holder structure
 *
 * Returns: 0, GLR_TRYFAILED, or errno on failure
 */

int gfs2_glock_wait(struct gfs2_holder *gh)
{
	int error;

	error = glock_wait_internal(gh);
	if (error == GLR_CANCELED) {
		msleep(100);
		gh->gh_flags &= ~GL_ASYNC;
		error = gfs2_glock_nq(gh);
	}

	return error;
}

/**
 * gfs2_glock_dq - dequeue a struct gfs2_holder from a glock (release a glock)
 * @gh: the glock holder
 *
 */

void gfs2_glock_dq(struct gfs2_holder *gh)
{
	struct gfs2_glock *gl = gh->gh_gl;
	const struct gfs2_glock_operations *glops = gl->gl_ops;
	unsigned delay = 0;

	if (gh->gh_flags & GL_NOCACHE)
		handle_callback(gl, LM_ST_UNLOCKED, 0, 0);

	gfs2_glmutex_lock(gl);

	spin_lock(&gl->gl_spin);
	list_del_init(&gh->gh_list);

	if (list_empty(&gl->gl_holders)) {
		spin_unlock(&gl->gl_spin);

		if (glops->go_unlock)
			glops->go_unlock(gh);

		spin_lock(&gl->gl_spin);
		gl->gl_stamp = jiffies;
	}

	clear_bit(GLF_LOCK, &gl->gl_flags);
	spin_unlock(&gl->gl_spin);

	gfs2_glock_hold(gl);
	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
	    !test_bit(GLF_DEMOTE, &gl->gl_flags))
		delay = gl->gl_ops->go_min_hold_time;
	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
		gfs2_glock_put(gl);
}

void gfs2_glock_dq_wait(struct gfs2_holder *gh)
{
	struct gfs2_glock *gl = gh->gh_gl;
	gfs2_glock_dq(gh);
	wait_on_demote(gl);
}

/**
 * gfs2_glock_dq_uninit - dequeue a holder from a glock and initialize it
 * @gh: the holder structure
 *
 */

void gfs2_glock_dq_uninit(struct gfs2_holder *gh)
{
	gfs2_glock_dq(gh);
	gfs2_holder_uninit(gh);
}

/**
 * gfs2_glock_nq_num - acquire a glock based on lock number
 * @sdp: the filesystem
 * @number: the lock number
 * @glops: the glock operations for the type of glock
 * @state: the state to acquire the glock in
 * @flags: modifier flags for the aquisition
 * @gh: the struct gfs2_holder
 *
 * Returns: errno
 */

int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
		      const struct gfs2_glock_operations *glops,
		      unsigned int state, int flags, struct gfs2_holder *gh)
{
	struct gfs2_glock *gl;
	int error;

	error = gfs2_glock_get(sdp, number, glops, CREATE, &gl);
	if (!error) {
		error = gfs2_glock_nq_init(gl, state, flags, gh);
		gfs2_glock_put(gl);
	}

	return error;
}

/**
 * glock_compare - Compare two struct gfs2_glock structures for sorting
 * @arg_a: the first structure
 * @arg_b: the second structure
 *
 */

static int glock_compare(const void *arg_a, const void *arg_b)
{
	const struct gfs2_holder *gh_a = *(const struct gfs2_holder **)arg_a;
	const struct gfs2_holder *gh_b = *(const struct gfs2_holder **)arg_b;
	const struct lm_lockname *a = &gh_a->gh_gl->gl_name;
	const struct lm_lockname *b = &gh_b->gh_gl->gl_name;

	if (a->ln_number > b->ln_number)
		return 1;
	if (a->ln_number < b->ln_number)
		return -1;
	BUG_ON(gh_a->gh_gl->gl_ops->go_type == gh_b->gh_gl->gl_ops->go_type);
	return 0;
}

/**
 * nq_m_sync - synchonously acquire more than one glock in deadlock free order
 * @num_gh: the number of structures
 * @ghs: an array of struct gfs2_holder structures
 *
 * Returns: 0 on success (all glocks acquired),
 *          errno on failure (no glocks acquired)
 */

static int nq_m_sync(unsigned int num_gh, struct gfs2_holder *ghs,
		     struct gfs2_holder **p)
{
	unsigned int x;
	int error = 0;

	for (x = 0; x < num_gh; x++)
		p[x] = &ghs[x];

	sort(p, num_gh, sizeof(struct gfs2_holder *), glock_compare, NULL);

	for (x = 0; x < num_gh; x++) {
		p[x]->gh_flags &= ~(LM_FLAG_TRY | GL_ASYNC);

		error = gfs2_glock_nq(p[x]);
		if (error) {
			while (x--)
				gfs2_glock_dq(p[x]);
			break;
		}
	}

	return error;
}

/**
 * gfs2_glock_nq_m - acquire multiple glocks
 * @num_gh: the number of structures
 * @ghs: an array of struct gfs2_holder structures
 *
 *
 * Returns: 0 on success (all glocks acquired),
 *          errno on failure (no glocks acquired)
 */

int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs)
{
	struct gfs2_holder *tmp[4];
	struct gfs2_holder **pph = tmp;
	int error = 0;

	switch(num_gh) {
	case 0:
		return 0;
	case 1:
		ghs->gh_flags &= ~(LM_FLAG_TRY | GL_ASYNC);
		return gfs2_glock_nq(ghs);
	default:
		if (num_gh <= 4)
			break;
		pph = kmalloc(num_gh * sizeof(struct gfs2_holder *), GFP_NOFS);
		if (!pph)
			return -ENOMEM;
	}

	error = nq_m_sync(num_gh, ghs, pph);

	if (pph != tmp)
		kfree(pph);

	return error;
}

/**
 * gfs2_glock_dq_m - release multiple glocks
 * @num_gh: the number of structures
 * @ghs: an array of struct gfs2_holder structures
 *
 */

void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs)
{
	unsigned int x;

	for (x = 0; x < num_gh; x++)
		gfs2_glock_dq(&ghs[x]);
}

/**
 * gfs2_glock_dq_uninit_m - release multiple glocks
 * @num_gh: the number of structures
 * @ghs: an array of struct gfs2_holder structures
 *
 */

void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs)
{
	unsigned int x;

	for (x = 0; x < num_gh; x++)
		gfs2_glock_dq_uninit(&ghs[x]);
}

/**
 * gfs2_lvb_hold - attach a LVB from a glock
 * @gl: The glock in question
 *
 */

int gfs2_lvb_hold(struct gfs2_glock *gl)
{
	int error;

	gfs2_glmutex_lock(gl);

	if (!atomic_read(&gl->gl_lvb_count)) {
		error = gfs2_lm_hold_lvb(gl->gl_sbd, gl->gl_lock, &gl->gl_lvb);
		if (error) {
			gfs2_glmutex_unlock(gl);
			return error;
		}
		gfs2_glock_hold(gl);
	}
	atomic_inc(&gl->gl_lvb_count);

	gfs2_glmutex_unlock(gl);

	return 0;
}

/**
 * gfs2_lvb_unhold - detach a LVB from a glock
 * @gl: The glock in question
 *
 */

void gfs2_lvb_unhold(struct gfs2_glock *gl)
{
	gfs2_glock_hold(gl);
	gfs2_glmutex_lock(gl);

	gfs2_assert(gl->gl_sbd, atomic_read(&gl->gl_lvb_count) > 0);
	if (atomic_dec_and_test(&gl->gl_lvb_count)) {
		gfs2_lm_unhold_lvb(gl->gl_sbd, gl->gl_lock, gl->gl_lvb);
		gl->gl_lvb = NULL;
		gfs2_glock_put(gl);
	}

	gfs2_glmutex_unlock(gl);
	gfs2_glock_put(gl);
}

static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name,
			unsigned int state)
{
	struct gfs2_glock *gl;
	unsigned long delay = 0;
	unsigned long holdtime;
	unsigned long now = jiffies;

	gl = gfs2_glock_find(sdp, name);
	if (!gl)
		return;

	holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
	if (time_before(now, holdtime))
		delay = holdtime - now;

	handle_callback(gl, state, 1, delay);
	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
		gfs2_glock_put(gl);
}

/**
 * gfs2_glock_cb - Callback used by locking module
 * @sdp: Pointer to the superblock
 * @type: Type of callback
 * @data: Type dependent data pointer
 *
 * Called by the locking module when it wants to tell us something.
 * Either we need to drop a lock, one of our ASYNC requests completed, or
 * a journal from another client needs to be recovered.
 */

void gfs2_glock_cb(void *cb_data, unsigned int type, void *data)
{
	struct gfs2_sbd *sdp = cb_data;

	switch (type) {
	case LM_CB_NEED_E:
		blocking_cb(sdp, data, LM_ST_UNLOCKED);
		return;

	case LM_CB_NEED_D:
		blocking_cb(sdp, data, LM_ST_DEFERRED);
		return;

	case LM_CB_NEED_S:
		blocking_cb(sdp, data, LM_ST_SHARED);
		return;

	case LM_CB_ASYNC: {
		struct lm_async_cb *async = data;
		struct gfs2_glock *gl;

		down_read(&gfs2_umount_flush_sem);
		gl = gfs2_glock_find(sdp, &async->lc_name);
		if (gfs2_assert_warn(sdp, gl))
			return;
		if (!gfs2_assert_warn(sdp, gl->gl_req_bh))
			gl->gl_req_bh(gl, async->lc_ret);
		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
			gfs2_glock_put(gl);
		up_read(&gfs2_umount_flush_sem);
		return;
	}

	case LM_CB_NEED_RECOVERY:
		gfs2_jdesc_make_dirty(sdp, *(unsigned int *)data);
		if (sdp->sd_recoverd_process)
			wake_up_process(sdp->sd_recoverd_process);
		return;

	case LM_CB_DROPLOCKS:
		gfs2_gl_hash_clear(sdp, NO_WAIT);
		gfs2_quota_scan(sdp);
		return;

	default:
		gfs2_assert_warn(sdp, 0);
		return;
	}
}

/**
 * demote_ok - Check to see if it's ok to unlock a glock
 * @gl: the glock
 *
 * Returns: 1 if it's ok
 */

static int demote_ok(struct gfs2_glock *gl)
{
	const struct gfs2_glock_operations *glops = gl->gl_ops;
	int demote = 1;

	if (test_bit(GLF_STICKY, &gl->gl_flags))
		demote = 0;
	else if (glops->go_demote_ok)
		demote = glops->go_demote_ok(gl);

	return demote;
}

/**
 * gfs2_glock_schedule_for_reclaim - Add a glock to the reclaim list
 * @gl: the glock
 *
 */

void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;

	spin_lock(&sdp->sd_reclaim_lock);
	if (list_empty(&gl->gl_reclaim)) {
		gfs2_glock_hold(gl);
		list_add(&gl->gl_reclaim, &sdp->sd_reclaim_list);
		atomic_inc(&sdp->sd_reclaim_count);
	}
	spin_unlock(&sdp->sd_reclaim_lock);

	wake_up(&sdp->sd_reclaim_wq);
}

/**
 * gfs2_reclaim_glock - process the next glock on the filesystem's reclaim list
 * @sdp: the filesystem
 *
 * Called from gfs2_glockd() glock reclaim daemon, or when promoting a
 * different glock and we notice that there are a lot of glocks in the
 * reclaim list.
 *
 */

void gfs2_reclaim_glock(struct gfs2_sbd *sdp)
{
	struct gfs2_glock *gl;

	spin_lock(&sdp->sd_reclaim_lock);
	if (list_empty(&sdp->sd_reclaim_list)) {
		spin_unlock(&sdp->sd_reclaim_lock);
		return;
	}
	gl = list_entry(sdp->sd_reclaim_list.next,
			struct gfs2_glock, gl_reclaim);
	list_del_init(&gl->gl_reclaim);
	spin_unlock(&sdp->sd_reclaim_lock);

	atomic_dec(&sdp->sd_reclaim_count);
	atomic_inc(&sdp->sd_reclaimed);

	if (gfs2_glmutex_trylock(gl)) {
		if (list_empty(&gl->gl_holders) &&
		    gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
			handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
		gfs2_glmutex_unlock(gl);
	}

	gfs2_glock_put(gl);
}

/**
 * examine_bucket - Call a function for glock in a hash bucket
 * @examiner: the function
 * @sdp: the filesystem
 * @bucket: the bucket
 *
 * Returns: 1 if the bucket has entries
 */

static int examine_bucket(glock_examiner examiner, struct gfs2_sbd *sdp,
			  unsigned int hash)
{
	struct gfs2_glock *gl, *prev = NULL;
	int has_entries = 0;
	struct hlist_head *head = &gl_hash_table[hash].hb_list;

	read_lock(gl_lock_addr(hash));
	/* Can't use hlist_for_each_entry - don't want prefetch here */
	if (hlist_empty(head))
		goto out;
	gl = list_entry(head->first, struct gfs2_glock, gl_list);
	while(1) {
		if (!sdp || gl->gl_sbd == sdp) {
			gfs2_glock_hold(gl);
			read_unlock(gl_lock_addr(hash));
			if (prev)
				gfs2_glock_put(prev);
			prev = gl;
			examiner(gl);
			has_entries = 1;
			read_lock(gl_lock_addr(hash));
		}
		if (gl->gl_list.next == NULL)
			break;
		gl = list_entry(gl->gl_list.next, struct gfs2_glock, gl_list);
	}
out:
	read_unlock(gl_lock_addr(hash));
	if (prev)
		gfs2_glock_put(prev);
	cond_resched();
	return has_entries;