1 files changed, 145 insertions, 39 deletions

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a50497142e59..4a26862d7667 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1103,8 +1103,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 				     frag.frag, mds);
 				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
 				    CEPH_MDS_STATE_ACTIVE) {
-					if (mode == USE_ANY_MDS &&
-					    !ceph_mdsmap_is_laggy(mdsc->mdsmap,
+					if (!ceph_mdsmap_is_laggy(mdsc->mdsmap,
 								  mds))
 						goto out;
 				}
@@ -1168,7 +1167,7 @@ static struct ceph_msg *create_session_msg(u32 op, u64 seq)
 
 static const unsigned char feature_bits[] = CEPHFS_FEATURES_CLIENT_SUPPORTED;
 #define FEATURE_BYTES(c) (DIV_ROUND_UP((size_t)feature_bits[c - 1] + 1, 64) * 8)
-static void encode_supported_features(void **p, void *end)
+static int encode_supported_features(void **p, void *end)
 {
 	static const size_t count = ARRAY_SIZE(feature_bits);
 
@@ -1176,16 +1175,64 @@ static void encode_supported_features(void **p, void *end)
 		size_t i;
 		size_t size = FEATURE_BYTES(count);
 
-		BUG_ON(*p + 4 + size > end);
+		if (WARN_ON_ONCE(*p + 4 + size > end))
+			return -ERANGE;
+
 		ceph_encode_32(p, size);
 		memset(*p, 0, size);
 		for (i = 0; i < count; i++)
 			((unsigned char*)(*p))[i / 8] |= BIT(feature_bits[i] % 8);
 		*p += size;
 	} else {
-		BUG_ON(*p + 4 > end);
+		if (WARN_ON_ONCE(*p + 4 > end))
+			return -ERANGE;
+
 		ceph_encode_32(p, 0);
 	}
+
+	return 0;
+}
+
+static const unsigned char metric_bits[] = CEPHFS_METRIC_SPEC_CLIENT_SUPPORTED;
+#define METRIC_BYTES(cnt) (DIV_ROUND_UP((size_t)metric_bits[cnt - 1] + 1, 64) * 8)
+static int encode_metric_spec(void **p, void *end)
+{
+	static const size_t count = ARRAY_SIZE(metric_bits);
+
+	/* header */
+	if (WARN_ON_ONCE(*p + 2 > end))
+		return -ERANGE;
+
+	ceph_encode_8(p, 1); /* version */
+	ceph_encode_8(p, 1); /* compat */
+
+	if (count > 0) {
+		size_t i;
+		size_t size = METRIC_BYTES(count);
+
+		if (WARN_ON_ONCE(*p + 4 + 4 + size > end))
+			return -ERANGE;
+
+		/* metric spec info length */
+		ceph_encode_32(p, 4 + size);
+
+		/* metric spec */
+		ceph_encode_32(p, size);
+		memset(*p, 0, size);
+		for (i = 0; i < count; i++)
+			((unsigned char *)(*p))[i / 8] |= BIT(metric_bits[i] % 8);
+		*p += size;
+	} else {
+		if (WARN_ON_ONCE(*p + 4 + 4 > end))
+			return -ERANGE;
+
+		/* metric spec info length */
+		ceph_encode_32(p, 4);
+		/* metric spec */
+		ceph_encode_32(p, 0);
+	}
+
+	return 0;
 }
 
 /*
@@ -1203,6 +1250,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 	struct ceph_mount_options *fsopt = mdsc->fsc->mount_options;
 	size_t size, count;
 	void *p, *end;
+	int ret;
 
 	const char* metadata[][2] = {
 		{"hostname", mdsc->nodename},
@@ -1227,12 +1275,19 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 		size = FEATURE_BYTES(count);
 	extra_bytes += 4 + size;
 
+	/* metric spec */
+	size = 0;
+	count = ARRAY_SIZE(metric_bits);
+	if (count > 0)
+		size = METRIC_BYTES(count);
+	extra_bytes += 2 + 4 + 4 + size;
+
 	/* Allocate the message */
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes,
 			   GFP_NOFS, false);
 	if (!msg) {
 		pr_err("create_session_msg ENOMEM creating msg\n");
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	p = msg->front.iov_base;
 	end = p + msg->front.iov_len;
@@ -1245,9 +1300,9 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 	 * Serialize client metadata into waiting buffer space, using
 	 * the format that userspace expects for map<string, string>
 	 *
-	 * ClientSession messages with metadata are v3
+	 * ClientSession messages with metadata are v4
 	 */
-	msg->hdr.version = cpu_to_le16(3);
+	msg->hdr.version = cpu_to_le16(4);
 	msg->hdr.compat_version = cpu_to_le16(1);
 
 	/* The write pointer, following the session_head structure */
@@ -1269,7 +1324,20 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 		p += val_len;
 	}
 
-	encode_supported_features(&p, end);
+	ret = encode_supported_features(&p, end);
+	if (ret) {
+		pr_err("encode_supported_features failed!\n");
+		ceph_msg_put(msg);
+		return ERR_PTR(ret);
+	}
+
+	ret = encode_metric_spec(&p, end);
+	if (ret) {
+		pr_err("encode_metric_spec failed!\n");
+		ceph_msg_put(msg);
+		return ERR_PTR(ret);
+	}
+
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 
@@ -1297,8 +1365,8 @@ static int __open_session(struct ceph_mds_client *mdsc,
 
 	/* send connect message */
 	msg = create_session_open_msg(mdsc, session->s_seq);
-	if (!msg)
-		return -ENOMEM;
+	if (IS_ERR(msg))
+		return PTR_ERR(msg);
 	ceph_con_send(&session->s_con, msg);
 	return 0;
 }
@@ -1312,6 +1380,7 @@ static struct ceph_mds_session *
 __open_export_target_session(struct ceph_mds_client *mdsc, int target)
 {
 	struct ceph_mds_session *session;
+	int ret;
 
 	session = __ceph_lookup_mds_session(mdsc, target);
 	if (!session) {
@@ -1320,8 +1389,11 @@ __open_export_target_session(struct ceph_mds_client *mdsc, int target)
 			return session;
 	}
 	if (session->s_state == CEPH_MDS_SESSION_NEW ||
-	    session->s_state == CEPH_MDS_SESSION_CLOSING)
-		__open_session(mdsc, session);
+	    session->s_state == CEPH_MDS_SESSION_CLOSING) {
+		ret = __open_session(mdsc, session);
+		if (ret)
+			return ERR_PTR(ret);
+	}
 
 	return session;
 }
@@ -1485,6 +1557,7 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session,
 			cap->session = NULL;
 			list_del_init(&cap->session_caps);
 			session->s_nr_caps--;
+			atomic64_dec(&session->s_mdsc->metric.total_caps);
 			if (cap->queue_release)
 				__ceph_queue_cap_release(session, cap);
 			else
@@ -1785,8 +1858,7 @@ static void renewed_caps(struct ceph_mds_client *mdsc,
 /*
  * send a session close request
  */
-static int request_close_session(struct ceph_mds_client *mdsc,
-				 struct ceph_mds_session *session)
+static int request_close_session(struct ceph_mds_session *session)
 {
 	struct ceph_msg *msg;
 
@@ -1809,7 +1881,7 @@ static int __close_session(struct ceph_mds_client *mdsc,
 	if (session->s_state >= CEPH_MDS_SESSION_CLOSING)
 		return 0;
 	session->s_state = CEPH_MDS_SESSION_CLOSING;
-	return request_close_session(mdsc, session);
+	return request_close_session(session);
 }
 
 static bool drop_negative_children(struct dentry *dentry)
@@ -2520,7 +2592,12 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 		ceph_encode_copy(&p, &ts, sizeof(ts));
 	}
 
-	BUG_ON(p > end);
+	if (WARN_ON_ONCE(p > end)) {
+		ceph_msg_put(msg);
+		msg = ERR_PTR(-ERANGE);
+		goto out_free2;
+	}
+
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 
@@ -2756,7 +2833,9 @@ static void __do_request(struct ceph_mds_client *mdsc,
 		}
 		if (session->s_state == CEPH_MDS_SESSION_NEW ||
 		    session->s_state == CEPH_MDS_SESSION_CLOSING) {
-			__open_session(mdsc, session);
+			err = __open_session(mdsc, session);
+			if (err)
+				goto out_session;
 			/* retry the same mds later */
 			if (random)
 				req->r_resend_mds = mds;
@@ -3279,8 +3358,10 @@ static void handle_session(struct ceph_mds_session *session,
 			goto bad;
 		/* version >= 3, feature bits */
 		ceph_decode_32_safe(&p, end, len, bad);
-		ceph_decode_64_safe(&p, end, features, bad);
-		p += len - sizeof(features);
+		if (len) {
+			ceph_decode_64_safe(&p, end, features, bad);
+			p += len - sizeof(features);
+		}
 	}
 
 	mutex_lock(&mdsc->mutex);
@@ -3310,6 +3391,8 @@ static void handle_session(struct ceph_mds_session *session,
 		session->s_state = CEPH_MDS_SESSION_OPEN;
 		session->s_features = features;
 		renewed_caps(mdsc, session, 0);
+		if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features))
+			metric_schedule_delayed(&mdsc->metric);
 		wake = 1;
 		if (mdsc->stopping)
 			__close_session(mdsc, session);
@@ -4263,6 +4346,30 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc)
 	ceph_force_reconnect(fsc->sb);
 }
 
+bool check_session_state(struct ceph_mds_session *s)
+{
+	if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
+		dout("resending session close request for mds%d\n",
+				s->s_mds);
+		request_close_session(s);
+		return false;
+	}
+	if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
+		if (s->s_state == CEPH_MDS_SESSION_OPEN) {
+			s->s_state = CEPH_MDS_SESSION_HUNG;
+			pr_info("mds%d hung\n", s->s_mds);
+		}
+	}
+	if (s->s_state == CEPH_MDS_SESSION_NEW ||
+	    s->s_state == CEPH_MDS_SESSION_RESTARTING ||
+	    s->s_state == CEPH_MDS_SESSION_CLOSED ||
+	    s->s_state == CEPH_MDS_SESSION_REJECTED)
+		/* this mds is failed or recovering, just wait */
+		return false;
+
+	return true;
+}
+
 /*
  * delayed work -- periodically trim expired leases, renew caps with mds
  */
@@ -4283,6 +4390,9 @@ static void delayed_work(struct work_struct *work)
 
 	dout("mdsc delayed_work\n");
 
+	if (mdsc->stopping)
+		return;
+
 	mutex_lock(&mdsc->mutex);
 	renew_interval = mdsc->mdsmap->m_session_timeout >> 2;
 	renew_caps = time_after_eq(jiffies, HZ*renew_interval +
@@ -4294,23 +4404,8 @@ static void delayed_work(struct work_struct *work)
 		struct ceph_mds_session *s = __ceph_lookup_mds_session(mdsc, i);
 		if (!s)
 			continue;
-		if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
-			dout("resending session close request for mds%d\n",
-			     s->s_mds);
-			request_close_session(mdsc, s);
-			ceph_put_mds_session(s);
-			continue;
-		}
-		if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
-			if (s->s_state == CEPH_MDS_SESSION_OPEN) {
-				s->s_state = CEPH_MDS_SESSION_HUNG;
-				pr_info("mds%d hung\n", s->s_mds);
-			}
-		}
-		if (s->s_state == CEPH_MDS_SESSION_NEW ||
-		    s->s_state == CEPH_MDS_SESSION_RESTARTING ||
-		    s->s_state == CEPH_MDS_SESSION_REJECTED) {
-			/* this mds is failed or recovering, just wait */
+
+		if (!check_session_state(s)) {
 			ceph_put_mds_session(s);
 			continue;
 		}
@@ -4359,7 +4454,6 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 		goto err_mdsc;
 	}
 
-	fsc->mdsc = mdsc;
 	init_completion(&mdsc->safe_umount_waiters);
 	init_waitqueue_head(&mdsc->session_close_wq);
 	INIT_LIST_HEAD(&mdsc->waiting_for_map);
@@ -4414,6 +4508,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 
 	strscpy(mdsc->nodename, utsname()->nodename,
 		sizeof(mdsc->nodename));
+
+	fsc->mdsc = mdsc;
 	return 0;
 
 err_mdsmap:
@@ -4657,7 +4753,16 @@ void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc)
 static void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
 {
 	dout("stop\n");
-	cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */
+	/*
+	 * Make sure the delayed work stopped before releasing
+	 * the resources.
+	 *
+	 * Because the cancel_delayed_work_sync() will only
+	 * guarantee that the work finishes executing. But the
+	 * delayed work will re-arm itself again after that.
+	 */
+	flush_delayed_work(&mdsc->delayed_work);
+
 	if (mdsc->mdsmap)
 		ceph_mdsmap_destroy(mdsc->mdsmap);
 	kfree(mdsc->sessions);
@@ -4680,6 +4785,7 @@ void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
 
 	ceph_metric_destroy(&mdsc->metric);
 
+	flush_delayed_work(&mdsc->metric.delayed_work);
 	fsc->mdsc = NULL;
 	kfree(mdsc);
 	dout("mdsc_destroy %p done\n", mdsc);