Merge branch 'stop-corrupting-socket-s-task_frag'

Benjamin Coddington says:

====================
Stop corrupting socket's task_frag

The networking code uses flags in sk_allocation to determine if it can use
current->task_frag, however in-kernel users of sockets may stop setting
sk_allocation when they convert to the preferred memalloc_nofs_save/restore,
as SUNRPC has done in commit a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save()
on all rpciod/xprtiod jobs").

This will cause corruption in current->task_frag when recursing into the
network layer for those subsystems during page fault or reclaim.  The
corruption is difficult to diagnose because stack traces may not contain the
offending subsystem at all.  The corruption is unlikely to show up in
testing because it requires memory pressure, and so subsystems that
convert to memalloc_nofs_save/restore are likely to continue to run into
this issue.

Previous reports and proposed fixes:
https://lore.kernel.org/netdev/96a18bd00cbc6cb554603cc0d6ef1c551965b078.1663762494.git.gnault@redhat.com/
https://lore.kernel.org/netdev/b4d8cb09c913d3e34f853736f3f5628abfd7f4b6.1656699567.git.gnault@redhat.com/
https://lore.kernel.org/linux-nfs/de6d99321d1dcaa2ad456b92b3680aa77c07a747.1665401788.git.gnault@redhat.com/

Guilluame Nault has done all of the hard work tracking this problem down and
finding the best fix for this issue.  I'm just taking a turn posting another
fix.
====================

Link: https://lore.kernel.org/r/cover.1671194454.git.bcodding@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

14 files changed, 24 insertions, 4 deletions

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 0e58a3187345e..757f4692b5bd8 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1030,6 +1030,9 @@ randomize:
 	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;
 
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index e379ccc63c520..592cfa8b765a5 100644
--- a/drivers/block/nbd.c
+++ b/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;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index b69b89166b6b9..8cedc1ef496c7 100644
--- a/drivers/nvme/host/tcp.c
+++ b/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;
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 5fb1f364e8155..1d1cf641937c1 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/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);
 
diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c
index f8b326eed54dc..a2b2da1255dda 100644
--- a/drivers/usb/usbip/usbip_common.c
+++ b/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)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index e80252a832257..7bc7b5e03c513 100644
--- a/fs/cifs/connect.c
+++ b/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
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 8b80ca0cd65fd..4450721ec83c6 100644
--- a/fs/dlm/lowcomms.c
+++ b/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);
 
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 37d222bdfc8c3..a07b24d170f23 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/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;
diff --git a/include/net/sock.h b/include/net/sock.h
index ecea3dcc2217b..dcd72e6285b23 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -318,6 +318,9 @@ struct sk_filter;
   *	@sk_stamp: time stamp of last packet received
   *	@sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
   *	@sk_tsflags: SO_TIMESTAMPING flags
+  *	@sk_use_task_frag: allow sk_page_frag() to use current->task_frag.
+  *			   Sockets that can be used under memory reclaim should
+  *			   set this to false.
   *	@sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock
   *	              for timestamping
   *	@sk_tskey: counter to disambiguate concurrent tstamp requests
@@ -512,6 +515,7 @@ struct sock {
 	u8			sk_txtime_deadline_mode : 1,
 				sk_txtime_report_errors : 1,
 				sk_txtime_unused : 6;
+	bool			sk_use_task_frag;
 
 	struct socket		*sk_socket;
 	void			*sk_user_data;
@@ -2560,16 +2564,14 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk)
  * Both direct reclaim and page faults can nest inside other
  * socket operations and end up recursing into sk_page_frag()
  * while it's already in use: explicitly avoid task page_frag
- * usage if the caller is potentially doing any of them.
- * This assumes that page fault handlers use the GFP_NOFS flags.
+ * when users disable sk_use_task_frag.
  *
  * Return: a per task page_frag if context allows that,
  * otherwise a per socket one.
  */
 static inline struct page_frag *sk_page_frag(struct sock *sk)
 {
-	if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) ==
-	    (__GFP_DIRECT_RECLAIM | __GFP_FS))
+	if (sk->sk_use_task_frag)
 		return &current->task_frag;
 
 	return &sk->sk_frag;
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 07db2f436d44b..d9120f14684b6 100644
--- a/net/9p/trans_fd.c
+++ b/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",
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index dfa237fbd5a32..1d06e114ba3ff 100644
--- a/net/ceph/messenger.c
+++ b/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);
diff --git a/net/core/sock.c b/net/core/sock.c
index d2587d8712dba..f954d5893e799 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3390,6 +3390,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_rcvbuf		=	READ_ONCE(sysctl_rmem_default);
 	sk->sk_sndbuf		=	READ_ONCE(sysctl_wmem_default);
 	sk->sk_state		=	TCP_CLOSE;
+	sk->sk_use_task_frag	=	true;
 	sk_set_socket(sk, sock);
 
 	sock_set_flag(sk, SOCK_ZAPPED);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index c0506d0d74780..aaa5b2741b79d 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1882,6 +1882,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt,
 		sk->sk_write_space = xs_udp_write_space;
 		sk->sk_state_change = xs_local_state_change;
 		sk->sk_error_report = xs_error_report;
+		sk->sk_use_task_frag = false;
 
 		xprt_clear_connected(xprt);
 
@@ -2082,6 +2083,7 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		sk->sk_user_data = xprt;
 		sk->sk_data_ready = xs_data_ready;
 		sk->sk_write_space = xs_udp_write_space;
+		sk->sk_use_task_frag = false;
 
 		xprt_set_connected(xprt);
 
@@ -2249,6 +2251,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		sk->sk_state_change = xs_tcp_state_change;
 		sk->sk_write_space = xs_tcp_write_space;
 		sk->sk_error_report = xs_error_report;
+		sk->sk_use_task_frag = false;
 
 		/* socket options */
 		sock_reset_flag(sk, SOCK_LINGER);
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index d6fece1ed982d..74a54295c1644 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -489,6 +489,7 @@ static int espintcp_init_sk(struct sock *sk)
 
 	/* avoid using task_frag */
 	sk->sk_allocation = GFP_ATOMIC;
+	sk->sk_use_task_frag = false;
 
 	return 0;