Merge git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-fixes

* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-fixes:
  [GFS2] Revert remounting w/o acl option leaves acls enabled
  [GFS2] Fix setting of inherit jdata attr
  [GFS2] Fix incorrect error path in prepare_write()
  [GFS2] Fix incorrect return code in rgrp.c
  [GFS2] soft lockup in rgblk_search
  [GFS2] soft lockup detected in databuf_lo_before_commit
  [DLM] fix basts for granted PR waiting CW
  [DLM] More othercon fixes
  [DLM] Fix memory leak in dlm_add_member() when dlm_node_weight() returns less than zero
  [DLM] zero unused parts of sockaddr_storage
  [DLM] fix NULL ls usage
  [DLM] Clear othercon pointers when a connection is closed

9 files changed, 124 insertions, 59 deletions

diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index b455919..2082daf 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -1670,9 +1670,10 @@ static int can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now,
    with a deadlk here, we'd have to generate something like grant_lock with
    the deadlk error.) */
 
-/* returns the highest requested mode of all blocked conversions */
+/* Returns the highest requested mode of all blocked conversions; sets
+   cw if there's a blocked conversion to DLM_LOCK_CW. */
 
-static int grant_pending_convert(struct dlm_rsb *r, int high)
+static int grant_pending_convert(struct dlm_rsb *r, int high, int *cw)
 {
 	struct dlm_lkb *lkb, *s;
 	int hi, demoted, quit, grant_restart, demote_restart;
@@ -1709,6 +1710,9 @@ static int grant_pending_convert(struct dlm_rsb *r, int high)
 		}
 
 		hi = max_t(int, lkb->lkb_rqmode, hi);
+
+		if (cw && lkb->lkb_rqmode == DLM_LOCK_CW)
+			*cw = 1;
 	}
 
 	if (grant_restart)
@@ -1721,29 +1725,52 @@ static int grant_pending_convert(struct dlm_rsb *r, int high)
 	return max_t(int, high, hi);
 }
 
-static int grant_pending_wait(struct dlm_rsb *r, int high)
+static int grant_pending_wait(struct dlm_rsb *r, int high, int *cw)
 {
 	struct dlm_lkb *lkb, *s;
 
 	list_for_each_entry_safe(lkb, s, &r->res_waitqueue, lkb_statequeue) {
 		if (can_be_granted(r, lkb, 0, NULL))
 			grant_lock_pending(r, lkb);
-                else
+                else {
 			high = max_t(int, lkb->lkb_rqmode, high);
+			if (lkb->lkb_rqmode == DLM_LOCK_CW)
+				*cw = 1;
+		}
 	}
 
 	return high;
 }
 
+/* cw of 1 means there's a lock with a rqmode of DLM_LOCK_CW that's blocked
+   on either the convert or waiting queue.
+   high is the largest rqmode of all locks blocked on the convert or
+   waiting queue. */
+
+static int lock_requires_bast(struct dlm_lkb *gr, int high, int cw)
+{
+	if (gr->lkb_grmode == DLM_LOCK_PR && cw) {
+		if (gr->lkb_highbast < DLM_LOCK_EX)
+			return 1;
+		return 0;
+	}
+
+	if (gr->lkb_highbast < high &&
+	    !__dlm_compat_matrix[gr->lkb_grmode+1][high+1])
+		return 1;
+	return 0;
+}
+
 static void grant_pending_locks(struct dlm_rsb *r)
 {
 	struct dlm_lkb *lkb, *s;
 	int high = DLM_LOCK_IV;
+	int cw = 0;
 
 	DLM_ASSERT(is_master(r), dlm_dump_rsb(r););
 
-	high = grant_pending_convert(r, high);
-	high = grant_pending_wait(r, high);
+	high = grant_pending_convert(r, high, &cw);
+	high = grant_pending_wait(r, high, &cw);
 
 	if (high == DLM_LOCK_IV)
 		return;
@@ -1751,27 +1778,41 @@ static void grant_pending_locks(struct dlm_rsb *r)
 	/*
 	 * If there are locks left on the wait/convert queue then send blocking
 	 * ASTs to granted locks based on the largest requested mode (high)
-	 * found above. FIXME: highbast < high comparison not valid for PR/CW.
+	 * found above.
 	 */
 
 	list_for_each_entry_safe(lkb, s, &r->res_grantqueue, lkb_statequeue) {
-		if (lkb->lkb_bastaddr && (lkb->lkb_highbast < high) &&
-		    !__dlm_compat_matrix[lkb->lkb_grmode+1][high+1]) {
-			queue_bast(r, lkb, high);
+		if (lkb->lkb_bastaddr && lock_requires_bast(lkb, high, cw)) {
+			if (cw && high == DLM_LOCK_PR)
+				queue_bast(r, lkb, DLM_LOCK_CW);
+			else
+				queue_bast(r, lkb, high);
 			lkb->lkb_highbast = high;
 		}
 	}
 }
 
+static int modes_require_bast(struct dlm_lkb *gr, struct dlm_lkb *rq)
+{
+	if ((gr->lkb_grmode == DLM_LOCK_PR && rq->lkb_rqmode == DLM_LOCK_CW) ||
+	    (gr->lkb_grmode == DLM_LOCK_CW && rq->lkb_rqmode == DLM_LOCK_PR)) {
+		if (gr->lkb_highbast < DLM_LOCK_EX)
+			return 1;
+		return 0;
+	}
+
+	if (gr->lkb_highbast < rq->lkb_rqmode && !modes_compat(gr, rq))
+		return 1;
+	return 0;
+}
+
 static void send_bast_queue(struct dlm_rsb *r, struct list_head *head,
 			    struct dlm_lkb *lkb)
 {
 	struct dlm_lkb *gr;
 
 	list_for_each_entry(gr, head, lkb_statequeue) {
-		if (gr->lkb_bastaddr &&
-		    gr->lkb_highbast < lkb->lkb_rqmode &&
-		    !modes_compat(gr, lkb)) {
+		if (gr->lkb_bastaddr && modes_require_bast(gr, lkb)) {
 			queue_bast(r, gr, lkb->lkb_rqmode);
 			gr->lkb_highbast = lkb->lkb_rqmode;
 		}
@@ -2235,7 +2276,7 @@ static int do_convert(struct dlm_rsb *r, struct dlm_lkb *lkb)
 	   before we try again to grant this one. */
 
 	if (is_demoted(lkb)) {
-		grant_pending_convert(r, DLM_LOCK_IV);
+		grant_pending_convert(r, DLM_LOCK_IV, NULL);
 		if (_can_be_granted(r, lkb, 1)) {
 			grant_lock(r, lkb);
 			queue_cast(r, lkb, 0);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index dd36273..9e9d2e8 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -313,6 +313,7 @@ static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port,
 		in6_addr->sin6_port = cpu_to_be16(port);
 		*addr_len = sizeof(struct sockaddr_in6);
 	}
+	memset((char *)saddr + *addr_len, 0, sizeof(struct sockaddr_storage) - *addr_len);
 }
 
 /* Close a remote connection and tidy up */
@@ -332,8 +333,19 @@ static void close_connection(struct connection *con, bool and_other)
 		__free_page(con->rx_page);
 		con->rx_page = NULL;
 	}
-	con->retries = 0;
-	mutex_unlock(&con->sock_mutex);
+
+	/* If we are an 'othercon' then NULL the pointer to us
+	   from the parent and tidy ourself up */
+	if (test_bit(CF_IS_OTHERCON, &con->flags)) {
+		struct connection *parent = __nodeid2con(con->nodeid, 0);
+		parent->othercon = NULL;
+		kmem_cache_free(con_cache, con);
+	}
+	else {
+		/* Parent connections get reused */
+		con->retries = 0;
+		mutex_unlock(&con->sock_mutex);
+	}
 }
 
 /* We only send shutdown messages to nodes that are not part of the cluster */
@@ -631,7 +643,7 @@ out_resched:
 
 out_close:
 	mutex_unlock(&con->sock_mutex);
-	if (ret != -EAGAIN && !test_bit(CF_IS_OTHERCON, &con->flags)) {
+	if (ret != -EAGAIN) {
 		close_connection(con, false);
 		/* Reconnect when there is something to send */
 	}
@@ -1122,8 +1134,6 @@ static int tcp_listen_for_all(void)
 
 	log_print("Using TCP for communications");
 
-	set_bit(CF_IS_OTHERCON, &con->flags);
-
 	sock = tcp_create_listen_sock(con, dlm_local_addr[0]);
 	if (sock) {
 		add_sock(sock, con);
@@ -1407,7 +1417,7 @@ void dlm_lowcomms_stop(void)
 	for (i = 0; i <= max_nodeid; i++) {
 		con = __nodeid2con(i, 0);
 		if (con) {
-			con->flags |= 0xFF;
+			con->flags |= 0x0F;
 			if (con->sock)
 				con->sock->sk->sk_user_data = NULL;
 		}
@@ -1423,8 +1433,6 @@ void dlm_lowcomms_stop(void)
 		con = __nodeid2con(i, 0);
 		if (con) {
 			close_connection(con, true);
-			if (con->othercon)
-				kmem_cache_free(con_cache, con->othercon);
 			kmem_cache_free(con_cache, con);
 		}
 	}
diff --git a/fs/dlm/member.c b/fs/dlm/member.c
index 073599d..d099775 100644
--- a/fs/dlm/member.c
+++ b/fs/dlm/member.c
@@ -56,8 +56,10 @@ static int dlm_add_member(struct dlm_ls *ls, int nodeid)
 		return -ENOMEM;
 
 	w = dlm_node_weight(ls->ls_name, nodeid);
-	if (w < 0)
+	if (w < 0) {
+		kfree(memb);
 		return w;
+	}
 
 	memb->nodeid = nodeid;
 	memb->weight = w;
diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c
index e3a1527..188b91c 100644
--- a/fs/dlm/rcom.c
+++ b/fs/dlm/rcom.c
@@ -386,8 +386,7 @@ static void receive_rcom_lock_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
 	dlm_recover_process_copy(ls, rc_in);
 }
 
-static int send_ls_not_ready(struct dlm_ls *ls, int nodeid,
-			     struct dlm_rcom *rc_in)
+static int send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in)
 {
 	struct dlm_rcom *rc;
 	struct rcom_config *rf;
@@ -395,7 +394,7 @@ static int send_ls_not_ready(struct dlm_ls *ls, int nodeid,
 	char *mb;
 	int mb_len = sizeof(struct dlm_rcom) + sizeof(struct rcom_config);
 
-	mh = dlm_lowcomms_get_buffer(nodeid, mb_len, ls->ls_allocation, &mb);
+	mh = dlm_lowcomms_get_buffer(nodeid, mb_len, GFP_NOFS, &mb);
 	if (!mh)
 		return -ENOBUFS;
 	memset(mb, 0, mb_len);
@@ -465,7 +464,7 @@ void dlm_receive_rcom(struct dlm_header *hd, int nodeid)
 		log_print("lockspace %x from %d type %x not found",
 			  hd->h_lockspace, nodeid, rc->rc_type);
 		if (rc->rc_type == DLM_RCOM_STATUS)
-			send_ls_not_ready(ls, nodeid, rc);
+			send_ls_not_ready(nodeid, rc);
 		return;
 	}
 
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index aff70f0..3b395c4 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -486,8 +486,8 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 		gfs2_pin(sdp, bd->bd_bh);
 		tr->tr_num_databuf_new++;
 	}
-	sdp->sd_log_num_databuf++;
 	gfs2_log_lock(sdp);
+	sdp->sd_log_num_databuf++;
 	list_add(&le->le_list, &sdp->sd_log_le_databuf);
 	gfs2_log_unlock(sdp);
 }
@@ -523,7 +523,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
 	struct buffer_head *bh = NULL,*bh1 = NULL;
 	struct gfs2_log_descriptor *ld;
 	unsigned int limit;
-	unsigned int total_dbuf = sdp->sd_log_num_databuf;
+	unsigned int total_dbuf;
 	unsigned int total_jdata = sdp->sd_log_num_jdata;
 	unsigned int num, n;
 	__be64 *ptr = NULL;
@@ -535,6 +535,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
 	 * into the log along with a header
 	 */
 	gfs2_log_lock(sdp);
+	total_dbuf = sdp->sd_log_num_databuf;
 	bd2 = bd1 = list_prepare_entry(bd1, &sdp->sd_log_le_databuf,
 				       bd_le.le_list);
 	while(total_dbuf) {
@@ -653,6 +654,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
 				break;
 		}
 		bh = NULL;
+		BUG_ON(total_dbuf < num);
 		total_dbuf -= num;
 		total_jdata -= num;
 	}
diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c
index 6f006a8..4864659 100644
--- a/fs/gfs2/mount.c
+++ b/fs/gfs2/mount.c
@@ -82,19 +82,20 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
 	char *options, *o, *v;
 	int error = 0;
 
-	/*  If someone preloaded options, use those instead  */
-	spin_lock(&gfs2_sys_margs_lock);
-	if (!remount && gfs2_sys_margs) {
-		data = gfs2_sys_margs;
-		gfs2_sys_margs = NULL;
-	}
-	spin_unlock(&gfs2_sys_margs_lock);
+	if (!remount) {
+		/*  If someone preloaded options, use those instead  */
+		spin_lock(&gfs2_sys_margs_lock);
+		if (gfs2_sys_margs) {
+			data = gfs2_sys_margs;
+			gfs2_sys_margs = NULL;
+		}
+		spin_unlock(&gfs2_sys_margs_lock);
 
-	/*  Set some defaults  */
-	memset(args, 0, sizeof(struct gfs2_args));
-	args->ar_num_glockd = GFS2_GLOCKD_DEFAULT;
-	args->ar_quota = GFS2_QUOTA_DEFAULT;
-	args->ar_data = GFS2_DATA_DEFAULT;
+		/*  Set some defaults  */
+		args->ar_num_glockd = GFS2_GLOCKD_DEFAULT;
+		args->ar_quota = GFS2_QUOTA_DEFAULT;
+		args->ar_data = GFS2_DATA_DEFAULT;
+	}
 
 	/* Split the options into tokens with the "," character and
 	   process them */
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index ce90032..42a5f58 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -416,7 +416,7 @@ static int gfs2_prepare_write(struct file *file, struct page *page,
 
 	error = gfs2_trans_begin(sdp, rblocks, 0);
 	if (error)
-		goto out;
+		goto out_trans_fail;
 
 	if (gfs2_is_stuffed(ip)) {
 		if (end > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
@@ -434,6 +434,7 @@ prepare_write:
 out:
 	if (error) {
 		gfs2_trans_end(sdp);
+out_trans_fail:
 		if (alloc_required) {
 			gfs2_inplace_release(ip);
 out_qunlock:
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index 7734211..94d76ac 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -177,8 +177,8 @@ static const u32 fsflags_to_gfs2[32] = {
 	[5] = GFS2_DIF_APPENDONLY,
 	[7] = GFS2_DIF_NOATIME,
 	[12] = GFS2_DIF_EXHASH,
-	[14] = GFS2_DIF_JDATA,
-	[20] = GFS2_DIF_DIRECTIO,
+	[14] = GFS2_DIF_INHERIT_JDATA,
+	[20] = GFS2_DIF_INHERIT_DIRECTIO,
 };
 
 static const u32 gfs2_to_fsflags[32] = {
@@ -187,8 +187,6 @@ static const u32 gfs2_to_fsflags[32] = {
 	[gfs2fl_AppendOnly] = FS_APPEND_FL,
 	[gfs2fl_NoAtime] = FS_NOATIME_FL,
 	[gfs2fl_ExHash] = FS_INDEX_FL,
-	[gfs2fl_Jdata] = FS_JOURNAL_DATA_FL,
-	[gfs2fl_Directio] = FS_DIRECTIO_FL,
 	[gfs2fl_InheritDirectio] = FS_DIRECTIO_FL,
 	[gfs2fl_InheritJdata] = FS_JOURNAL_DATA_FL,
 };
@@ -207,6 +205,12 @@ static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
 		return error;
 
 	fsflags = fsflags_cvt(gfs2_to_fsflags, ip->i_di.di_flags);
+	if (!S_ISDIR(inode->i_mode)) {
+		if (ip->i_di.di_flags & GFS2_DIF_JDATA)
+			fsflags |= FS_JOURNAL_DATA_FL;
+		if (ip->i_di.di_flags & GFS2_DIF_DIRECTIO)
+			fsflags |= FS_DIRECTIO_FL;
+	}
 	if (put_user(fsflags, ptr))
 		error = -EFAULT;
 
@@ -270,13 +274,6 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
 	if ((new_flags ^ flags) == 0)
 		goto out;
 
-	if (S_ISDIR(inode->i_mode)) {
-		if ((new_flags ^ flags) & GFS2_DIF_JDATA)
-			new_flags ^= (GFS2_DIF_JDATA|GFS2_DIF_INHERIT_JDATA);
-		if ((new_flags ^ flags) & GFS2_DIF_DIRECTIO)
-			new_flags ^= (GFS2_DIF_DIRECTIO|GFS2_DIF_INHERIT_DIRECTIO);
-	}
-
 	error = -EINVAL;
 	if ((new_flags ^ flags) & ~GFS2_FLAGS_USER_SET)
 		goto out;
@@ -315,11 +312,19 @@ out:
 
 static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
 {
+	struct inode *inode = filp->f_path.dentry->d_inode;
 	u32 fsflags, gfsflags;
 	if (get_user(fsflags, ptr))
 		return -EFAULT;
 	gfsflags = fsflags_cvt(fsflags_to_gfs2, fsflags);
-	return do_gfs2_set_flags(filp, gfsflags, ~0);
+	if (!S_ISDIR(inode->i_mode)) {
+		if (gfsflags & GFS2_DIF_INHERIT_JDATA)
+			gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA);
+		if (gfsflags & GFS2_DIF_INHERIT_DIRECTIO)
+			gfsflags ^= (GFS2_DIF_DIRECTIO | GFS2_DIF_INHERIT_DIRECTIO);
+		return do_gfs2_set_flags(filp, gfsflags, ~0);
+	}
+	return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_JDATA);
 }
 
 static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index e4e0406..ce48c45 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -863,16 +863,19 @@ static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked)
 	u64 no_addr;
 
 	for(;;) {
+		if (goal >= rgd->rd_data)
+			break;
 		goal = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
 				    GFS2_BLKST_UNLINKED);
-		if (goal == 0)
-			return 0;
+		if (goal == BFITNOENT)
+			break;
 		no_addr = goal + rgd->rd_data0;
-		if (no_addr <= *last_unlinked)
+		goal++;
+		if (no_addr < *last_unlinked)
 			continue;
 		*last_unlinked = no_addr;
 		inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN,
-					no_addr, -1);
+					  no_addr, -1);
 		if (!IS_ERR(inode))
 			return inode;
 	}
@@ -1313,7 +1316,7 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
 				    bi->bi_len, blk, new_state);
 	}
 
-	return (blk == BFITNOENT) ? 0 : (bi->bi_start * GFS2_NBBY) + blk;
+	return (blk == BFITNOENT) ? blk : (bi->bi_start * GFS2_NBBY) + blk;
 }
 
 /**
@@ -1393,6 +1396,7 @@ u64 gfs2_alloc_data(struct gfs2_inode *ip)
 		goal = rgd->rd_last_alloc_data;
 
 	blk = rgblk_search(rgd, goal, GFS2_BLKST_FREE, GFS2_BLKST_USED);
+	BUG_ON(blk == BFITNOENT);
 	rgd->rd_last_alloc_data = blk;
 
 	block = rgd->rd_data0 + blk;
@@ -1437,6 +1441,7 @@ u64 gfs2_alloc_meta(struct gfs2_inode *ip)
 		goal = rgd->rd_last_alloc_meta;
 
 	blk = rgblk_search(rgd, goal, GFS2_BLKST_FREE, GFS2_BLKST_USED);
+	BUG_ON(blk == BFITNOENT);
 	rgd->rd_last_alloc_meta = blk;
 
 	block = rgd->rd_data0 + blk;
@@ -1478,6 +1483,7 @@ u64 gfs2_alloc_di(struct gfs2_inode *dip, u64 *generation)
 
 	blk = rgblk_search(rgd, rgd->rd_last_alloc_meta,
 			   GFS2_BLKST_FREE, GFS2_BLKST_DINODE);
+	BUG_ON(blk == BFITNOENT);
 
 	rgd->rd_last_alloc_meta = blk;