Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless

net/bluetooth/hci_conn.c

@@ -29,6 +29,7 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/a2mp.h>
+#include <net/bluetooth/smp.h>
 
 static void hci_le_connect(struct hci_conn *conn)
 {
@@ -619,6 +620,9 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 {
 	BT_DBG("hcon %p", conn);
 
+	if (conn->type == LE_LINK)
+		return smp_conn_security(conn, sec_level);
+
 	/* For sdp we don't need the link key. */
 	if (sec_level == BT_SECURITY_SDP)
 		return 1;

net/bluetooth/hci_event.c

@@ -1365,6 +1365,9 @@ static bool hci_resolve_next_name(struct hci_dev *hdev)
 		return false;
 
 	e = hci_inquiry_cache_lookup_resolve(hdev, BDADDR_ANY, NAME_NEEDED);
+	if (!e)
+		return false;
+
 	if (hci_resolve_name(hdev, e) == 0) {
 		e->name_state = NAME_PENDING;
 		return true;
@@ -1393,12 +1396,20 @@ static void hci_check_pending_name(struct hci_dev *hdev, struct hci_conn *conn,
 		return;
 
 	e = hci_inquiry_cache_lookup_resolve(hdev, bdaddr, NAME_PENDING);
-	if (e) {
+	/* If the device was not found in a list of found devices names of which
+	 * are pending. there is no need to continue resolving a next name as it
+	 * will be done upon receiving another Remote Name Request Complete
+	 * Event */
+	if (!e)
+		return;
+
+	list_del(&e->list);
+	if (name) {
 		e->name_state = NAME_KNOWN;
-		list_del(&e->list);
-		if (name)
-			mgmt_remote_name(hdev, bdaddr, ACL_LINK, 0x00,
-					 e->data.rssi, name, name_len);
+		mgmt_remote_name(hdev, bdaddr, ACL_LINK, 0x00,
+				 e->data.rssi, name, name_len);
+	} else {
+		e->name_state = NAME_NOT_KNOWN;
 	}
 
 	if (hci_resolve_next_name(hdev))
@@ -1749,7 +1760,12 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		if (conn->type == ACL_LINK) {
 			conn->state = BT_CONFIG;
 			hci_conn_hold(conn);
-			conn->disc_timeout = HCI_DISCONN_TIMEOUT;
+
+			if (!conn->out && !hci_conn_ssp_enabled(conn) &&
+			    !hci_find_link_key(hdev, &ev->bdaddr))
+				conn->disc_timeout = HCI_PAIRING_TIMEOUT;
+			else
+				conn->disc_timeout = HCI_DISCONN_TIMEOUT;
 		} else
 			conn->state = BT_CONNECTED;
 

net/bluetooth/l2cap_core.c

@@ -1198,6 +1198,7 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn)
 	sk = chan->sk;
 
 	hci_conn_hold(conn->hcon);
+	conn->hcon->disc_timeout = HCI_DISCONN_TIMEOUT;
 
 	bacpy(&bt_sk(sk)->src, conn->src);
 	bacpy(&bt_sk(sk)->dst, conn->dst);
@@ -1215,14 +1216,15 @@ clean:
 static void l2cap_conn_ready(struct l2cap_conn *conn)
 {
 	struct l2cap_chan *chan;
+	struct hci_conn *hcon = conn->hcon;
 
 	BT_DBG("conn %p", conn);
 
-	if (!conn->hcon->out && conn->hcon->type == LE_LINK)
+	if (!hcon->out && hcon->type == LE_LINK)
 		l2cap_le_conn_ready(conn);
 
-	if (conn->hcon->out && conn->hcon->type == LE_LINK)
-		smp_conn_security(conn, conn->hcon->pending_sec_level);
+	if (hcon->out && hcon->type == LE_LINK)
+		smp_conn_security(hcon, hcon->pending_sec_level);
 
 	mutex_lock(&conn->chan_lock);
 
@@ -1235,8 +1237,8 @@ static void l2cap_conn_ready(struct l2cap_conn *conn)
 			continue;
 		}
 
-		if (conn->hcon->type == LE_LINK) {
-			if (smp_conn_security(conn, chan->sec_level))
+		if (hcon->type == LE_LINK) {
+			if (smp_conn_security(hcon, chan->sec_level))
 				l2cap_chan_ready(chan);
 
 		} else if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) {

net/bluetooth/l2cap_sock.c

@@ -619,7 +619,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch
 				break;
 			}
 
-			if (smp_conn_security(conn, sec.level))
+			if (smp_conn_security(conn->hcon, sec.level))
 				break;
 			sk->sk_state = BT_CONFIG;
 			chan->state = BT_CONFIG;
@@ -1180,7 +1180,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int p
 
 	chan = l2cap_chan_create();
 	if (!chan) {
-		l2cap_sock_kill(sk);
+		sk_free(sk);
 		return NULL;
 	}
 

net/bluetooth/sco.c

@@ -131,6 +131,15 @@ static int sco_conn_del(struct hci_conn *hcon, int err)
 		sco_sock_clear_timer(sk);
 		sco_chan_del(sk, err);
 		bh_unlock_sock(sk);
+
+		sco_conn_lock(conn);
+		conn->sk = NULL;
+		sco_pi(sk)->conn = NULL;
+		sco_conn_unlock(conn);
+
+		if (conn->hcon)
+			hci_conn_put(conn->hcon);
+
 		sco_sock_kill(sk);
 	}
 
@@ -821,16 +830,6 @@ static void sco_chan_del(struct sock *sk, int err)
 
 	BT_DBG("sk %p, conn %p, err %d", sk, conn, err);
 
-	if (conn) {
-		sco_conn_lock(conn);
-		conn->sk = NULL;
-		sco_pi(sk)->conn = NULL;
-		sco_conn_unlock(conn);
-
-		if (conn->hcon)
-			hci_conn_put(conn->hcon);
-	}
-
 	sk->sk_state = BT_CLOSED;
 	sk->sk_err   = err;
 	sk->sk_state_change(sk);

net/bluetooth/smp.c

@@ -267,10 +267,10 @@ static void smp_failure(struct l2cap_conn *conn, u8 reason, u8 send)
 	mgmt_auth_failed(conn->hcon->hdev, conn->dst, hcon->type,
 			 hcon->dst_type, reason);
 
-	if (test_and_clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags)) {
-		cancel_delayed_work_sync(&conn->security_timer);
+	cancel_delayed_work_sync(&conn->security_timer);
+
+	if (test_and_clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags))
 		smp_chan_destroy(conn);
-	}
 }
 
 #define JUST_WORKS	0x00
@@ -579,8 +579,11 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 
 	if (!test_and_set_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags))
 		smp = smp_chan_create(conn);
+	else
+		smp = conn->smp_chan;
 
-	smp = conn->smp_chan;
+	if (!smp)
+		return SMP_UNSPECIFIED;
 
 	smp->preq[0] = SMP_CMD_PAIRING_REQ;
 	memcpy(&smp->preq[1], req, sizeof(*req));
@@ -757,9 +760,9 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	return 0;
 }
 
-int smp_conn_security(struct l2cap_conn *conn, __u8 sec_level)
+int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 {
-	struct hci_conn *hcon = conn->hcon;
+	struct l2cap_conn *conn = hcon->l2cap_data;
 	struct smp_chan *smp = conn->smp_chan;
 	__u8 authreq;
 

net/caif/caif_socket.c

@@ -141,7 +141,7 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	err = sk_filter(sk, skb);
 	if (err)
 		return err;
-	if (!sk_rmem_schedule(sk, skb->truesize) && rx_flow_is_on(cf_sk)) {
+	if (!sk_rmem_schedule(sk, skb, skb->truesize) && rx_flow_is_on(cf_sk)) {
 		set_rx_flow_off(cf_sk);
 		net_dbg_ratelimited("sending flow OFF due to rmem_schedule\n");
 		caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ);

net/ceph/ceph_common.c

@@ -17,6 +17,7 @@
 #include <linux/string.h>
 
 
+#include <linux/ceph/ceph_features.h>
 #include <linux/ceph/libceph.h>
 #include <linux/ceph/debugfs.h>
 #include <linux/ceph/decode.h>
@@ -460,27 +461,23 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
 	client->auth_err = 0;
 
 	client->extra_mon_dispatch = NULL;
-	client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT |
+	client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT |
 		supported_features;
-	client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT |
+	client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT |
 		required_features;
 
 	/* msgr */
 	if (ceph_test_opt(client, MYIP))
 		myaddr = &client->options->my_addr;
-	client->msgr = ceph_messenger_create(myaddr,
-					     client->supported_features,
-					     client->required_features);
-	if (IS_ERR(client->msgr)) {
-		err = PTR_ERR(client->msgr);
-		goto fail;
-	}
-	client->msgr->nocrc = ceph_test_opt(client, NOCRC);
+	ceph_messenger_init(&client->msgr, myaddr,
+		client->supported_features,
+		client->required_features,
+		ceph_test_opt(client, NOCRC));
 
 	/* subsystems */
 	err = ceph_monc_init(&client->monc, client);
 	if (err < 0)
-		goto fail_msgr;
+		goto fail;
 	err = ceph_osdc_init(&client->osdc, client);
 	if (err < 0)
 		goto fail_monc;
@@ -489,8 +486,6 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
 
 fail_monc:
 	ceph_monc_stop(&client->monc);
-fail_msgr:
-	ceph_messenger_destroy(client->msgr);
 fail:
 	kfree(client);
 	return ERR_PTR(err);
@@ -501,6 +496,8 @@ void ceph_destroy_client(struct ceph_client *client)
 {
 	dout("destroy_client %p\n", client);
 
+	atomic_set(&client->msgr.stopping, 1);
+
 	/* unmount */
 	ceph_osdc_stop(&client->osdc);
 
@@ -508,8 +505,6 @@ void ceph_destroy_client(struct ceph_client *client)
 
 	ceph_debugfs_client_cleanup(client);
 
-	ceph_messenger_destroy(client->msgr);
-
 	ceph_destroy_options(client->options);
 
 	kfree(client);

net/ceph/crush/mapper.c

@@ -306,7 +306,6 @@ static int crush_choose(const struct crush_map *map,
 	int item = 0;
 	int itemtype;
 	int collide, reject;
-	const unsigned int orig_tries = 5; /* attempts before we fall back to search */
 
 	dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "",
 		bucket->id, x, outpos, numrep);
@@ -351,8 +350,9 @@ static int crush_choose(const struct crush_map *map,
 					reject = 1;
 					goto reject;
 				}
-				if (flocal >= (in->size>>1) &&
-				    flocal > orig_tries)
+				if (map->choose_local_fallback_tries > 0 &&
+				    flocal >= (in->size>>1) &&
+				    flocal > map->choose_local_fallback_tries)
 					item = bucket_perm_choose(in, x, r);
 				else
 					item = crush_bucket_choose(in, x, r);
@@ -422,13 +422,14 @@ reject:
 					ftotal++;
 					flocal++;
 
-					if (collide && flocal < 3)
+					if (collide && flocal <= map->choose_local_tries)
 						/* retry locally a few times */
 						retry_bucket = 1;
-					else if (flocal <= in->size + orig_tries)
+					else if (map->choose_local_fallback_tries > 0 &&
+						 flocal <= in->size + map->choose_local_fallback_tries)
 						/* exhaustive bucket search */
 						retry_bucket = 1;
-					else if (ftotal < 20)
+					else if (ftotal <= map->choose_total_tries)
 						/* then retry descent */
 						retry_descent = 1;
 					else

net/ceph/mon_client.c

@@ -106,9 +106,9 @@ static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len)
 	monc->pending_auth = 1;
 	monc->m_auth->front.iov_len = len;
 	monc->m_auth->hdr.front_len = cpu_to_le32(len);
-	ceph_con_revoke(monc->con, monc->m_auth);
+	ceph_msg_revoke(monc->m_auth);
 	ceph_msg_get(monc->m_auth);  /* keep our ref */
-	ceph_con_send(monc->con, monc->m_auth);
+	ceph_con_send(&monc->con, monc->m_auth);
 }
 
 /*
@@ -117,8 +117,11 @@ static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len)
 static void __close_session(struct ceph_mon_client *monc)
 {
 	dout("__close_session closing mon%d\n", monc->cur_mon);
-	ceph_con_revoke(monc->con, monc->m_auth);
-	ceph_con_close(monc->con);
+	ceph_msg_revoke(monc->m_auth);
+	ceph_msg_revoke_incoming(monc->m_auth_reply);
+	ceph_msg_revoke(monc->m_subscribe);
+	ceph_msg_revoke_incoming(monc->m_subscribe_ack);
+	ceph_con_close(&monc->con);
 	monc->cur_mon = -1;
 	monc->pending_auth = 0;
 	ceph_auth_reset(monc->auth);
@@ -142,9 +145,8 @@ static int __open_session(struct ceph_mon_client *monc)
 		monc->want_next_osdmap = !!monc->want_next_osdmap;
 
 		dout("open_session mon%d opening\n", monc->cur_mon);
-		monc->con->peer_name.type = CEPH_ENTITY_TYPE_MON;
-		monc->con->peer_name.num = cpu_to_le64(monc->cur_mon);
-		ceph_con_open(monc->con,
+		ceph_con_open(&monc->con,
+			      CEPH_ENTITY_TYPE_MON, monc->cur_mon,
 			      &monc->monmap->mon_inst[monc->cur_mon].addr);
 
 		/* initiatiate authentication handshake */
@@ -226,8 +228,8 @@ static void __send_subscribe(struct ceph_mon_client *monc)
 
 		msg->front.iov_len = p - msg->front.iov_base;
 		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
-		ceph_con_revoke(monc->con, msg);
-		ceph_con_send(monc->con, ceph_msg_get(msg));
+		ceph_msg_revoke(msg);
+		ceph_con_send(&monc->con, ceph_msg_get(msg));
 
 		monc->sub_sent = jiffies | 1;  /* never 0 */
 	}
@@ -247,7 +249,7 @@ static void handle_subscribe_ack(struct ceph_mon_client *monc,
 	if (monc->hunting) {
 		pr_info("mon%d %s session established\n",
 			monc->cur_mon,
-			ceph_pr_addr(&monc->con->peer_addr.in_addr));
+			ceph_pr_addr(&monc->con.peer_addr.in_addr));
 		monc->hunting = false;
 	}
 	dout("handle_subscribe_ack after %d seconds\n", seconds);
@@ -439,6 +441,7 @@ static struct ceph_msg *get_generic_reply(struct ceph_connection *con,
 		m = NULL;
 	} else {
 		dout("get_generic_reply %lld got %p\n", tid, req->reply);
+		*skip = 0;
 		m = ceph_msg_get(req->reply);
 		/*
 		 * we don't need to track the connection reading into
@@ -461,7 +464,7 @@ static int do_generic_request(struct ceph_mon_client *monc,
 	req->request->hdr.tid = cpu_to_le64(req->tid);
 	__insert_generic_request(monc, req);
 	monc->num_generic_requests++;
-	ceph_con_send(monc->con, ceph_msg_get(req->request));
+	ceph_con_send(&monc->con, ceph_msg_get(req->request));
 	mutex_unlock(&monc->mutex);
 
 	err = wait_for_completion_interruptible(&req->completion);
@@ -684,8 +687,9 @@ static void __resend_generic_request(struct ceph_mon_client *monc)
 
 	for (p = rb_first(&monc->generic_request_tree); p; p = rb_next(p)) {
 		req = rb_entry(p, struct ceph_mon_generic_request, node);
-		ceph_con_revoke(monc->con, req->request);
-		ceph_con_send(monc->con, ceph_msg_get(req->request));
+		ceph_msg_revoke(req->request);
+		ceph_msg_revoke_incoming(req->reply);
+		ceph_con_send(&monc->con, ceph_msg_get(req->request));
 	}
 }
 
@@ -705,7 +709,7 @@ static void delayed_work(struct work_struct *work)
 		__close_session(monc);
 		__open_session(monc);  /* continue hunting */
 	} else {
-		ceph_con_keepalive(monc->con);
+		ceph_con_keepalive(&monc->con);
 
 		__validate_auth(monc);
 
@@ -760,19 +764,12 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
 		goto out;
 
 	/* connection */
-	monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL);
-	if (!monc->con)
-		goto out_monmap;
-	ceph_con_init(monc->client->msgr, monc->con);
-	monc->con->private = monc;
-	monc->con->ops = &mon_con_ops;
-
 	/* authentication */
 	monc->auth = ceph_auth_init(cl->options->name,
 				    cl->options->key);
 	if (IS_ERR(monc->auth)) {
 		err = PTR_ERR(monc->auth);
-		goto out_con;
+		goto out_monmap;
 	}
 	monc->auth->want_keys =
 		CEPH_ENTITY_TYPE_AUTH | CEPH_ENTITY_TYPE_MON |
@@ -801,6 +798,9 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
 	if (!monc->m_auth)
 		goto out_auth_reply;
 
+	ceph_con_init(&monc->con, monc, &mon_con_ops,
+		      &monc->client->msgr);
+
 	monc->cur_mon = -1;
 	monc->hunting = true;
 	monc->sub_renew_after = jiffies;
@@ -824,8 +824,6 @@ out_subscribe_ack:
 	ceph_msg_put(monc->m_subscribe_ack);
 out_auth:
 	ceph_auth_destroy(monc->auth);
-out_con:
-	monc->con->ops->put(monc->con);
 out_monmap:
 	kfree(monc->monmap);
 out:
@@ -841,10 +839,6 @@ void ceph_monc_stop(struct ceph_mon_client *monc)
 	mutex_lock(&monc->mutex);
 	__close_session(monc);
 
-	monc->con->private = NULL;
-	monc->con->ops->put(monc->con);
-	monc->con = NULL;
-
 	mutex_unlock(&monc->mutex);
 
 	/*
@@ -888,8 +882,8 @@ static void handle_auth_reply(struct ceph_mon_client *monc,
 	} else if (!was_auth && monc->auth->ops->is_authenticated(monc->auth)) {
 		dout("authenticated, starting session\n");
 
-		monc->client->msgr->inst.name.type = CEPH_ENTITY_TYPE_CLIENT;
-		monc->client->msgr->inst.name.num =
+		monc->client->msgr.inst.name.type = CEPH_ENTITY_TYPE_CLIENT;
+		monc->client->msgr.inst.name.num =
 					cpu_to_le64(monc->auth->global_id);
 
 		__send_subscribe(monc);
@@ -1000,6 +994,8 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 	case CEPH_MSG_MDS_MAP:
 	case CEPH_MSG_OSD_MAP:
 		m = ceph_msg_new(type, front_len, GFP_NOFS, false);
+		if (!m)
+			return NULL;	/* ENOMEM--return skip == 0 */
 		break;
 	}
 
@@ -1029,7 +1025,7 @@ static void mon_fault(struct ceph_connection *con)
 	if (!monc->hunting)
 		pr_info("mon%d %s session lost, "
 			"hunting for new mon\n", monc->cur_mon,
-			ceph_pr_addr(&monc->con->peer_addr.in_addr));
+			ceph_pr_addr(&monc->con.peer_addr.in_addr));
 
 	__close_session(monc);
 	if (!monc->hunting) {
@@ -1044,9 +1040,23 @@ out:
 	mutex_unlock(&monc->mutex);
 }
 
+/*
+ * We can ignore refcounting on the connection struct, as all references
+ * will come from the messenger workqueue, which is drained prior to
+ * mon_client destruction.
+ */
+static struct ceph_connection *con_get(struct ceph_connection *con)
+{
+	return con;
+}
+
+static void con_put(struct ceph_connection *con)
+{
+}
+
 static const struct ceph_connection_operations mon_con_ops = {
-	.get = ceph_con_get,
-	.put = ceph_con_put,
+	.get = con_get,
+	.put = con_put,
 	.dispatch = dispatch,
 	.fault = mon_fault,
 	.alloc_msg = mon_alloc_msg,

net/ceph/msgpool.c

@@ -12,7 +12,7 @@ static void *msgpool_alloc(gfp_t gfp_mask, void *arg)
 	struct ceph_msgpool *pool = arg;
 	struct ceph_msg *msg;
 
-	msg = ceph_msg_new(0, pool->front_len, gfp_mask, true);
+	msg = ceph_msg_new(pool->type, pool->front_len, gfp_mask, true);
 	if (!msg) {
 		dout("msgpool_alloc %s failed\n", pool->name);
 	} else {
@@ -32,10 +32,11 @@ static void msgpool_free(void *element, void *arg)
 	ceph_msg_put(msg);
 }
 
-int ceph_msgpool_init(struct ceph_msgpool *pool,
+int ceph_msgpool_init(struct ceph_msgpool *pool, int type,
 		      int front_len, int size, bool blocking, const char *name)
 {
 	dout("msgpool %s init\n", name);
+	pool->type = type;
 	pool->front_len = front_len;
 	pool->pool = mempool_create(size, msgpool_alloc, msgpool_free, pool);
 	if (!pool->pool)
@@ -61,7 +62,7 @@ struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool,
 		WARN_ON(1);
 
 		/* try to alloc a fresh message */
-		return ceph_msg_new(0, front_len, GFP_NOFS, false);
+		return ceph_msg_new(pool->type, front_len, GFP_NOFS, false);
 	}
 
 	msg = mempool_alloc(pool->pool, GFP_NOFS);

net/ceph/osd_client.c

@@ -140,10 +140,9 @@ void ceph_osdc_release_request(struct kref *kref)
 	if (req->r_request)
 		ceph_msg_put(req->r_request);
 	if (req->r_con_filling_msg) {
-		dout("release_request revoking pages %p from con %p\n",
+		dout("%s revoking pages %p from con %p\n", __func__,
 		     req->r_pages, req->r_con_filling_msg);
-		ceph_con_revoke_message(req->r_con_filling_msg,
-				      req->r_reply);
+		ceph_msg_revoke_incoming(req->r_reply);
 		req->r_con_filling_msg->ops->put(req->r_con_filling_msg);
 	}
 	if (req->r_reply)
@@ -214,10 +213,13 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 	kref_init(&req->r_kref);
 	init_completion(&req->r_completion);
 	init_completion(&req->r_safe_completion);
+	rb_init_node(&req->r_node);
 	INIT_LIST_HEAD(&req->r_unsafe_item);
 	INIT_LIST_HEAD(&req->r_linger_item);
 	INIT_LIST_HEAD(&req->r_linger_osd);
 	INIT_LIST_HEAD(&req->r_req_lru_item);
+	INIT_LIST_HEAD(&req->r_osd_item);
+
 	req->r_flags = flags;
 
 	WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0);
@@ -243,6 +245,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 		}
 		ceph_pagelist_init(req->r_trail);
 	}
+
 	/* create request message; allow space for oid */
 	msg_size += MAX_OBJ_NAME_SIZE;
 	if (snapc)
@@ -256,7 +259,6 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 		return NULL;
 	}
 
-	msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP);
 	memset(msg->front.iov_base, 0, msg->front.iov_len);
 
 	req->r_request = msg;
@@ -624,7 +626,7 @@ static void osd_reset(struct ceph_connection *con)
 /*
  * Track open sessions with osds.
  */
-static struct ceph_osd *create_osd(struct ceph_osd_client *osdc)
+static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
 {
 	struct ceph_osd *osd;
 
@@ -634,15 +636,13 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc)
 
 	atomic_set(&osd->o_ref, 1);
 	osd->o_osdc = osdc;
+	osd->o_osd = onum;
 	INIT_LIST_HEAD(&osd->o_requests);
 	INIT_LIST_HEAD(&osd->o_linger_requests);
 	INIT_LIST_HEAD(&osd->o_osd_lru);
 	osd->o_incarnation = 1;
 
-	ceph_con_init(osdc->client->msgr, &osd->o_con);
-	osd->o_con.private = osd;
-	osd->o_con.ops = &osd_con_ops;
-	osd->o_con.peer_name.type = CEPH_ENTITY_TYPE_OSD;
+	ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr);
 
 	INIT_LIST_HEAD(&osd->o_keepalive_item);
 	return osd;
@@ -688,7 +688,7 @@ static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
 
 static void remove_all_osds(struct ceph_osd_client *osdc)
 {
-	dout("__remove_old_osds %p\n", osdc);
+	dout("%s %p\n", __func__, osdc);
 	mutex_lock(&osdc->request_mutex);
 	while (!RB_EMPTY_ROOT(&osdc->osds)) {
 		struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
@@ -752,7 +752,8 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
 		ret = -EAGAIN;
 	} else {
 		ceph_con_close(&osd->o_con);
-		ceph_con_open(&osd->o_con, &osdc->osdmap->osd_addr[osd->o_osd]);
+		ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd,
+			      &osdc->osdmap->osd_addr[osd->o_osd]);
 		osd->o_incarnation++;
 	}
 	return ret;
@@ -853,7 +854,7 @@ static void __unregister_request(struct ceph_osd_client *osdc,
 
 	if (req->r_osd) {
 		/* make sure the original request isn't in flight. */
-		ceph_con_revoke(&req->r_osd->o_con, req->r_request);
+		ceph_msg_revoke(req->r_request);
 
 		list_del_init(&req->r_osd_item);
 		if (list_empty(&req->r_osd->o_requests) &&
@@ -880,7 +881,7 @@ static void __unregister_request(struct ceph_osd_client *osdc,
 static void __cancel_request(struct ceph_osd_request *req)
 {
 	if (req->r_sent && req->r_osd) {
-		ceph_con_revoke(&req->r_osd->o_con, req->r_request);
+		ceph_msg_revoke(req->r_request);
 		req->r_sent = 0;
 	}
 }
@@ -890,7 +891,9 @@ static void __register_linger_request(struct ceph_osd_client *osdc,
 {
 	dout("__register_linger_request %p\n", req);
 	list_add_tail(&req->r_linger_item, &osdc->req_linger);
-	list_add_tail(&req->r_linger_osd, &req->r_osd->o_linger_requests);
+	if (req->r_osd)
+		list_add_tail(&req->r_linger_osd,
+			      &req->r_osd->o_linger_requests);
 }
 
 static void __unregister_linger_request(struct ceph_osd_client *osdc,
@@ -998,18 +1001,18 @@ static int __map_request(struct ceph_osd_client *osdc,
 	req->r_osd = __lookup_osd(osdc, o);
 	if (!req->r_osd && o >= 0) {
 		err = -ENOMEM;
-		req->r_osd = create_osd(osdc);
+		req->r_osd = create_osd(osdc, o);
 		if (!req->r_osd) {
 			list_move(&req->r_req_lru_item, &osdc->req_notarget);
 			goto out;
 		}
 
 		dout("map_request osd %p is osd%d\n", req->r_osd, o);
-		req->r_osd->o_osd = o;
-		req->r_osd->o_con.peer_name.num = cpu_to_le64(o);
 		__insert_osd(osdc, req->r_osd);
 
-		ceph_con_open(&req->r_osd->o_con, &osdc->osdmap->osd_addr[o]);
+		ceph_con_open(&req->r_osd->o_con,
+			      CEPH_ENTITY_TYPE_OSD, o,
+			      &osdc->osdmap->osd_addr[o]);
 	}
 
 	if (req->r_osd) {
@@ -1304,8 +1307,9 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 
 	dout("kick_requests %s\n", force_resend ? " (force resend)" : "");
 	mutex_lock(&osdc->request_mutex);
-	for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
+	for (p = rb_first(&osdc->requests); p; ) {
 		req = rb_entry(p, struct ceph_osd_request, r_node);
+		p = rb_next(p);
 		err = __map_request(osdc, req, force_resend);
 		if (err < 0)
 			continue;  /* error */
@@ -1313,10 +1317,23 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 			dout("%p tid %llu maps to no osd\n", req, req->r_tid);
 			needmap++;  /* request a newer map */
 		} else if (err > 0) {
-			dout("%p tid %llu requeued on osd%d\n", req, req->r_tid,
-			     req->r_osd ? req->r_osd->o_osd : -1);
-			if (!req->r_linger)
+			if (!req->r_linger) {
+				dout("%p tid %llu requeued on osd%d\n", req,
+				     req->r_tid,
+				     req->r_osd ? req->r_osd->o_osd : -1);
 				req->r_flags |= CEPH_OSD_FLAG_RETRY;
+			}
+		}
+		if (req->r_linger && list_empty(&req->r_linger_item)) {
+			/*
+			 * register as a linger so that we will
+			 * re-submit below and get a new tid
+			 */
+			dout("%p tid %llu restart on osd%d\n",
+			     req, req->r_tid,
+			     req->r_osd ? req->r_osd->o_osd : -1);
+			__register_linger_request(osdc, req);
+			__unregister_request(osdc, req);
 		}
 	}
 
@@ -1391,7 +1408,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 			     epoch, maplen);
 			newmap = osdmap_apply_incremental(&p, next,
 							  osdc->osdmap,
-							  osdc->client->msgr);
+							  &osdc->client->msgr);
 			if (IS_ERR(newmap)) {
 				err = PTR_ERR(newmap);
 				goto bad;
@@ -1839,11 +1856,12 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
 	if (!osdc->req_mempool)
 		goto out;
 
-	err = ceph_msgpool_init(&osdc->msgpool_op, OSD_OP_FRONT_LEN, 10, true,
+	err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP,
+				OSD_OP_FRONT_LEN, 10, true,
 				"osd_op");
 	if (err < 0)
 		goto out_mempool;
-	err = ceph_msgpool_init(&osdc->msgpool_op_reply,
+	err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY,
 				OSD_OPREPLY_FRONT_LEN, 10, true,
 				"osd_op_reply");
 	if (err < 0)
@@ -2019,15 +2037,15 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	if (!req) {
 		*skip = 1;
 		m = NULL;
-		pr_info("get_reply unknown tid %llu from osd%d\n", tid,
-			osd->o_osd);
+		dout("get_reply unknown tid %llu from osd%d\n", tid,
+		     osd->o_osd);
 		goto out;
 	}
 
 	if (req->r_con_filling_msg) {
-		dout("get_reply revoking msg %p from old con %p\n",
+		dout("%s revoking msg %p from old con %p\n", __func__,
 		     req->r_reply, req->r_con_filling_msg);
-		ceph_con_revoke_message(req->r_con_filling_msg, req->r_reply);
+		ceph_msg_revoke_incoming(req->r_reply);
 		req->r_con_filling_msg->ops->put(req->r_con_filling_msg);
 		req->r_con_filling_msg = NULL;
 	}
@@ -2080,6 +2098,7 @@ static struct ceph_msg *alloc_msg(struct ceph_connection *con,
 	int type = le16_to_cpu(hdr->type);
 	int front = le32_to_cpu(hdr->front_len);
 
+	*skip = 0;
 	switch (type) {
 	case CEPH_MSG_OSD_MAP:
 	case CEPH_MSG_WATCH_NOTIFY:

net/ceph/osdmap.c

@@ -135,6 +135,21 @@ bad:
 	return -EINVAL;
 }
 
+static int skip_name_map(void **p, void *end)
+{
+        int len;
+        ceph_decode_32_safe(p, end, len ,bad);
+        while (len--) {
+                int strlen;
+                *p += sizeof(u32);
+                ceph_decode_32_safe(p, end, strlen, bad);
+                *p += strlen;
+}
+        return 0;
+bad:
+        return -EINVAL;
+}
+
 static struct crush_map *crush_decode(void *pbyval, void *end)
 {
 	struct crush_map *c;
@@ -143,6 +158,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	void **p = &pbyval;
 	void *start = pbyval;
 	u32 magic;
+	u32 num_name_maps;
 
 	dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p));
 
@@ -150,6 +166,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	if (c == NULL)
 		return ERR_PTR(-ENOMEM);
 
+        /* set tunables to default values */
+        c->choose_local_tries = 2;
+        c->choose_local_fallback_tries = 5;
+        c->choose_total_tries = 19;
+
 	ceph_decode_need(p, end, 4*sizeof(u32), bad);
 	magic = ceph_decode_32(p);
 	if (magic != CRUSH_MAGIC) {
@@ -297,7 +318,25 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	}
 
 	/* ignore trailing name maps. */
+        for (num_name_maps = 0; num_name_maps < 3; num_name_maps++) {
+                err = skip_name_map(p, end);
+                if (err < 0)
+                        goto done;
+        }
 
+        /* tunables */
+        ceph_decode_need(p, end, 3*sizeof(u32), done);
+        c->choose_local_tries = ceph_decode_32(p);
+        c->choose_local_fallback_tries =  ceph_decode_32(p);
+        c->choose_total_tries = ceph_decode_32(p);
+        dout("crush decode tunable choose_local_tries = %d",
+             c->choose_local_tries);
+        dout("crush decode tunable choose_local_fallback_tries = %d",
+             c->choose_local_fallback_tries);
+        dout("crush decode tunable choose_total_tries = %d",
+             c->choose_total_tries);
+
+done:
 	dout("crush_decode success\n");
 	return c;
 
@@ -488,15 +527,16 @@ static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
 		ceph_decode_32_safe(p, end, pool, bad);
 		ceph_decode_32_safe(p, end, len, bad);
 		dout("  pool %d len %d\n", pool, len);
+		ceph_decode_need(p, end, len, bad);
 		pi = __lookup_pg_pool(&map->pg_pools, pool);
 		if (pi) {
+			char *name = kstrndup(*p, len, GFP_NOFS);
+
+			if (!name)
+				return -ENOMEM;
 			kfree(pi->name);
-			pi->name = kmalloc(len + 1, GFP_NOFS);
-			if (pi->name) {
-				memcpy(pi->name, *p, len);
-				pi->name[len] = '\0';
-				dout("  name is %s\n", pi->name);
-			}
+			pi->name = name;
+			dout("  name is %s\n", pi->name);
 		}
 		*p += len;
 	}
@@ -666,6 +706,9 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
 		ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad);
 		ceph_decode_copy(p, &pgid, sizeof(pgid));
 		n = ceph_decode_32(p);
+		err = -EINVAL;
+		if (n > (UINT_MAX - sizeof(*pg)) / sizeof(u32))
+			goto bad;
 		ceph_decode_need(p, end, n * sizeof(u32), bad);
 		err = -ENOMEM;
 		pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS);
@@ -889,6 +932,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 			(void) __remove_pg_mapping(&map->pg_temp, pgid);
 
 			/* insert */
+			if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) {
+				err = -EINVAL;
+				goto bad;
+			}
 			pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS);
 			if (!pg) {
 				err = -ENOMEM;

net/core/dev.c

@@ -1172,6 +1172,7 @@ static int __dev_open(struct net_device *dev)
 		net_dmaengine_get();
 		dev_set_rx_mode(dev);
 		dev_activate(dev);
+		add_device_randomness(dev->dev_addr, dev->addr_len);
 	}
 
 	return ret;
@@ -2133,6 +2134,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 	__be16 protocol = skb->protocol;
 	netdev_features_t features = skb->dev->features;
 
+	if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+		features &= ~NETIF_F_GSO_MASK;
+
 	if (protocol == htons(ETH_P_8021Q)) {
 		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
@@ -3155,6 +3159,23 @@ void netdev_rx_handler_unregister(struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
 
+/*
+ * Limit the use of PFMEMALLOC reserves to those protocols that implement
+ * the special handling of PFMEMALLOC skbs.
+ */
+static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
+{
+	switch (skb->protocol) {
+	case __constant_htons(ETH_P_ARP):
+	case __constant_htons(ETH_P_IP):
+	case __constant_htons(ETH_P_IPV6):
+	case __constant_htons(ETH_P_8021Q):
+		return true;
+	default:
+		return false;
+	}
+}
+
 static int __netif_receive_skb(struct sk_buff *skb)
 {
 	struct packet_type *ptype, *pt_prev;
@@ -3164,14 +3185,27 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	bool deliver_exact = false;
 	int ret = NET_RX_DROP;
 	__be16 type;
+	unsigned long pflags = current->flags;
 
 	net_timestamp_check(!netdev_tstamp_prequeue, skb);
 
 	trace_netif_receive_skb(skb);
 
+	/*
+	 * PFMEMALLOC skbs are special, they should
+	 * - be delivered to SOCK_MEMALLOC sockets only
+	 * - stay away from userspace
+	 * - have bounded memory usage
+	 *
+	 * Use PF_MEMALLOC as this saves us from propagating the allocation
+	 * context down to all allocation sites.
+	 */
+	if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+		current->flags |= PF_MEMALLOC;
+
 	/* if we've gotten here through NAPI, check netpoll */
 	if (netpoll_receive_skb(skb))
-		return NET_RX_DROP;
+		goto out;
 
 	orig_dev = skb->dev;
 
@@ -3191,7 +3225,7 @@ another_round:
 	if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
 		skb = vlan_untag(skb);
 		if (unlikely(!skb))
-			goto out;
+			goto unlock;
 	}
 
 #ifdef CONFIG_NET_CLS_ACT
@@ -3201,6 +3235,9 @@ another_round:
 	}
 #endif
 
+	if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+		goto skip_taps;
+
 	list_for_each_entry_rcu(ptype, &ptype_all, list) {
 		if (!ptype->dev || ptype->dev == skb->dev) {
 			if (pt_prev)
@@ -3209,13 +3246,18 @@ another_round:
 		}
 	}
 
+skip_taps:
 #ifdef CONFIG_NET_CLS_ACT
 	skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
 	if (!skb)
-		goto out;
+		goto unlock;
 ncls:
 #endif
 
+	if (sk_memalloc_socks() && skb_pfmemalloc(skb)
+				&& !skb_pfmemalloc_protocol(skb))
+		goto drop;
+
 	rx_handler = rcu_dereference(skb->dev->rx_handler);
 	if (vlan_tx_tag_present(skb)) {
 		if (pt_prev) {
@@ -3225,7 +3267,7 @@ ncls:
 		if (vlan_do_receive(&skb, !rx_handler))
 			goto another_round;
 		else if (unlikely(!skb))
-			goto out;
+			goto unlock;
 	}
 
 	if (rx_handler) {
@@ -3235,7 +3277,7 @@ ncls:
 		}
 		switch (rx_handler(&skb)) {
 		case RX_HANDLER_CONSUMED:
-			goto out;
+			goto unlock;
 		case RX_HANDLER_ANOTHER:
 			goto another_round;
 		case RX_HANDLER_EXACT:
@@ -3268,6 +3310,7 @@ ncls:
 		else
 			ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
 	} else {
+drop:
 		atomic_long_inc(&skb->dev->rx_dropped);
 		kfree_skb(skb);
 		/* Jamal, now you will not able to escape explaining
@@ -3276,8 +3319,10 @@ ncls:
 		ret = NET_RX_DROP;
 	}
 
-out:
+unlock:
 	rcu_read_unlock();
+out:
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 	return ret;
 }
 
@@ -4801,6 +4846,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
 	err = ops->ndo_set_mac_address(dev, sa);
 	if (!err)
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+	add_device_randomness(dev->dev_addr, dev->addr_len);
 	return err;
 }
 EXPORT_SYMBOL(dev_set_mac_address);
@@ -5579,6 +5625,7 @@ int register_netdevice(struct net_device *dev)
 	dev_init_scheduler(dev);
 	dev_hold(dev);
 	list_netdevice(dev);
+	add_device_randomness(dev->dev_addr, dev->addr_len);
 
 	/* Notify protocols, that a new device appeared. */
 	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
@@ -5942,6 +5989,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev_net_set(dev, &init_net);
 
 	dev->gso_max_size = GSO_MAX_SIZE;
+	dev->gso_max_segs = GSO_MAX_SEGS;
 
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);

net/core/filter.c

@@ -83,6 +83,14 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
 	int err;
 	struct sk_filter *filter;
 
+	/*
+	 * If the skb was allocated from pfmemalloc reserves, only
+	 * allow SOCK_MEMALLOC sockets to use it as this socket is
+	 * helping free memory
+	 */
+	if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
+		return -ENOMEM;
+
 	err = security_sock_rcv_skb(sk, skb);
 	if (err)
 		return err;

net/core/rtnetlink.c

@@ -1381,6 +1381,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 			goto errout;
 		send_addr_notify = 1;
 		modified = 1;
+		add_device_randomness(dev->dev_addr, dev->addr_len);
 	}
 
 	if (tb[IFLA_MTU]) {

net/core/skbuff.c

@@ -145,6 +145,43 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
 	BUG();
 }
 
+
+/*
+ * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells
+ * the caller if emergency pfmemalloc reserves are being used. If it is and
+ * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves
+ * may be used. Otherwise, the packet data may be discarded until enough
+ * memory is free
+ */
+#define kmalloc_reserve(size, gfp, node, pfmemalloc) \
+	 __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc)
+void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip,
+			 bool *pfmemalloc)
+{
+	void *obj;
+	bool ret_pfmemalloc = false;
+
+	/*
+	 * Try a regular allocation, when that fails and we're not entitled
+	 * to the reserves, fail.
+	 */
+	obj = kmalloc_node_track_caller(size,
+					flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
+					node);
+	if (obj || !(gfp_pfmemalloc_allowed(flags)))
+		goto out;
+
+	/* Try again but now we are using pfmemalloc reserves */
+	ret_pfmemalloc = true;
+	obj = kmalloc_node_track_caller(size, flags, node);
+
+out:
+	if (pfmemalloc)
+		*pfmemalloc = ret_pfmemalloc;
+
+	return obj;
+}
+
 /* 	Allocate a new skbuff. We do this ourselves so we can fill in a few
  *	'private' fields and also do memory statistics to find all the
  *	[BEEP] leaks.
@@ -155,8 +192,10 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
  *	__alloc_skb	-	allocate a network buffer
  *	@size: size to allocate
  *	@gfp_mask: allocation mask
- *	@fclone: allocate from fclone cache instead of head cache
- *		and allocate a cloned (child) skb
+ *	@flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache
+ *		instead of head cache and allocate a cloned (child) skb.
+ *		If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
+ *		allocations in case the data is required for writeback
  *	@node: numa node to allocate memory on
  *
  *	Allocate a new &sk_buff. The returned buffer has no headroom and a
@@ -167,14 +206,19 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
  *	%GFP_ATOMIC.
  */
 struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
-			    int fclone, int node)
+			    int flags, int node)
 {
 	struct kmem_cache *cache;
 	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
 	u8 *data;
+	bool pfmemalloc;
 
-	cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;
+	cache = (flags & SKB_ALLOC_FCLONE)
+		? skbuff_fclone_cache : skbuff_head_cache;
+
+	if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX))
+		gfp_mask |= __GFP_MEMALLOC;
 
 	/* Get the HEAD */
 	skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
@@ -189,7 +233,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	 */
 	size = SKB_DATA_ALIGN(size);
 	size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	data = kmalloc_node_track_caller(size, gfp_mask, node);
+	data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc);
 	if (!data)
 		goto nodata;
 	/* kmalloc(size) might give us more room than requested.
@@ -207,6 +251,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	/* Account for allocated memory : skb + skb->head */
 	skb->truesize = SKB_TRUESIZE(size);
+	skb->pfmemalloc = pfmemalloc;
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -222,7 +267,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	atomic_set(&shinfo->dataref, 1);
 	kmemcheck_annotate_variable(shinfo->destructor_arg);
 
-	if (fclone) {
+	if (flags & SKB_ALLOC_FCLONE) {
 		struct sk_buff *child = skb + 1;
 		atomic_t *fclone_ref = (atomic_t *) (child + 1);
 
@@ -232,6 +277,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 		atomic_set(fclone_ref, 1);
 
 		child->fclone = SKB_FCLONE_UNAVAILABLE;
+		child->pfmemalloc = pfmemalloc;
 	}
 out:
 	return skb;
@@ -302,14 +348,7 @@ static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
 
 #define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES)
 
-/**
- * netdev_alloc_frag - allocate a page fragment
- * @fragsz: fragment size
- *
- * Allocates a frag from a page for receive buffer.
- * Uses GFP_ATOMIC allocations.
- */
-void *netdev_alloc_frag(unsigned int fragsz)
+static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 {
 	struct netdev_alloc_cache *nc;
 	void *data = NULL;
@@ -319,7 +358,7 @@ void *netdev_alloc_frag(unsigned int fragsz)
 	nc = &__get_cpu_var(netdev_alloc_cache);
 	if (unlikely(!nc->page)) {
 refill:
-		nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+		nc->page = alloc_page(gfp_mask);
 		if (unlikely(!nc->page))
 			goto end;
 recycle:
@@ -343,6 +382,18 @@ end:
 	local_irq_restore(flags);
 	return data;
 }
+
+/**
+ * netdev_alloc_frag - allocate a page fragment
+ * @fragsz: fragment size
+ *
+ * Allocates a frag from a page for receive buffer.
+ * Uses GFP_ATOMIC allocations.
+ */
+void *netdev_alloc_frag(unsigned int fragsz)
+{
+	return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
+}
 EXPORT_SYMBOL(netdev_alloc_frag);
 
 /**
@@ -366,7 +417,12 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
 			      SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) {
-		void *data = netdev_alloc_frag(fragsz);
+		void *data;
+
+		if (sk_memalloc_socks())
+			gfp_mask |= __GFP_MEMALLOC;
+
+		data = __netdev_alloc_frag(fragsz, gfp_mask);
 
 		if (likely(data)) {
 			skb = build_skb(data, fragsz);
@@ -374,7 +430,8 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
 				put_page(virt_to_head_page(data));
 		}
 	} else {
-		skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE);
+		skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
+				  SKB_ALLOC_RX, NUMA_NO_NODE);
 	}
 	if (likely(skb)) {
 		skb_reserve(skb, NET_SKB_PAD);
@@ -656,6 +713,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 #if IS_ENABLED(CONFIG_IP_VS)
 	new->ipvs_property	= old->ipvs_property;
 #endif
+	new->pfmemalloc		= old->pfmemalloc;
 	new->protocol		= old->protocol;
 	new->mark		= old->mark;
 	new->skb_iif		= old->skb_iif;
@@ -814,6 +872,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 		n->fclone = SKB_FCLONE_CLONE;
 		atomic_inc(fclone_ref);
 	} else {
+		if (skb_pfmemalloc(skb))
+			gfp_mask |= __GFP_MEMALLOC;
+
 		n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);
 		if (!n)
 			return NULL;
@@ -850,6 +911,13 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
 }
 
+static inline int skb_alloc_rx_flag(const struct sk_buff *skb)
+{
+	if (skb_pfmemalloc(skb))
+		return SKB_ALLOC_RX;
+	return 0;
+}
+
 /**
  *	skb_copy	-	create private copy of an sk_buff
  *	@skb: buffer to copy
@@ -871,7 +939,8 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
 {
 	int headerlen = skb_headroom(skb);
 	unsigned int size = skb_end_offset(skb) + skb->data_len;
-	struct sk_buff *n = alloc_skb(size, gfp_mask);
+	struct sk_buff *n = __alloc_skb(size, gfp_mask,
+					skb_alloc_rx_flag(skb), NUMA_NO_NODE);
 
 	if (!n)
 		return NULL;
@@ -906,7 +975,8 @@ EXPORT_SYMBOL(skb_copy);
 struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
 {
 	unsigned int size = skb_headlen(skb) + headroom;
-	struct sk_buff *n = alloc_skb(size, gfp_mask);
+	struct sk_buff *n = __alloc_skb(size, gfp_mask,
+					skb_alloc_rx_flag(skb), NUMA_NO_NODE);
 
 	if (!n)
 		goto out;
@@ -979,8 +1049,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 
 	size = SKB_DATA_ALIGN(size);
 
-	data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
-		       gfp_mask);
+	if (skb_pfmemalloc(skb))
+		gfp_mask |= __GFP_MEMALLOC;
+	data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
+			       gfp_mask, NUMA_NO_NODE, NULL);
 	if (!data)
 		goto nodata;
 	size = SKB_WITH_OVERHEAD(ksize(data));
@@ -1092,8 +1164,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 	/*
 	 *	Allocate the copy buffer
 	 */
-	struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
-				      gfp_mask);
+	struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom,
+					gfp_mask, skb_alloc_rx_flag(skb),
+					NUMA_NO_NODE);
 	int oldheadroom = skb_headroom(skb);
 	int head_copy_len, head_copy_off;
 	int off;
@@ -2775,8 +2848,9 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 			skb_release_head_state(nskb);
 			__skb_push(nskb, doffset);
 		} else {
-			nskb = alloc_skb(hsize + doffset + headroom,
-					 GFP_ATOMIC);
+			nskb = __alloc_skb(hsize + doffset + headroom,
+					   GFP_ATOMIC, skb_alloc_rx_flag(skb),
+					   NUMA_NO_NODE);
 
 			if (unlikely(!nskb))
 				goto err;

net/core/sock.c

@@ -142,7 +142,7 @@
 static DEFINE_MUTEX(proto_list_mutex);
 static LIST_HEAD(proto_list);
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	struct proto *proto;
@@ -271,6 +271,61 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
 EXPORT_SYMBOL(sysctl_optmem_max);
 
+struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE;
+EXPORT_SYMBOL_GPL(memalloc_socks);
+
+/**
+ * sk_set_memalloc - sets %SOCK_MEMALLOC
+ * @sk: socket to set it on
+ *
+ * Set %SOCK_MEMALLOC on a socket for access to emergency reserves.
+ * It's the responsibility of the admin to adjust min_free_kbytes
+ * to meet the requirements
+ */
+void sk_set_memalloc(struct sock *sk)
+{
+	sock_set_flag(sk, SOCK_MEMALLOC);
+	sk->sk_allocation |= __GFP_MEMALLOC;
+	static_key_slow_inc(&memalloc_socks);
+}
+EXPORT_SYMBOL_GPL(sk_set_memalloc);
+
+void sk_clear_memalloc(struct sock *sk)
+{
+	sock_reset_flag(sk, SOCK_MEMALLOC);
+	sk->sk_allocation &= ~__GFP_MEMALLOC;
+	static_key_slow_dec(&memalloc_socks);
+
+	/*
+	 * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
+	 * progress of swapping. However, if SOCK_MEMALLOC is cleared while
+	 * it has rmem allocations there is a risk that the user of the
+	 * socket cannot make forward progress due to exceeding the rmem
+	 * limits. By rights, sk_clear_memalloc() should only be called
+	 * on sockets being torn down but warn and reset the accounting if
+	 * that assumption breaks.
+	 */
+	if (WARN_ON(sk->sk_forward_alloc))
+		sk_mem_reclaim(sk);
+}
+EXPORT_SYMBOL_GPL(sk_clear_memalloc);
+
+int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+{
+	int ret;
+	unsigned long pflags = current->flags;
+
+	/* these should have been dropped before queueing */
+	BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));
+
+	current->flags |= PF_MEMALLOC;
+	ret = sk->sk_backlog_rcv(sk, skb);
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
+
+	return ret;
+}
+EXPORT_SYMBOL(__sk_backlog_rcv);
+
 #if defined(CONFIG_CGROUPS)
 #if !defined(CONFIG_NET_CLS_CGROUP)
 int net_cls_subsys_id = -1;
@@ -353,7 +408,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if (err)
 		return err;
 
-	if (!sk_rmem_schedule(sk, skb->truesize)) {
+	if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
 		atomic_inc(&sk->sk_drops);
 		return -ENOBUFS;
 	}
@@ -1403,6 +1458,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 		} else {
 			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
 			sk->sk_gso_max_size = dst->dev->gso_max_size;
+			sk->sk_gso_max_segs = dst->dev->gso_max_segs;
 		}
 	}
 }

net/ipv4/Makefile

@@ -49,7 +49,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
 obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
 obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
 obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
-obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o
+obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o
 obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
 
 obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \