Convert wait_caps_flush() from an unbounded wait_event() to a
bounded wait_event_timeout() with a 60-second period. If the
flush hasn't completed after each timeout, dump the pending
cap_flush list (up to 5 times) to aid debugging hung flush
scenarios.

Add a ci back-pointer to struct ceph_cap_flush so the diagnostic
dump can identify which inodes have outstanding flushes. Add
i_last_cap_flush_ack to ceph_inode_info for tracking the latest
acknowledged flush tid per inode.

Signed-off-by: Alex Markuze <amarkuze@redhat.com>
---
 fs/ceph/caps.c       |  7 +++++++
 fs/ceph/mds_client.c | 41 +++++++++++++++++++++++++++++++++++++++--
 fs/ceph/super.h      |  2 ++
 3 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d51454e995a8..be030fb8e864 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1648,6 +1648,7 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci,
 
 		spin_lock(&mdsc->cap_dirty_lock);
 		capsnap->cap_flush.tid = ++mdsc->last_cap_flush_tid;
+		capsnap->cap_flush.ci = ci;
 		list_add_tail(&capsnap->cap_flush.g_list,
 			      &mdsc->cap_flush_list);
 		if (oldest_flush_tid == 0)
@@ -1846,6 +1847,9 @@ struct ceph_cap_flush *ceph_alloc_cap_flush(void)
 		return NULL;
 
 	cf->is_capsnap = false;
+	cf->ci = NULL;
+	cf->tid = 0;
+	cf->wake = false;
 	return cf;
 }
 
@@ -1931,6 +1935,7 @@ static u64 __mark_caps_flushing(struct inode *inode,
 	doutc(cl, "%p %llx.%llx now !dirty\n", inode, ceph_vinop(inode));
 
 	swap(cf, ci->i_prealloc_cap_flush);
+	cf->ci = ci;
 	cf->caps = flushing;
 	cf->wake = wake;
 
@@ -3826,6 +3831,8 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 	bool wake_ci = false;
 	bool wake_mdsc = false;
 
+	ci->i_last_cap_flush_ack = flush_tid;
+
 	list_for_each_entry_safe(cf, tmp_cf, &ci->i_cap_flush_list, i_list) {
 		/* Is this the one that was flushed? */
 		if (cf->tid == flush_tid)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 28bb27b09b40..e27f2f148dea 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -27,6 +27,8 @@
 #include <trace/events/ceph.h>
 
 #define RECONNECT_MAX_SIZE (INT_MAX - PAGE_SIZE)
+#define CEPH_CAP_FLUSH_WAIT_TIMEOUT_SEC 60
+#define CEPH_CAP_FLUSH_MAX_DUMP_COUNT 5
 
 /*
  * A cluster of MDS (metadata server) daemons is responsible for
@@ -2285,6 +2287,34 @@ static int check_caps_flush(struct ceph_mds_client *mdsc,
 	return ret;
 }
 
+static void dump_cap_flushes(struct ceph_mds_client *mdsc, u64 want_tid)
+{
+	struct ceph_client *cl = mdsc->fsc->client;
+	struct ceph_cap_flush *cf;
+
+	pr_info_client(cl, "still waiting for cap flushes through %llu:\n",
+		       want_tid);
+	spin_lock(&mdsc->cap_dirty_lock);
+	list_for_each_entry(cf, &mdsc->cap_flush_list, g_list) {
+		if (cf->tid > want_tid)
+			break;
+		if (!cf->ci) {
+			pr_info_client(cl,
+				       "(null ci) %s tid=%llu wake=%d%s\n",
+				       ceph_cap_string(cf->caps), cf->tid,
+				       cf->wake,
+				       cf->is_capsnap ? " is_capsnap" : "");
+			continue;
+		}
+		pr_info_client(cl, "%llx:%llx %s %llu %llu %d%s\n",
+			       ceph_vinop(&cf->ci->netfs.inode),
+			       ceph_cap_string(cf->caps), cf->tid,
+			       cf->ci->i_last_cap_flush_ack, cf->wake,
+			       cf->is_capsnap ? " is_capsnap" : "");
+	}
+	spin_unlock(&mdsc->cap_dirty_lock);
+}
+
 /*
  * flush all dirty inode data to disk.
  *
@@ -2294,11 +2324,18 @@ static void wait_caps_flush(struct ceph_mds_client *mdsc,
 			    u64 want_flush_tid)
 {
 	struct ceph_client *cl = mdsc->fsc->client;
+	int i = 0;
+	long ret;
 
 	doutc(cl, "want %llu\n", want_flush_tid);
 
-	wait_event(mdsc->cap_flushing_wq,
-		   check_caps_flush(mdsc, want_flush_tid));
+	do {
+		ret = wait_event_timeout(mdsc->cap_flushing_wq,
+			   check_caps_flush(mdsc, want_flush_tid),
+			   CEPH_CAP_FLUSH_WAIT_TIMEOUT_SEC * HZ);
+		if (ret == 0 && i++ < CEPH_CAP_FLUSH_MAX_DUMP_COUNT)
+			dump_cap_flushes(mdsc, want_flush_tid);
+	} while (ret == 0);
 
 	doutc(cl, "ok, flushed thru %llu\n", want_flush_tid);
 }
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 69a71848240f..9e80c816aa7a 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -238,6 +238,7 @@ struct ceph_cap_flush {
 	bool is_capsnap; /* true means capsnap */
 	struct list_head g_list; // global
 	struct list_head i_list; // per inode
+	struct ceph_inode_info *ci;
 };
 
 /*
@@ -443,6 +444,7 @@ struct ceph_inode_info {
 	struct ceph_snap_context *i_head_snapc;  /* set if wr_buffer_head > 0 or
 						    dirty|flushing caps */
 	unsigned i_snap_caps;           /* cap bits for snapped files */
+	u64 i_last_cap_flush_ack;		/* latest cap flush_ack tid for this inode */
 
 	unsigned long i_last_rd;
 	unsigned long i_last_wr;
-- 
2.34.1