gfs2: Evict inodes cooperatively

Add a gfs2_evict_inodes() helper that evicts inodes cooperatively across
the cluster.  This avoids running into timeouts during unmount
unnecessarily.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

3 files changed, 59 insertions, 0 deletions

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index d35bb49d1d3f..79485329118b 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -607,6 +607,7 @@ enum {
 	SDF_WITHDRAW_RECOVERY	= 14, /* Wait for journal recovery when we are
 					 withdrawing */
 	SDF_DEACTIVATING	= 15,
+	SDF_EVICTING		= 16,
 };
 
 enum gfs2_freeze_state {
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 9db376950014..6de901c3b89b 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1728,6 +1728,55 @@ static int gfs2_meta_init_fs_context(struct fs_context *fc)
 	return 0;
 }
 
+/**
+ * gfs2_evict_inodes - evict inodes cooperatively
+ * @sb: the superblock
+ *
+ * When evicting an inode with a zero link count, we are trying to upgrade the
+ * inode's iopen glock from SH to EX mode in order to determine if we can
+ * delete the inode.  The other nodes are supposed to evict the inode from
+ * their caches if they can, and to poke the inode's inode glock if they cannot
+ * do so.  Either behavior allows gfs2_upgrade_iopen_glock() to proceed
+ * quickly, but if the other nodes are not cooperating, the lock upgrading
+ * attempt will time out.  Since inodes are evicted sequentially, this can add
+ * up quickly.
+ *
+ * Function evict_inodes() tries to keep the s_inode_list_lock list locked over
+ * a long time, which prevents other inodes from being evicted concurrently.
+ * This precludes the cooperative behavior we are looking for.  This special
+ * version of evict_inodes() avoids that.
+ *
+ * Modeled after drop_pagecache_sb().
+ */
+static void gfs2_evict_inodes(struct super_block *sb)
+{
+	struct inode *inode, *toput_inode = NULL;
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+
+	set_bit(SDF_EVICTING, &sdp->sd_flags);
+
+	spin_lock(&sb->s_inode_list_lock);
+	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+		spin_lock(&inode->i_lock);
+		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) &&
+		    !need_resched()) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+		atomic_inc(&inode->i_count);
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&sb->s_inode_list_lock);
+
+		iput(toput_inode);
+		toput_inode = inode;
+
+		cond_resched();
+		spin_lock(&sb->s_inode_list_lock);
+	}
+	spin_unlock(&sb->s_inode_list_lock);
+	iput(toput_inode);
+}
+
 static void gfs2_kill_sb(struct super_block *sb)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
@@ -1744,6 +1793,8 @@ static void gfs2_kill_sb(struct super_block *sb)
 	sdp->sd_master_dir = NULL;
 	shrink_dcache_sb(sb);
 
+	gfs2_evict_inodes(sb);
+
 	/*
 	 * Flush and then drain the delete workqueue here (via
 	 * destroy_workqueue()) to ensure that any delete work that
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 63512bb9d6f0..52c3502de58c 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -935,6 +935,7 @@ static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
 static int gfs2_drop_inode(struct inode *inode)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 
 	if (inode->i_nlink &&
 	    gfs2_holder_initialized(&ip->i_iopen_gh)) {
@@ -959,6 +960,12 @@ static int gfs2_drop_inode(struct inode *inode)
 		return 0;
 	}
 
+	/*
+	 * No longer cache inodes when trying to evict them all.
+	 */
+	if (test_bit(SDF_EVICTING, &sdp->sd_flags))
+		return 1;
+
 	return generic_drop_inode(inode);
 }