Treewide: Stop corrupting socket's task_frag

Since moving to memalloc_nofs_save/restore, SUNRPC has stopped setting the
GFP_NOIO flag on sk_allocation which the networking system uses to decide
when it is safe to use current->task_frag.  The results of this are
unexpected corruption in task_frag when SUNRPC is involved in memory
reclaim.

The corruption can be seen in crashes, but the root cause is often
difficult to ascertain as a crashing machine's stack trace will have no
evidence of being near NFS or SUNRPC code.  I believe this problem to
be much more pervasive than reports to the community may indicate.

Fix this by having kernel users of sockets that may corrupt task_frag due
to reclaim set sk_use_task_frag = false.  Preemptively correcting this
situation for users that still set sk_allocation allows them to convert to
memalloc_nofs_save/restore without the same unexpected corruptions that are
sure to follow, unlikely to show up in testing, and difficult to bisect.

CC: Philipp Reisner <[email protected]>
CC: Lars Ellenberg <[email protected]>
CC: "Christoph Böhmwalder" <[email protected]>
CC: Jens Axboe <[email protected]>
CC: Josef Bacik <[email protected]>
CC: Keith Busch <[email protected]>
CC: Christoph Hellwig <[email protected]>
CC: Sagi Grimberg <[email protected]>
CC: Lee Duncan <[email protected]>
CC: Chris Leech <[email protected]>
CC: Mike Christie <[email protected]>
CC: "James E.J. Bottomley" <[email protected]>
CC: "Martin K. Petersen" <[email protected]>
CC: Valentina Manea <[email protected]>
CC: Shuah Khan <[email protected]>
CC: Greg Kroah-Hartman <[email protected]>
CC: David Howells <[email protected]>
CC: Marc Dionne <[email protected]>
CC: Steve French <[email protected]>
CC: Christine Caulfield <[email protected]>
CC: David Teigland <[email protected]>
CC: Mark Fasheh <[email protected]>
CC: Joel Becker <[email protected]>
CC: Joseph Qi <[email protected]>
CC: Eric Van Hensbergen <[email protected]>
CC: Latchesar Ionkov <[email protected]>
CC: Dominique Martinet <[email protected]>
CC: Ilya Dryomov <[email protected]>
CC: Xiubo Li <[email protected]>
CC: Chuck Lever <[email protected]>
CC: Jeff Layton <[email protected]>
CC: Trond Myklebust <[email protected]>
CC: Anna Schumaker <[email protected]>
CC: Steffen Klassert <[email protected]>
CC: Herbert Xu <[email protected]>

Suggested-by: Guillaume Nault <[email protected]>
Signed-off-by: Benjamin Coddington <[email protected]>
Reviewed-by: Guillaume Nault <[email protected]>
Signed-off-by: Jakub Kicinski <[email protected]>

Author: bcodding-rh

drivers/block/drbd/drbd_receiver.c

@@ -1030,6 +1030,9 @@ static int conn_connect(struct drbd_connection *connection)
 	sock.socket->sk->sk_allocation = GFP_NOIO;
 	msock.socket->sk->sk_allocation = GFP_NOIO;
 
+	sock.socket->sk->sk_use_task_frag = false;
+	msock.socket->sk->sk_use_task_frag = false;
+
 	sock.socket->sk->sk_priority = TC_PRIO_INTERACTIVE_BULK;
 	msock.socket->sk->sk_priority = TC_PRIO_INTERACTIVE;
 

drivers/block/nbd.c

@@ -512,6 +512,7 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
 	noreclaim_flag = memalloc_noreclaim_save();
 	do {
 		sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
+		sock->sk->sk_use_task_frag = false;
 		msg.msg_name = NULL;
 		msg.msg_namelen = 0;
 		msg.msg_control = NULL;

drivers/nvme/host/tcp.c

@@ -1537,6 +1537,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid)
 	queue->sock->sk->sk_rcvtimeo = 10 * HZ;
 
 	queue->sock->sk->sk_allocation = GFP_ATOMIC;
+	queue->sock->sk->sk_use_task_frag = false;
 	nvme_tcp_set_queue_io_cpu(queue);
 	queue->request = NULL;
 	queue->data_remaining = 0;

drivers/scsi/iscsi_tcp.c

@@ -738,6 +738,7 @@ iscsi_sw_tcp_conn_bind(struct iscsi_cls_session *cls_session,
 	sk->sk_reuse = SK_CAN_REUSE;
 	sk->sk_sndtimeo = 15 * HZ; /* FIXME: make it configurable */
 	sk->sk_allocation = GFP_ATOMIC;
+	sk->sk_use_task_frag = false;
 	sk_set_memalloc(sk);
 	sock_no_linger(sk);
 

drivers/usb/usbip/usbip_common.c

@@ -315,6 +315,7 @@ int usbip_recv(struct socket *sock, void *buf, int size)
 
 	do {
 		sock->sk->sk_allocation = GFP_NOIO;
+		sock->sk->sk_use_task_frag = false;
 
 		result = sock_recvmsg(sock, &msg, MSG_WAITALL);
 		if (result <= 0)

fs/cifs/connect.c

@@ -2944,6 +2944,7 @@ generic_ip_connect(struct TCP_Server_Info *server)
 		cifs_dbg(FYI, "Socket created\n");
 		server->ssocket = socket;
 		socket->sk->sk_allocation = GFP_NOFS;
+		socket->sk->sk_use_task_frag = false;
 		if (sfamily == AF_INET6)
 			cifs_reclassify_socket6(socket);
 		else

fs/dlm/lowcomms.c

@@ -645,6 +645,7 @@ static void add_sock(struct socket *sock, struct connection *con)
 	if (dlm_config.ci_protocol == DLM_PROTO_SCTP)
 		sk->sk_state_change = lowcomms_state_change;
 	sk->sk_allocation = GFP_NOFS;
+	sk->sk_use_task_frag = false;
 	sk->sk_error_report = lowcomms_error_report;
 	release_sock(sk);
 }
@@ -1769,6 +1770,7 @@ static int dlm_listen_for_all(void)
 	listen_con.sock = sock;
 
 	sock->sk->sk_allocation = GFP_NOFS;
+	sock->sk->sk_use_task_frag = false;
 	sock->sk->sk_data_ready = lowcomms_listen_data_ready;
 	release_sock(sock->sk);
 

fs/ocfs2/cluster/tcp.c

@@ -1602,6 +1602,7 @@ static void o2net_start_connect(struct work_struct *work)
 	sc->sc_sock = sock; /* freed by sc_kref_release */
 
 	sock->sk->sk_allocation = GFP_ATOMIC;
+	sock->sk->sk_use_task_frag = false;
 
 	myaddr.sin_family = AF_INET;
 	myaddr.sin_addr.s_addr = mynode->nd_ipv4_address;

net/9p/trans_fd.c

@@ -868,6 +868,7 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket)
 	}
 
 	csocket->sk->sk_allocation = GFP_NOIO;
+	csocket->sk->sk_use_task_frag = false;
 	file = sock_alloc_file(csocket, 0, NULL);
 	if (IS_ERR(file)) {
 		pr_err("%s (%d): failed to map fd\n",

net/ceph/messenger.c

@@ -446,6 +446,7 @@ int ceph_tcp_connect(struct ceph_connection *con)
 	if (ret)
 		return ret;
 	sock->sk->sk_allocation = GFP_NOFS;
+	sock->sk->sk_use_task_frag = false;
 
 #ifdef CONFIG_LOCKDEP
 	lockdep_set_class(&sock->sk->sk_lock, &socket_class);