Merge branch 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2

* 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2:
  O2net: Disallow o2net accept connection request from itself.
  ocfs2/dlm: remove potential deadlock -V3
  ocfs2/dlm: avoid incorrect bit set in refmap on recovery master
  Fix the nested PR lock calling issue in ACL
  ocfs2: Count more refcount records in file system fragmentation.
  ocfs2 fix o2dlm dlm run purgelist (rev 3)
  ocfs2/dlm: fix a dead lock
  ocfs2: do not overwrite error codes in ocfs2_init_acl

6 files changed, 122 insertions, 93 deletions

diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index da70229..a76e0aa 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -290,12 +290,30 @@ static int ocfs2_set_acl(handle_t *handle,
 
 int ocfs2_check_acl(struct inode *inode, int mask)
 {
-	struct posix_acl *acl = ocfs2_get_acl(inode, ACL_TYPE_ACCESS);
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct buffer_head *di_bh = NULL;
+	struct posix_acl *acl;
+	int ret = -EAGAIN;
 
-	if (IS_ERR(acl))
+	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+		return ret;
+
+	ret = ocfs2_read_inode_block(inode, &di_bh);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, di_bh);
+
+	brelse(di_bh);
+
+	if (IS_ERR(acl)) {
+		mlog_errno(PTR_ERR(acl));
 		return PTR_ERR(acl);
+	}
 	if (acl) {
-		int ret = posix_acl_permission(inode, acl, mask);
+		ret = posix_acl_permission(inode, acl, mask);
 		posix_acl_release(acl);
 		return ret;
 	}
@@ -344,7 +362,7 @@ int ocfs2_init_acl(handle_t *handle,
 {
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct posix_acl *acl = NULL;
-	int ret = 0;
+	int ret = 0, ret2;
 	mode_t mode;
 
 	if (!S_ISLNK(inode->i_mode)) {
@@ -381,7 +399,12 @@ int ocfs2_init_acl(handle_t *handle,
 		mode = inode->i_mode;
 		ret = posix_acl_create_masq(clone, &mode);
 		if (ret >= 0) {
-			ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
+			ret2 = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
+			if (ret2) {
+				mlog_errno(ret2);
+				ret = ret2;
+				goto cleanup;
+			}
 			if (ret > 0) {
 				ret = ocfs2_set_acl(handle, inode,
 						    di_bh, ACL_TYPE_ACCESS,
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index aa75ca3..1361997 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1759,6 +1759,7 @@ static int o2net_accept_one(struct socket *sock)
 	struct sockaddr_in sin;
 	struct socket *new_sock = NULL;
 	struct o2nm_node *node = NULL;
+	struct o2nm_node *local_node = NULL;
 	struct o2net_sock_container *sc = NULL;
 	struct o2net_node *nn;
 
@@ -1796,11 +1797,15 @@ static int o2net_accept_one(struct socket *sock)
 		goto out;
 	}
 
-	if (o2nm_this_node() > node->nd_num) {
-		mlog(ML_NOTICE, "unexpected connect attempted from a lower "
-		     "numbered node '%s' at " "%pI4:%d with num %u\n",
-		     node->nd_name, &sin.sin_addr.s_addr,
-		     ntohs(sin.sin_port), node->nd_num);
+	if (o2nm_this_node() >= node->nd_num) {
+		local_node = o2nm_get_node_by_num(o2nm_this_node());
+		mlog(ML_NOTICE, "unexpected connect attempt seen at node '%s' ("
+		     "%u, %pI4:%d) from node '%s' (%u, %pI4:%d)\n",
+		     local_node->nd_name, local_node->nd_num,
+		     &(local_node->nd_ipv4_address),
+		     ntohs(local_node->nd_ipv4_port),
+		     node->nd_name, node->nd_num, &sin.sin_addr.s_addr,
+		     ntohs(sin.sin_port));
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1857,6 +1862,8 @@ out:
 		sock_release(new_sock);
 	if (node)
 		o2nm_node_put(node);
+	if (local_node)
+		o2nm_node_put(local_node);
 	if (sc)
 		sc_put(sc);
 	return ret;
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 94b97fc..ffb4c68 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -511,8 +511,6 @@ static void dlm_lockres_release(struct kref *kref)
 
 	atomic_dec(&dlm->res_cur_count);
 
-	dlm_put(dlm);
-
 	if (!hlist_unhashed(&res->hash_node) ||
 	    !list_empty(&res->granted) ||
 	    !list_empty(&res->converting) ||
@@ -585,8 +583,6 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm,
 	res->migration_pending = 0;
 	res->inflight_locks = 0;
 
-	/* put in dlm_lockres_release */
-	dlm_grab(dlm);
 	res->dlm = dlm;
 
 	kref_init(&res->refs);
@@ -3050,8 +3046,6 @@ int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data,
 	/* check for pre-existing lock */
 	spin_lock(&dlm->spinlock);
 	res = __dlm_lookup_lockres(dlm, name, namelen, hash);
-	spin_lock(&dlm->master_lock);
-
 	if (res) {
 		spin_lock(&res->spinlock);
 		if (res->state & DLM_LOCK_RES_RECOVERING) {
@@ -3069,14 +3063,15 @@ int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data,
 		spin_unlock(&res->spinlock);
 	}
 
+	spin_lock(&dlm->master_lock);
 	/* ignore status.  only nonzero status would BUG. */
 	ret = dlm_add_migration_mle(dlm, res, mle, &oldmle,
 				    name, namelen,
 				    migrate->new_master,
 				    migrate->master);
 
-unlock:
 	spin_unlock(&dlm->master_lock);
+unlock:
 	spin_unlock(&dlm->spinlock);
 
 	if (oldmle) {
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 9dfaac7..aaaffbc 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1997,6 +1997,8 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm,
 	struct list_head *queue;
 	struct dlm_lock *lock, *next;
 
+	assert_spin_locked(&dlm->spinlock);
+	assert_spin_locked(&res->spinlock);
 	res->state |= DLM_LOCK_RES_RECOVERING;
 	if (!list_empty(&res->recovering)) {
 		mlog(0,
@@ -2326,19 +2328,15 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 			/* zero the lvb if necessary */
 			dlm_revalidate_lvb(dlm, res, dead_node);
 			if (res->owner == dead_node) {
-				if (res->state & DLM_LOCK_RES_DROPPING_REF)
-					mlog(0, "%s:%.*s: owned by "
-					     "dead node %u, this node was "
-					     "dropping its ref when it died. "
-					     "continue, dropping the flag.\n",
-					     dlm->name, res->lockname.len,
-					     res->lockname.name, dead_node);
-
-				/* the wake_up for this will happen when the
-				 * RECOVERING flag is dropped later */
-				res->state &= ~DLM_LOCK_RES_DROPPING_REF;
+				if (res->state & DLM_LOCK_RES_DROPPING_REF) {
+					mlog(ML_NOTICE, "Ignore %.*s for "
+					     "recovery as it is being freed\n",
+					     res->lockname.len,
+					     res->lockname.name);
+				} else
+					dlm_move_lockres_to_recovery_list(dlm,
+									  res);
 
-				dlm_move_lockres_to_recovery_list(dlm, res);
 			} else if (res->owner == dlm->node_num) {
 				dlm_free_dead_locks(dlm, res, dead_node);
 				__dlm_lockres_calc_usage(dlm, res);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index d4f73ca..2211acf 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -92,19 +92,27 @@ int __dlm_lockres_has_locks(struct dlm_lock_resource *res)
  * truly ready to be freed. */
 int __dlm_lockres_unused(struct dlm_lock_resource *res)
 {
-	if (!__dlm_lockres_has_locks(res) &&
-	    (list_empty(&res->dirty) && !(res->state & DLM_LOCK_RES_DIRTY))) {
-		/* try not to scan the bitmap unless the first two
-		 * conditions are already true */
-		int bit = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
-		if (bit >= O2NM_MAX_NODES) {
-			/* since the bit for dlm->node_num is not
-			 * set, inflight_locks better be zero */
-			BUG_ON(res->inflight_locks != 0);
-			return 1;
-		}
-	}
-	return 0;
+	int bit;
+
+	if (__dlm_lockres_has_locks(res))
+		return 0;
+
+	if (!list_empty(&res->dirty) || res->state & DLM_LOCK_RES_DIRTY)
+		return 0;
+
+	if (res->state & DLM_LOCK_RES_RECOVERING)
+		return 0;
+
+	bit = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
+	if (bit < O2NM_MAX_NODES)
+		return 0;
+
+	/*
+	 * since the bit for dlm->node_num is not set, inflight_locks better
+	 * be zero
+	 */
+	BUG_ON(res->inflight_locks != 0);
+	return 1;
 }
 
 
@@ -152,45 +160,25 @@ void dlm_lockres_calc_usage(struct dlm_ctxt *dlm,
 	spin_unlock(&dlm->spinlock);
 }
 
-static int dlm_purge_lockres(struct dlm_ctxt *dlm,
+static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 			     struct dlm_lock_resource *res)
 {
 	int master;
 	int ret = 0;
 
-	spin_lock(&res->spinlock);
-	if (!__dlm_lockres_unused(res)) {
-		mlog(0, "%s:%.*s: tried to purge but not unused\n",
-		     dlm->name, res->lockname.len, res->lockname.name);
-		__dlm_print_one_lock_resource(res);
-		spin_unlock(&res->spinlock);
-		BUG();
-	}
-
-	if (res->state & DLM_LOCK_RES_MIGRATING) {
-		mlog(0, "%s:%.*s: Delay dropref as this lockres is "
-		     "being remastered\n", dlm->name, res->lockname.len,
-		     res->lockname.name);
-		/* Re-add the lockres to the end of the purge list */
-		if (!list_empty(&res->purge)) {
-			list_del_init(&res->purge);
-			list_add_tail(&res->purge, &dlm->purge_list);
-		}
-		spin_unlock(&res->spinlock);
-		return 0;
-	}
+	assert_spin_locked(&dlm->spinlock);
+	assert_spin_locked(&res->spinlock);
 
 	master = (res->owner == dlm->node_num);
 
-	if (!master)
-		res->state |= DLM_LOCK_RES_DROPPING_REF;
-	spin_unlock(&res->spinlock);
 
 	mlog(0, "purging lockres %.*s, master = %d\n", res->lockname.len,
 	     res->lockname.name, master);
 
 	if (!master) {
+		res->state |= DLM_LOCK_RES_DROPPING_REF;
 		/* drop spinlock...  retake below */
+		spin_unlock(&res->spinlock);
 		spin_unlock(&dlm->spinlock);
 
 		spin_lock(&res->spinlock);
@@ -208,31 +196,35 @@ static int dlm_purge_lockres(struct dlm_ctxt *dlm,
 		mlog(0, "%s:%.*s: dlm_deref_lockres returned %d\n",
 		     dlm->name, res->lockname.len, res->lockname.name, ret);
 		spin_lock(&dlm->spinlock);
+		spin_lock(&res->spinlock);
 	}
 
-	spin_lock(&res->spinlock);
 	if (!list_empty(&res->purge)) {
 		mlog(0, "removing lockres %.*s:%p from purgelist, "
 		     "master = %d\n", res->lockname.len, res->lockname.name,
 		     res, master);
 		list_del_init(&res->purge);
-		spin_unlock(&res->spinlock);
 		dlm_lockres_put(res);
 		dlm->purge_count--;
-	} else
-		spin_unlock(&res->spinlock);
+	}
+
+	if (!__dlm_lockres_unused(res)) {
+		mlog(ML_ERROR, "found lockres %s:%.*s: in use after deref\n",
+		     dlm->name, res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+		BUG();
+	}
 
 	__dlm_unhash_lockres(res);
 
 	/* lockres is not in the hash now.  drop the flag and wake up
 	 * any processes waiting in dlm_get_lock_resource. */
 	if (!master) {
-		spin_lock(&res->spinlock);
 		res->state &= ~DLM_LOCK_RES_DROPPING_REF;
 		spin_unlock(&res->spinlock);
 		wake_up(&res->wq);
-	}
-	return 0;
+	} else
+		spin_unlock(&res->spinlock);
 }
 
 static void dlm_run_purge_list(struct dlm_ctxt *dlm,
@@ -251,17 +243,7 @@ static void dlm_run_purge_list(struct dlm_ctxt *dlm,
 		lockres = list_entry(dlm->purge_list.next,
 				     struct dlm_lock_resource, purge);
 
-		/* Status of the lockres *might* change so double
-		 * check. If the lockres is unused, holding the dlm
-		 * spinlock will prevent people from getting and more
-		 * refs on it -- there's no need to keep the lockres
-		 * spinlock. */
 		spin_lock(&lockres->spinlock);
-		unused = __dlm_lockres_unused(lockres);
-		spin_unlock(&lockres->spinlock);
-
-		if (!unused)
-			continue;
 
 		purge_jiffies = lockres->last_used +
 			msecs_to_jiffies(DLM_PURGE_INTERVAL_MS);
@@ -273,15 +255,29 @@ static void dlm_run_purge_list(struct dlm_ctxt *dlm,
 			 * in tail order, we can stop at the first
 			 * unpurgable resource -- anyone added after
 			 * him will have a greater last_used value */
+			spin_unlock(&lockres->spinlock);
 			break;
 		}
 
+		/* Status of the lockres *might* change so double
+		 * check. If the lockres is unused, holding the dlm
+		 * spinlock will prevent people from getting and more
+		 * refs on it. */
+		unused = __dlm_lockres_unused(lockres);
+		if (!unused ||
+		    (lockres->state & DLM_LOCK_RES_MIGRATING)) {
+			mlog(0, "lockres %s:%.*s: is in use or "
+			     "being remastered, used %d, state %d\n",
+			     dlm->name, lockres->lockname.len,
+			     lockres->lockname.name, !unused, lockres->state);
+			list_move_tail(&dlm->purge_list, &lockres->purge);
+			spin_unlock(&lockres->spinlock);
+			continue;
+		}
+
 		dlm_lockres_get(lockres);
 
-		/* This may drop and reacquire the dlm spinlock if it
-		 * has to do migration. */
-		if (dlm_purge_lockres(dlm, lockres))
-			BUG();
+		dlm_purge_lockres(dlm, lockres);
 
 		dlm_lockres_put(lockres);
 
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 3ac5aa7..73a11cc 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2436,16 +2436,26 @@ static int ocfs2_calc_refcount_meta_credits(struct super_block *sb,
 		len = min((u64)cpos + clusters, le64_to_cpu(rec.r_cpos) +
 			  le32_to_cpu(rec.r_clusters)) - cpos;
 		/*
-		 * If the refcount rec already exist, cool. We just need
-		 * to check whether there is a split. Otherwise we just need
-		 * to increase the refcount.
-		 * If we will insert one, increases recs_add.
-		 *
 		 * We record all the records which will be inserted to the
 		 * same refcount block, so that we can tell exactly whether
 		 * we need a new refcount block or not.
+		 *
+		 * If we will insert a new one, this is easy and only happens
+		 * during adding refcounted flag to the extent, so we don't
+		 * have a chance of spliting. We just need one record.
+		 *
+		 * If the refcount rec already exists, that would be a little
+		 * complicated. we may have to:
+		 * 1) split at the beginning if the start pos isn't aligned.
+		 *    we need 1 more record in this case.
+		 * 2) split int the end if the end pos isn't aligned.
+		 *    we need 1 more record in this case.
+		 * 3) split in the middle because of file system fragmentation.
+		 *    we need 2 more records in this case(we can't detect this
+		 *    beforehand, so always think of the worst case).
 		 */
 		if (rec.r_refcount) {
+			recs_add += 2;
 			/* Check whether we need a split at the beginning. */
 			if (cpos == start_cpos &&
 			    cpos != le64_to_cpu(rec.r_cpos))