dlm: add rsb lists for iteration

To prepare for using rhashtable, add two rsb lists for iterating
through rsb's in two uncommon cases where this is necesssary:
- when dumping rsb state from debugfs, now using seq_list.
- when looking at all rsb's during recovery.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>

6 files changed, 84 insertions, 261 deletions

diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index 37f4dfca5e44..70567919f1b7 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -366,12 +366,10 @@ static void print_format4(struct dlm_rsb *r, struct seq_file *s)
 	unlock_rsb(r);
 }
 
-struct rsbtbl_iter {
-	struct dlm_rsb *rsb;
-	unsigned bucket;
-	int format;
-	int header;
-};
+static const struct seq_operations format1_seq_ops;
+static const struct seq_operations format2_seq_ops;
+static const struct seq_operations format3_seq_ops;
+static const struct seq_operations format4_seq_ops;
 
 /*
  * If the buffer is full, seq_printf can be called again, but it
@@ -382,220 +380,61 @@ struct rsbtbl_iter {
 
 static int table_seq_show(struct seq_file *seq, void *iter_ptr)
 {
-	struct rsbtbl_iter *ri = iter_ptr;
-
-	switch (ri->format) {
-	case 1:
-		print_format1(ri->rsb, seq);
-		break;
-	case 2:
-		if (ri->header) {
-			seq_puts(seq, "id nodeid remid pid xid exflags flags sts grmode rqmode time_ms r_nodeid r_len r_name\n");
-			ri->header = 0;
-		}
-		print_format2(ri->rsb, seq);
-		break;
-	case 3:
-		if (ri->header) {
-			seq_puts(seq, "rsb ptr nodeid first_lkid flags !root_list_empty !recover_list_empty recover_locks_count len\n");
-			ri->header = 0;
-		}
-		print_format3(ri->rsb, seq);
-		break;
-	case 4:
-		if (ri->header) {
-			seq_puts(seq, "rsb ptr nodeid master_nodeid dir_nodeid our_nodeid toss_time flags len str|hex name\n");
-			ri->header = 0;
-		}
-		print_format4(ri->rsb, seq);
-		break;
-	}
+	struct dlm_rsb *rsb = list_entry(iter_ptr, struct dlm_rsb, res_rsbs_list);
+
+	if (seq->op == &format1_seq_ops)
+		print_format1(rsb, seq);
+	else if (seq->op == &format2_seq_ops)
+		print_format2(rsb, seq);
+	else if (seq->op == &format3_seq_ops)
+		print_format3(rsb, seq);
+	else if (seq->op == &format4_seq_ops)
+		print_format4(rsb, seq);
 
 	return 0;
 }
 
-static const struct seq_operations format1_seq_ops;
-static const struct seq_operations format2_seq_ops;
-static const struct seq_operations format3_seq_ops;
-static const struct seq_operations format4_seq_ops;
-
 static void *table_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	struct rb_root *tree;
-	struct rb_node *node;
 	struct dlm_ls *ls = seq->private;
-	struct rsbtbl_iter *ri;
-	struct dlm_rsb *r;
-	loff_t n = *pos;
-	unsigned bucket, entry;
-	int toss = (seq->op == &format4_seq_ops);
-
-	bucket = n >> 32;
-	entry = n & ((1LL << 32) - 1);
-
-	if (bucket >= ls->ls_rsbtbl_size)
-		return NULL;
-
-	ri = kzalloc(sizeof(*ri), GFP_NOFS);
-	if (!ri)
-		return NULL;
-	if (n == 0)
-		ri->header = 1;
-	if (seq->op == &format1_seq_ops)
-		ri->format = 1;
-	if (seq->op == &format2_seq_ops)
-		ri->format = 2;
-	if (seq->op == &format3_seq_ops)
-		ri->format = 3;
-	if (seq->op == &format4_seq_ops)
-		ri->format = 4;
-
-	tree = &ls->ls_rsbtbl[bucket].r;
+	struct list_head *list;
 
-	spin_lock_bh(&ls->ls_rsbtbl_lock);
-	if (!RB_EMPTY_ROOT(tree)) {
-		for (node = rb_first(tree); node; node = rb_next(node)) {
-			r = rb_entry(node, struct dlm_rsb, res_hashnode);
-			if (toss) {
-				if (!rsb_flag(r, RSB_TOSS))
-					continue;
-			} else {
-				if (rsb_flag(r, RSB_TOSS))
-					continue;
-			}
-
-			if (!entry--) {
-				dlm_hold_rsb(r);
-				ri->rsb = r;
-				ri->bucket = bucket;
-				spin_unlock_bh(&ls->ls_rsbtbl_lock);
-				return ri;
-			}
-		}
+	if (!*pos) {
+		if (seq->op == &format2_seq_ops)
+			seq_puts(seq, "id nodeid remid pid xid exflags flags sts grmode rqmode time_ms r_nodeid r_len r_name\n");
+		else if (seq->op == &format3_seq_ops)
+			seq_puts(seq, "rsb ptr nodeid first_lkid flags !root_list_empty !recover_list_empty recover_locks_count len\n");
+		else if (seq->op == &format4_seq_ops)
+			seq_puts(seq, "rsb ptr nodeid master_nodeid dir_nodeid our_nodeid toss_time flags len str|hex name\n");
 	}
-	spin_unlock_bh(&ls->ls_rsbtbl_lock);
-
-	/*
-	 * move to the first rsb in the next non-empty bucket
-	 */
-
-	/* zero the entry */
-	n &= ~((1LL << 32) - 1);
 
-	while (1) {
-		bucket++;
-		n += 1LL << 32;
+	if (seq->op == &format4_seq_ops)
+		list = &ls->ls_toss;
+	else
+		list = &ls->ls_keep;
 
-		if (bucket >= ls->ls_rsbtbl_size) {
-			kfree(ri);
-			return NULL;
-		}
-		tree = &ls->ls_rsbtbl[bucket].r;
-
-		spin_lock_bh(&ls->ls_rsbtbl_lock);
-		if (!RB_EMPTY_ROOT(tree)) {
-			node = rb_first(tree);
-			r = rb_entry(node, struct dlm_rsb, res_hashnode);
-			if (toss) {
-				if (!rsb_flag(r, RSB_TOSS))
-					continue;
-			} else {
-				if (rsb_flag(r, RSB_TOSS))
-					continue;
-			}
-
-			dlm_hold_rsb(r);
-			ri->rsb = r;
-			ri->bucket = bucket;
-			spin_unlock_bh(&ls->ls_rsbtbl_lock);
-			*pos = n;
-			return ri;
-		}
-		spin_unlock_bh(&ls->ls_rsbtbl_lock);
-	}
+	spin_lock_bh(&ls->ls_rsbtbl_lock);
+	return seq_list_start(list, *pos);
 }
 
 static void *table_seq_next(struct seq_file *seq, void *iter_ptr, loff_t *pos)
 {
 	struct dlm_ls *ls = seq->private;
-	struct rsbtbl_iter *ri = iter_ptr;
-	struct rb_root *tree;
-	struct rb_node *next;
-	struct dlm_rsb *r, *rp;
-	loff_t n = *pos;
-	unsigned bucket;
-	int toss = (seq->op == &format4_seq_ops);
-
-	bucket = n >> 32;
-
-	/*
-	 * move to the next rsb in the same bucket
-	 */
-
-	spin_lock_bh(&ls->ls_rsbtbl_lock);
-	rp = ri->rsb;
-	next = rb_next(&rp->res_hashnode);
-
-	if (next) {
-		r = rb_entry(next, struct dlm_rsb, res_hashnode);
-		dlm_hold_rsb(r);
-		ri->rsb = r;
-		spin_unlock_bh(&ls->ls_rsbtbl_lock);
-		dlm_put_rsb(rp);
-		++*pos;
-		return ri;
-	}
-	spin_unlock_bh(&ls->ls_rsbtbl_lock);
-	dlm_put_rsb(rp);
-
-	/*
-	 * move to the first rsb in the next non-empty bucket
-	 */
+	struct list_head *list;
 
-	/* zero the entry */
-	n &= ~((1LL << 32) - 1);
-
-	while (1) {
-		bucket++;
-		n += 1LL << 32;
+	if (seq->op == &format4_seq_ops)
+		list = &ls->ls_toss;
+	else
+		list = &ls->ls_keep;
 
-		if (bucket >= ls->ls_rsbtbl_size) {
-			kfree(ri);
-			++*pos;
-			return NULL;
-		}
-		tree = &ls->ls_rsbtbl[bucket].r;
-
-		spin_lock_bh(&ls->ls_rsbtbl_lock);
-		if (!RB_EMPTY_ROOT(tree)) {
-			next = rb_first(tree);
-			r = rb_entry(next, struct dlm_rsb, res_hashnode);
-			if (toss) {
-				if (!rsb_flag(r, RSB_TOSS))
-					continue;
-			} else {
-				if (rsb_flag(r, RSB_TOSS))
-					continue;
-			}
-			dlm_hold_rsb(r);
-			ri->rsb = r;
-			ri->bucket = bucket;
-			spin_unlock_bh(&ls->ls_rsbtbl_lock);
-			*pos = n;
-			return ri;
-		}
-		spin_unlock_bh(&ls->ls_rsbtbl_lock);
-	}
+	return seq_list_next(iter_ptr, list, pos);
 }
 
 static void table_seq_stop(struct seq_file *seq, void *iter_ptr)
 {
-	struct rsbtbl_iter *ri = iter_ptr;
+	struct dlm_ls *ls = seq->private;
 
-	if (ri) {
-		dlm_put_rsb(ri->rsb);
-		kfree(ri);
-	}
+	spin_unlock_bh(&ls->ls_rsbtbl_lock);
 }
 
 static const struct seq_operations format1_seq_ops = {
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index af88fc2f978c..6d06840029c3 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -339,6 +339,7 @@ struct dlm_rsb {
 	struct list_head	res_convertqueue;
 	struct list_head	res_waitqueue;
 
+	struct list_head	res_rsbs_list;
 	struct list_head	res_root_list;	    /* used for recovery */
 	struct list_head	res_masters_list;   /* used for recovery */
 	struct list_head	res_recover_list;   /* used for recovery */
@@ -595,6 +596,9 @@ struct dlm_ls {
 	spinlock_t		ls_rsbtbl_lock;
 	uint32_t		ls_rsbtbl_size;
 
+	struct list_head	ls_toss;
+	struct list_head	ls_keep;
+
 	spinlock_t		ls_waiters_lock;
 	struct list_head	ls_waiters;	/* lkbs needing a reply */
 
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 08ec1a04476a..a70b8edb5d3f 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -668,6 +668,7 @@ static int find_rsb_dir(struct dlm_ls *ls, const void *name, int len,
 		r->res_first_lkid = 0;
 	}
 
+	list_move(&r->res_rsbs_list, &ls->ls_keep);
 	rsb_clear_flag(r, RSB_TOSS);
 	goto out_unlock;
 
@@ -730,6 +731,8 @@ static int find_rsb_dir(struct dlm_ls *ls, const void *name, int len,
 
  out_add:
 	error = rsb_insert(r, &ls->ls_rsbtbl[b].r);
+	if (!error)
+		list_add(&r->res_rsbs_list, &ls->ls_keep);
  out_unlock:
 	spin_unlock_bh(&ls->ls_rsbtbl_lock);
  out:
@@ -801,6 +804,7 @@ static int find_rsb_nodir(struct dlm_ls *ls, const void *name, int len,
 		r->res_nodeid = 0;
 	}
 
+	list_move(&r->res_rsbs_list, &ls->ls_keep);
 	rsb_clear_flag(r, RSB_TOSS);
 	goto out_unlock;
 
@@ -826,6 +830,8 @@ static int find_rsb_nodir(struct dlm_ls *ls, const void *name, int len,
 	kref_init(&r->res_ref);
 
 	error = rsb_insert(r, &ls->ls_rsbtbl[b].r);
+	if (!error)
+		list_add(&r->res_rsbs_list, &ls->ls_keep);
  out_unlock:
 	spin_unlock_bh(&ls->ls_rsbtbl_lock);
  out:
@@ -1110,6 +1116,8 @@ int dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, const char *name,
 		goto retry;
 	}
 
+	list_add(&r->res_rsbs_list, &ls->ls_toss);
+
 	if (result)
 		*result = DLM_LU_ADD;
 	*r_nodeid = from_nodeid;
@@ -1120,20 +1128,12 @@ int dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, const char *name,
 
 static void dlm_dump_rsb_hash(struct dlm_ls *ls, uint32_t hash)
 {
-	struct rb_node *n;
 	struct dlm_rsb *r;
-	int i;
 
 	spin_lock_bh(&ls->ls_rsbtbl_lock);
-	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
-		for (n = rb_first(&ls->ls_rsbtbl[i].r); n; n = rb_next(n)) {
-			r = rb_entry(n, struct dlm_rsb, res_hashnode);
-			if (rsb_flag(r, RSB_TOSS))
-				continue;
-
-			if (r->res_hash == hash)
-				dlm_dump_rsb(r);
-		}
+	list_for_each_entry(r, &ls->ls_keep, res_rsbs_list) {
+		if (r->res_hash == hash)
+			dlm_dump_rsb(r);
 	}
 	spin_unlock_bh(&ls->ls_rsbtbl_lock);
 }
@@ -1166,6 +1166,7 @@ static void toss_rsb(struct kref *kref)
 	kref_init(&r->res_ref);
 	WARN_ON(rsb_flag(r, RSB_TOSS));
 	rsb_set_flag(r, RSB_TOSS);
+	list_move(&r->res_rsbs_list, &ls->ls_toss);
 	r->res_toss_time = jiffies;
 	set_bit(DLM_RTF_SHRINK_BIT, &ls->ls_rsbtbl[r->res_bucket].flags);
 	if (r->res_lvbptr) {
@@ -1672,6 +1673,7 @@ static void shrink_bucket(struct dlm_ls *ls, int b)
 			continue;
 		}
 
+		list_del(&r->res_rsbs_list);
 		rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[b].r);
 		dlm_free_rsb(r);
 	}
@@ -1740,6 +1742,7 @@ static void shrink_bucket(struct dlm_ls *ls, int b)
 			continue;
 		}
 
+		list_del(&r->res_rsbs_list);
 		rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[b].r);
 		send_remove(r);
 		spin_unlock_bh(&ls->ls_rsbtbl_lock);
@@ -4243,6 +4246,7 @@ static void receive_remove(struct dlm_ls *ls, const struct dlm_message *ms)
 	}
 
 	if (kref_put(&r->res_ref, kill_rsb)) {
+		list_del(&r->res_rsbs_list);
 		rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[b].r);
 		spin_unlock_bh(&ls->ls_rsbtbl_lock);
 		dlm_free_rsb(r);
@@ -5313,17 +5317,12 @@ void dlm_recover_purge(struct dlm_ls *ls, const struct list_head *root_list)
 			  lkb_count, nodes_count);
 }
 
-static struct dlm_rsb *find_grant_rsb(struct dlm_ls *ls, int bucket)
+static struct dlm_rsb *find_grant_rsb(struct dlm_ls *ls)
 {
-	struct rb_node *n;
 	struct dlm_rsb *r;
 
 	spin_lock_bh(&ls->ls_rsbtbl_lock);
-	for (n = rb_first(&ls->ls_rsbtbl[bucket].r); n; n = rb_next(n)) {
-		r = rb_entry(n, struct dlm_rsb, res_hashnode);
-		if (rsb_flag(r, RSB_TOSS))
-			continue;
-
+	list_for_each_entry(r, &ls->ls_keep, res_rsbs_list) {
 		if (!rsb_flag(r, RSB_RECOVER_GRANT))
 			continue;
 		if (!is_master(r)) {
@@ -5358,19 +5357,15 @@ static struct dlm_rsb *find_grant_rsb(struct dlm_ls *ls, int bucket)
 void dlm_recover_grant(struct dlm_ls *ls)
 {
 	struct dlm_rsb *r;
-	int bucket = 0;
 	unsigned int count = 0;
 	unsigned int rsb_count = 0;
 	unsigned int lkb_count = 0;
 
 	while (1) {
-		r = find_grant_rsb(ls, bucket);
-		if (!r) {
-			if (bucket == ls->ls_rsbtbl_size - 1)
-				break;
-			bucket++;
-			continue;
-		}
+		r = find_grant_rsb(ls);
+		if (!r)
+			break;
+
 		rsb_count++;
 		count = 0;
 		lock_rsb(r);
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index b5184ad550fa..2b5771a7bf31 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -495,6 +495,8 @@ static int new_lockspace(const char *name, const char *cluster,
 	 */
 	ls->ls_exflags = (flags & ~(DLM_LSFL_FS | DLM_LSFL_NEWEXCL));
 
+	INIT_LIST_HEAD(&ls->ls_toss);
+	INIT_LIST_HEAD(&ls->ls_keep);
 	spin_lock_init(&ls->ls_rsbtbl_lock);
 	size = READ_ONCE(dlm_config.ci_rsbtbl_size);
 	ls->ls_rsbtbl_size = size;
@@ -838,6 +840,7 @@ static int release_lockspace(struct dlm_ls *ls, int force)
 	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
 		while ((n = rb_first(&ls->ls_rsbtbl[i].r))) {
 			rsb = rb_entry(n, struct dlm_rsb, res_hashnode);
+			list_del(&rsb->res_rsbs_list);
 			rb_erase(n, &ls->ls_rsbtbl[i].r);
 			dlm_free_rsb(rsb);
 		}
diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c
index e53d88e4ec93..512c1ae81a96 100644
--- a/fs/dlm/recover.c
+++ b/fs/dlm/recover.c
@@ -881,23 +881,15 @@ void dlm_recover_rsbs(struct dlm_ls *ls, const struct list_head *root_list)
 
 void dlm_clear_toss(struct dlm_ls *ls)
 {
-	struct rb_node *n, *next;
-	struct dlm_rsb *r;
+	struct dlm_rsb *r, *safe;
 	unsigned int count = 0;
-	int i;
-
-	spin_lock(&ls->ls_rsbtbl_lock);
-	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
-		for (n = rb_first(&ls->ls_rsbtbl[i].r); n; n = next) {
-			next = rb_next(n);
-			r = rb_entry(n, struct dlm_rsb, res_hashnode);
-			if (!rsb_flag(r, RSB_TOSS))
-				continue;
-
-			rb_erase(n, &ls->ls_rsbtbl[i].r);
-			dlm_free_rsb(r);
-			count++;
-		}
+
+	spin_lock_bh(&ls->ls_rsbtbl_lock);
+	list_for_each_entry_safe(r, safe, &ls->ls_toss, res_rsbs_list) {
+		list_del(&r->res_rsbs_list);
+		rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[r->res_bucket].r);
+		dlm_free_rsb(r);
+		count++;
 	}
 	spin_unlock_bh(&ls->ls_rsbtbl_lock);
 
diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c
index ad696528ebe7..5e8e10030b74 100644
--- a/fs/dlm/recoverd.c
+++ b/fs/dlm/recoverd.c
@@ -22,9 +22,8 @@
 
 static int dlm_create_masters_list(struct dlm_ls *ls)
 {
-	struct rb_node *n;
 	struct dlm_rsb *r;
-	int i, error = 0;
+	int error = 0;
 
 	write_lock_bh(&ls->ls_masters_lock);
 	if (!list_empty(&ls->ls_masters_list)) {
@@ -34,15 +33,12 @@ static int dlm_create_masters_list(struct dlm_ls *ls)
 	}
 
 	spin_lock_bh(&ls->ls_rsbtbl_lock);
-	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
-		for (n = rb_first(&ls->ls_rsbtbl[i].r); n; n = rb_next(n)) {
-			r = rb_entry(n, struct dlm_rsb, res_hashnode);
-			if (rsb_flag(r, RSB_TOSS) || r->res_nodeid)
-				continue;
-
-			list_add(&r->res_masters_list, &ls->ls_masters_list);
-			dlm_hold_rsb(r);
-		}
+	list_for_each_entry(r, &ls->ls_keep, res_rsbs_list) {
+		if (r->res_nodeid)
+			continue;
+
+		list_add(&r->res_masters_list, &ls->ls_masters_list);
+		dlm_hold_rsb(r);
 	}
 	spin_unlock_bh(&ls->ls_rsbtbl_lock);
  out:
@@ -64,21 +60,15 @@ static void dlm_release_masters_list(struct dlm_ls *ls)
 
 static void dlm_create_root_list(struct dlm_ls *ls, struct list_head *root_list)
 {
-	struct rb_node *n;
 	struct dlm_rsb *r;
-	int i;
 
 	spin_lock_bh(&ls->ls_rsbtbl_lock);
-	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
-		for (n = rb_first(&ls->ls_rsbtbl[i].r); n; n = rb_next(n)) {
-			r = rb_entry(n, struct dlm_rsb, res_hashnode);
-			if (WARN_ON_ONCE(rsb_flag(r, RSB_TOSS)))
-				continue;
-
-			list_add(&r->res_root_list, root_list);
-			dlm_hold_rsb(r);
-		}
+	list_for_each_entry(r, &ls->ls_keep, res_rsbs_list) {
+		list_add(&r->res_root_list, root_list);
+		dlm_hold_rsb(r);
 	}
+
+	WARN_ON_ONCE(!list_empty(&ls->ls_toss));
 	spin_unlock_bh(&ls->ls_rsbtbl_lock);
 }