Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (159 commits)
  tools/testing/selftests/proc/proc-self-syscall.c: remove duplicate include
  proc: more robust bulk read test
  proc: test /proc/*/maps, smaps, smaps_rollup, statm
  proc: use seq_puts() everywhere
  proc: read kernel cpu stat pointer once
  proc: remove unused argument in proc_pid_lookup()
  fs/proc/thread_self.c: code cleanup for proc_setup_thread_self()
  fs/proc/self.c: code cleanup for proc_setup_self()
  proc: return exit code 4 for skipped tests
  mm,mremap: bail out earlier in mremap_to under map pressure
  mm/sparse: fix a bad comparison
  mm/memory.c: do_fault: avoid usage of stale vm_area_struct
  writeback: fix inode cgroup switching comment
  mm/huge_memory.c: fix "orig_pud" set but not used
  mm/hotplug: fix an imbalance with DEBUG_PAGEALLOC
  mm/memcontrol.c: fix bad line in comment
  mm/cma.c: cma_declare_contiguous: correct err handling
  mm/page_ext.c: fix an imbalance with kmemleak
  mm/compaction: pass pgdat to too_many_isolated() instead of zone
  mm: remove zone_lru_lock() function, access ->lru_lock directly
  ...

7 files changed, 116 insertions, 75 deletions

diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index d1cbb27808e2..6f0999015a44 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7532,10 +7532,11 @@ static int ocfs2_trim_group(struct super_block *sb,
 	return count;
 }
 
-int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
+static
+int ocfs2_trim_mainbm(struct super_block *sb, struct fstrim_range *range)
 {
 	struct ocfs2_super *osb = OCFS2_SB(sb);
-	u64 start, len, trimmed, first_group, last_group, group;
+	u64 start, len, trimmed = 0, first_group, last_group = 0, group = 0;
 	int ret, cnt;
 	u32 first_bit, last_bit, minlen;
 	struct buffer_head *main_bm_bh = NULL;
@@ -7543,7 +7544,6 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	struct buffer_head *gd_bh = NULL;
 	struct ocfs2_dinode *main_bm;
 	struct ocfs2_group_desc *gd = NULL;
-	struct ocfs2_trim_fs_info info, *pinfo = NULL;
 
 	start = range->start >> osb->s_clustersize_bits;
 	len = range->len >> osb->s_clustersize_bits;
@@ -7552,6 +7552,9 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	if (minlen >= osb->bitmap_cpg || range->len < sb->s_blocksize)
 		return -EINVAL;
 
+	trace_ocfs2_trim_mainbm(start, len, minlen);
+
+next_group:
 	main_bm_inode = ocfs2_get_system_file_inode(osb,
 						    GLOBAL_BITMAP_SYSTEM_INODE,
 						    OCFS2_INVALID_SLOT);
@@ -7570,64 +7573,34 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	}
 	main_bm = (struct ocfs2_dinode *)main_bm_bh->b_data;
 
-	if (start >= le32_to_cpu(main_bm->i_clusters)) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
-	len = range->len >> osb->s_clustersize_bits;
-	if (start + len > le32_to_cpu(main_bm->i_clusters))
-		len = le32_to_cpu(main_bm->i_clusters) - start;
-
-	trace_ocfs2_trim_fs(start, len, minlen);
-
-	ocfs2_trim_fs_lock_res_init(osb);
-	ret = ocfs2_trim_fs_lock(osb, NULL, 1);
-	if (ret < 0) {
-		if (ret != -EAGAIN) {
-			mlog_errno(ret);
-			ocfs2_trim_fs_lock_res_uninit(osb);
+	/*
+	 * Do some check before trim the first group.
+	 */
+	if (!group) {
+		if (start >= le32_to_cpu(main_bm->i_clusters)) {
+			ret = -EINVAL;
 			goto out_unlock;
 		}
 
-		mlog(ML_NOTICE, "Wait for trim on device (%s) to "
-		     "finish, which is running from another node.\n",
-		     osb->dev_str);
-		ret = ocfs2_trim_fs_lock(osb, &info, 0);
-		if (ret < 0) {
-			mlog_errno(ret);
-			ocfs2_trim_fs_lock_res_uninit(osb);
-			goto out_unlock;
-		}
+		if (start + len > le32_to_cpu(main_bm->i_clusters))
+			len = le32_to_cpu(main_bm->i_clusters) - start;
 
-		if (info.tf_valid && info.tf_success &&
-		    info.tf_start == start && info.tf_len == len &&
-		    info.tf_minlen == minlen) {
-			/* Avoid sending duplicated trim to a shared device */
-			mlog(ML_NOTICE, "The same trim on device (%s) was "
-			     "just done from node (%u), return.\n",
-			     osb->dev_str, info.tf_nodenum);
-			range->len = info.tf_trimlen;
-			goto out_trimunlock;
-		}
+		/*
+		 * Determine first and last group to examine based on
+		 * start and len
+		 */
+		first_group = ocfs2_which_cluster_group(main_bm_inode, start);
+		if (first_group == osb->first_cluster_group_blkno)
+			first_bit = start;
+		else
+			first_bit = start - ocfs2_blocks_to_clusters(sb,
+								first_group);
+		last_group = ocfs2_which_cluster_group(main_bm_inode,
+						       start + len - 1);
+		group = first_group;
 	}
 
-	info.tf_nodenum = osb->node_num;
-	info.tf_start = start;
-	info.tf_len = len;
-	info.tf_minlen = minlen;
-
-	/* Determine first and last group to examine based on start and len */
-	first_group = ocfs2_which_cluster_group(main_bm_inode, start);
-	if (first_group == osb->first_cluster_group_blkno)
-		first_bit = start;
-	else
-		first_bit = start - ocfs2_blocks_to_clusters(sb, first_group);
-	last_group = ocfs2_which_cluster_group(main_bm_inode, start + len - 1);
-	last_bit = osb->bitmap_cpg;
-
-	trimmed = 0;
-	for (group = first_group; group <= last_group;) {
+	do {
 		if (first_bit + len >= osb->bitmap_cpg)
 			last_bit = osb->bitmap_cpg;
 		else
@@ -7659,21 +7632,81 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
 			group = ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg);
 		else
 			group += ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg);
-	}
-	range->len = trimmed * sb->s_blocksize;
+	} while (0);
 
-	info.tf_trimlen = range->len;
-	info.tf_success = (ret ? 0 : 1);
-	pinfo = &info;
-out_trimunlock:
-	ocfs2_trim_fs_unlock(osb, pinfo);
-	ocfs2_trim_fs_lock_res_uninit(osb);
 out_unlock:
 	ocfs2_inode_unlock(main_bm_inode, 0);
 	brelse(main_bm_bh);
+	main_bm_bh = NULL;
 out_mutex:
 	inode_unlock(main_bm_inode);
 	iput(main_bm_inode);
+
+	/*
+	 * If all the groups trim are not done or failed, but we should release
+	 * main_bm related locks for avoiding the current IO starve, then go to
+	 * trim the next group
+	 */
+	if (ret >= 0 && group <= last_group)
+		goto next_group;
 out:
+	range->len = trimmed * sb->s_blocksize;
+	return ret;
+}
+
+int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
+{
+	int ret;
+	struct ocfs2_super *osb = OCFS2_SB(sb);
+	struct ocfs2_trim_fs_info info, *pinfo = NULL;
+
+	ocfs2_trim_fs_lock_res_init(osb);
+
+	trace_ocfs2_trim_fs(range->start, range->len, range->minlen);
+
+	ret = ocfs2_trim_fs_lock(osb, NULL, 1);
+	if (ret < 0) {
+		if (ret != -EAGAIN) {
+			mlog_errno(ret);
+			ocfs2_trim_fs_lock_res_uninit(osb);
+			return ret;
+		}
+
+		mlog(ML_NOTICE, "Wait for trim on device (%s) to "
+		     "finish, which is running from another node.\n",
+		     osb->dev_str);
+		ret = ocfs2_trim_fs_lock(osb, &info, 0);
+		if (ret < 0) {
+			mlog_errno(ret);
+			ocfs2_trim_fs_lock_res_uninit(osb);
+			return ret;
+		}
+
+		if (info.tf_valid && info.tf_success &&
+		    info.tf_start == range->start &&
+		    info.tf_len == range->len &&
+		    info.tf_minlen == range->minlen) {
+			/* Avoid sending duplicated trim to a shared device */
+			mlog(ML_NOTICE, "The same trim on device (%s) was "
+			     "just done from node (%u), return.\n",
+			     osb->dev_str, info.tf_nodenum);
+			range->len = info.tf_trimlen;
+			goto out;
+		}
+	}
+
+	info.tf_nodenum = osb->node_num;
+	info.tf_start = range->start;
+	info.tf_len = range->len;
+	info.tf_minlen = range->minlen;
+
+	ret = ocfs2_trim_mainbm(sb, range);
+
+	info.tf_trimlen = range->len;
+	info.tf_success = (ret < 0 ? 0 : 1);
+	pinfo = &info;
+out:
+	ocfs2_trim_fs_unlock(osb, pinfo);
+	ocfs2_trim_fs_lock_res_uninit(osb);
 	return ret;
 }
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index 0e4166cc23a0..4ac775e32240 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -621,13 +621,15 @@ static void o2nm_node_group_drop_item(struct config_group *group,
 	struct o2nm_node *node = to_o2nm_node(item);
 	struct o2nm_cluster *cluster = to_o2nm_cluster(group->cg_item.ci_parent);
 
-	o2net_disconnect_node(node);
+	if (cluster->cl_nodes[node->nd_num] == node) {
+		o2net_disconnect_node(node);
 
-	if (cluster->cl_has_local &&
-	    (cluster->cl_local_node == node->nd_num)) {
-		cluster->cl_has_local = 0;
-		cluster->cl_local_node = O2NM_INVALID_NODE_NUM;
-		o2net_stop_listening(node);
+		if (cluster->cl_has_local &&
+		    (cluster->cl_local_node == node->nd_num)) {
+			cluster->cl_has_local = 0;
+			cluster->cl_local_node = O2NM_INVALID_NODE_NUM;
+			o2net_stop_listening(node);
+		}
 	}
 
 	/* XXX call into net to stop this node from trading messages */
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 7c835824247e..af405586c5b1 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -686,6 +686,9 @@ void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb)
 {
 	struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres;
 
+	/* Only one trimfs thread are allowed to work at the same time. */
+	mutex_lock(&osb->obs_trim_fs_mutex);
+
 	ocfs2_lock_res_init_once(lockres);
 	ocfs2_build_lock_name(OCFS2_LOCK_TYPE_TRIM_FS, 0, 0, lockres->l_name);
 	ocfs2_lock_res_init_common(osb, lockres, OCFS2_LOCK_TYPE_TRIM_FS,
@@ -698,6 +701,8 @@ void ocfs2_trim_fs_lock_res_uninit(struct ocfs2_super *osb)
 
 	ocfs2_simple_drop_lockres(osb, lockres);
 	ocfs2_lock_res_free(lockres);
+
+	mutex_unlock(&osb->obs_trim_fs_mutex);
 }
 
 static void ocfs2_orphan_scan_lock_res_init(struct ocfs2_lock_res *res,
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 4f86ac0027b5..1f029fbe8b8d 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -407,6 +407,7 @@ struct ocfs2_super
 	struct ocfs2_lock_res osb_rename_lockres;
 	struct ocfs2_lock_res osb_nfs_sync_lockres;
 	struct ocfs2_lock_res osb_trim_fs_lockres;
+	struct mutex obs_trim_fs_mutex;
 	struct ocfs2_dlm_debug *osb_dlm_debug;
 
 	struct dentry *osb_debug_root;
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 2ee76a90ba8f..dc4bce1649c1 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -712,6 +712,8 @@ TRACE_EVENT(ocfs2_trim_extent,
 
 DEFINE_OCFS2_ULL_UINT_UINT_UINT_EVENT(ocfs2_trim_group);
 
+DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_trim_mainbm);
+
 DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_trim_fs);
 
 /* End of trace events for fs/ocfs2/alloc.c. */
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index d7407994f308..ea0756d83250 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -55,7 +55,7 @@ struct ocfs2_slot_info {
 	unsigned int si_blocks;
 	struct buffer_head **si_bh;
 	unsigned int si_num_slots;
-	struct ocfs2_slot *si_slots;
+	struct ocfs2_slot si_slots[];
 };
 
 
@@ -420,9 +420,7 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb)
 	struct inode *inode = NULL;
 	struct ocfs2_slot_info *si;
 
-	si = kzalloc(sizeof(struct ocfs2_slot_info) +
-		     (sizeof(struct ocfs2_slot) * osb->max_slots),
-		     GFP_KERNEL);
+	si = kzalloc(struct_size(si, si_slots, osb->max_slots), GFP_KERNEL);
 	if (!si) {
 		status = -ENOMEM;
 		mlog_errno(status);
@@ -431,8 +429,6 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb)
 
 	si->si_extended = ocfs2_uses_extended_slot_map(osb);
 	si->si_num_slots = osb->max_slots;
-	si->si_slots = (struct ocfs2_slot *)((char *)si +
-					     sizeof(struct ocfs2_slot_info));
 
 	inode = ocfs2_get_system_file_inode(osb, SLOT_MAP_SYSTEM_INODE,
 					    OCFS2_INVALID_SLOT);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 3415e0b09398..96ae7cedd487 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1847,6 +1847,8 @@ static int ocfs2_mount_volume(struct super_block *sb)
 	if (ocfs2_is_hard_readonly(osb))
 		goto leave;
 
+	mutex_init(&osb->obs_trim_fs_mutex);
+
 	status = ocfs2_dlm_init(osb);
 	if (status < 0) {
 		mlog_errno(status);