[PATCH 2/2] GFS2: Add a gfs2-specific prune_icache_sb

[Bob Peterson]

This patch adds a new prune_icache_sb function for the VFS slab
shrinker to call. Trying to directly free the inodes from memory
might deadlock because it evicts inodes, which calls into DLM
to acquire the glock. The DLM, in turn, may block on a pending
fence operation, which may already be blocked on memory allocation
that caused the slab shrinker to be called in the first place.

Signed-off-by: Bob Peterson <rpeterso@xxxxxxxxxx>
---
 fs/gfs2/incore.h     |  2 ++
 fs/gfs2/ops_fstype.c |  1 +
 fs/gfs2/quota.c      | 25 +++++++++++++++++++++++++
 fs/gfs2/super.c      | 13 +++++++++++++
 4 files changed, 41 insertions(+)

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index a6a3389..a367459 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -757,6 +757,8 @@ struct gfs2_sbd {
 
 	struct task_struct *sd_logd_process;
 	struct task_struct *sd_quotad_process;
+	int sd_iprune; /* inodes to prune */
+	spinlock_t sd_shrinkspin;
 
 	/* Quota stuff */
 
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 4546360..65a69be 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -95,6 +95,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	spin_lock_init(&sdp->sd_jindex_spin);
 	mutex_init(&sdp->sd_jindex_mutex);
 	init_completion(&sdp->sd_journal_ready);
+	spin_lock_init(&sdp->sd_shrinkspin);
 
 	INIT_LIST_HEAD(&sdp->sd_quota_list);
 	mutex_init(&sdp->sd_quota_mutex);
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index ce7d69a..5810a2c 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1528,14 +1528,39 @@ void gfs2_wake_up_statfs(struct gfs2_sbd *sdp) {
 int gfs2_quotad(void *data)
 {
 	struct gfs2_sbd *sdp = data;
+	struct super_block *sb = sdp->sd_vfs;
 	struct gfs2_tune *tune = &sdp->sd_tune;
 	unsigned long statfs_timeo = 0;
 	unsigned long quotad_timeo = 0;
 	unsigned long t = 0;
 	DEFINE_WAIT(wait);
 	int empty;
+	int rc;
+	struct shrink_control sc = {.gfp_mask = GFP_KERNEL, };
 
 	while (!kthread_should_stop()) {
+		/* TODO: Deal with shrinking of dcache */
+		/* Prune any inode cache intended by the shrinker. */
+		spin_lock(&sdp->sd_shrinkspin);
+		if (sdp->sd_iprune > 0) {
+			sc.nr_to_scan = sdp->sd_iprune;
+			if (sc.nr_to_scan > 1024)
+				sc.nr_to_scan = 1024;
+			sdp->sd_iprune -= sc.nr_to_scan;
+			spin_unlock(&sdp->sd_shrinkspin);
+			rc = prune_icache_sb(sb, &sc);
+			if (rc < 0) {
+				spin_lock(&sdp->sd_shrinkspin);
+				sdp->sd_iprune = 0;
+				spin_unlock(&sdp->sd_shrinkspin);
+			}
+			if (sdp->sd_iprune) {
+				cond_resched();
+				continue;
+			}
+		} else {
+			spin_unlock(&sdp->sd_shrinkspin);
+		}
 
 		/* Update the master statfs file */
 		if (sdp->sd_statfs_force_sync) {
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 9b2ff353..75e8a85 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1667,6 +1667,18 @@ static void gfs2_destroy_inode(struct inode *inode)
 	call_rcu(&inode->i_rcu, gfs2_i_callback);
 }
 
+static long gfs2_prune_icache_sb(struct super_block *sb,
+				 struct shrink_control *sc)
+{
+	struct gfs2_sbd *sdp;
+
+	sdp = sb->s_fs_info;
+	spin_lock(&sdp->sd_shrinkspin);
+	sdp->sd_iprune = sc->nr_to_scan + 1;
+	spin_unlock(&sdp->sd_shrinkspin);
+	return 0;
+}
+
 const struct super_operations gfs2_super_ops = {
 	.alloc_inode		= gfs2_alloc_inode,
 	.destroy_inode		= gfs2_destroy_inode,
@@ -1681,5 +1693,6 @@ const struct super_operations gfs2_super_ops = {
 	.remount_fs		= gfs2_remount_fs,
 	.drop_inode		= gfs2_drop_inode,
 	.show_options		= gfs2_show_options,
+	.prune_icache_sb	= gfs2_prune_icache_sb,
 };
 
-- 
2.5.5