net: rework recvmsg handler msg_name and msg_namelen logic
This patch now always passes msg->msg_namelen as 0. recvmsg handlers must
set msg_namelen to the proper size <= sizeof(struct sockaddr_storage)
to return msg_name to the user.
This prevents numerous uninitialized memory leaks we had in the
recvmsg handlers and makes it harder for new code to accidentally leak
uninitialized memory.
Optimize for the case recvfrom is called with NULL as address. We don't
need to copy the address at all, so set it to NULL before invoking the
recvmsg handler. We can do so, because all the recvmsg handlers must
cope with the case a plain read() is called on them. read() also sets
msg_name to NULL.
Also document these changes in include/linux/net.h as suggested by David
Miller.
Changes since RFC:
Set msg->msg_name = NULL if user specified a NULL in msg_name but had a
non-null msg_namelen in verify_iovec/verify_compat_iovec. This doesn't
affect sendto as it would bail out earlier while trying to copy-in the
address. It also more naturally reflects the logic by the callers of
verify_iovec.
With this change in place I could remove "
if (!uaddr || msg_sys->msg_namelen == 0)
msg->msg_name = NULL
".
This change does not alter the user visible error logic as we ignore
msg_namelen as long as msg_name is NULL.
Also remove two unnecessary curly brackets in ___sys_recvmsg and change
comments to netdev style.
Cc: David Miller <davem@davemloft.net>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 7fee50d..7d424ac 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1735,7 +1735,6 @@
size_t size, int flags)
{
struct sock *sk = sock->sk;
- struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
struct ddpehdr *ddp;
int copied = 0;
int offset = 0;
@@ -1764,14 +1763,13 @@
}
err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
- if (!err) {
- if (sat) {
- sat->sat_family = AF_APPLETALK;
- sat->sat_port = ddp->deh_sport;
- sat->sat_addr.s_node = ddp->deh_snode;
- sat->sat_addr.s_net = ddp->deh_snet;
- }
- msg->msg_namelen = sizeof(*sat);
+ if (!err && msg->msg_name) {
+ struct sockaddr_at *sat = msg->msg_name;
+ sat->sat_family = AF_APPLETALK;
+ sat->sat_port = ddp->deh_sport;
+ sat->sat_addr.s_node = ddp->deh_snode;
+ sat->sat_addr.s_net = ddp->deh_snet;
+ msg->msg_namelen = sizeof(*sat);
}
skb_free_datagram(sk, skb); /* Free the datagram. */
diff --git a/net/atm/common.c b/net/atm/common.c
index 737bef5..7b49100 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -531,8 +531,6 @@
struct sk_buff *skb;
int copied, error = -EINVAL;
- msg->msg_namelen = 0;
-
if (sock->state != SS_CONNECTED)
return -ENOTCONN;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index a00123e..7bb1605 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1636,11 +1636,11 @@
skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
- if (msg->msg_namelen != 0) {
- struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name;
+ if (msg->msg_name) {
ax25_digi digi;
ax25_address src;
const unsigned char *mac = skb_mac_header(skb);
+ struct sockaddr_ax25 *sax = msg->msg_name;
memset(sax, 0, sizeof(struct full_sockaddr_ax25));
ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL,
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index f6a1671..56ca494 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -224,10 +224,9 @@
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb) {
- if (sk->sk_shutdown & RCV_SHUTDOWN) {
- msg->msg_namelen = 0;
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
return 0;
- }
+
return err;
}
@@ -245,8 +244,6 @@
if (bt_sk(sk)->skb_msg_name)
bt_sk(sk)->skb_msg_name(skb, msg->msg_name,
&msg->msg_namelen);
- else
- msg->msg_namelen = 0;
}
skb_free_datagram(sk, skb);
@@ -295,8 +292,6 @@
if (flags & MSG_OOB)
return -EOPNOTSUPP;
- msg->msg_namelen = 0;
-
BT_DBG("sk %p size %zu", sk, size);
lock_sock(sk);
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 71f0be1..6a6c8bb 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -856,8 +856,6 @@
if (!skb)
return err;
- msg->msg_namelen = 0;
-
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index c4d3d42..c80766f 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -615,7 +615,6 @@
if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
rfcomm_dlc_accept(d);
- msg->msg_namelen = 0;
return 0;
}
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 12a0e51..24fa396 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -711,7 +711,6 @@
test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
sco_conn_defer_accept(pi->conn->hcon, pi->setting);
sk->sk_state = BT_CONFIG;
- msg->msg_namelen = 0;
release_sock(sk);
return 0;
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 05a41c7..d6be3ed 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -286,8 +286,6 @@
if (m->msg_flags&MSG_OOB)
goto read_error;
- m->msg_namelen = 0;
-
skb = skb_recv_datagram(sk, flags, 0 , &ret);
if (!skb)
goto read_error;
@@ -361,8 +359,6 @@
if (flags&MSG_OOB)
goto out;
- msg->msg_namelen = 0;
-
/*
* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
diff --git a/net/compat.c b/net/compat.c
index 8903258..618c6a8 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -93,7 +93,8 @@
if (err < 0)
return err;
}
- kern_msg->msg_name = kern_address;
+ if (kern_msg->msg_name)
+ kern_msg->msg_name = kern_address;
} else
kern_msg->msg_name = NULL;
diff --git a/net/core/iovec.c b/net/core/iovec.c
index 4cdb7c4..b618694 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -48,7 +48,8 @@
if (err < 0)
return err;
}
- m->msg_name = address;
+ if (m->msg_name)
+ m->msg_name = address;
} else {
m->msg_name = NULL;
}
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 7a1e0fc..e096025 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1823,8 +1823,6 @@
if (skb->tstamp.tv64)
sk->sk_stamp = skb->tstamp;
- msg->msg_namelen = sizeof(*sipx);
-
if (sipx) {
sipx->sipx_family = AF_IPX;
sipx->sipx_port = ipx->ipx_source.sock;
@@ -1832,6 +1830,7 @@
sipx->sipx_network = IPX_SKB_CB(skb)->ipx_source_net;
sipx->sipx_type = ipx->ipx_type;
sipx->sipx_zero = 0;
+ msg->msg_namelen = sizeof(*sipx);
}
rc = copied;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 0f67690..de7db23 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1385,8 +1385,6 @@
IRDA_DEBUG(4, "%s()\n", __func__);
- msg->msg_namelen = 0;
-
skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
flags & MSG_DONTWAIT, &err);
if (!skb)
@@ -1451,8 +1449,6 @@
target = sock_rcvlowat(sk, flags & MSG_WAITALL, size);
timeo = sock_rcvtimeo(sk, noblock);
- msg->msg_namelen = 0;
-
do {
int chunk;
struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 168aff5..c4b7218 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1324,8 +1324,6 @@
int err = 0;
u32 offset;
- msg->msg_namelen = 0;
-
if ((sk->sk_state == IUCV_DISCONN) &&
skb_queue_empty(&iucv->backlog_skb_q) &&
skb_queue_empty(&sk->sk_receive_queue) &&
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 911ef03..545f047 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3616,7 +3616,6 @@
if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
goto out;
- msg->msg_namelen = 0;
skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto out;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index ffda81e..be5fadf 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -197,8 +197,6 @@
if (sk->sk_state & PPPOX_BOUND)
goto end;
- msg->msg_namelen = 0;
-
err = 0;
skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
flags & MSG_DONTWAIT, &err);
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 6cba486..7b01b9f 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -720,8 +720,6 @@
int target; /* Read at least this many bytes */
long timeo;
- msg->msg_namelen = 0;
-
lock_sock(sk);
copied = -ENOTCONN;
if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN))
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index f0176e1..bca50b9 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2335,8 +2335,6 @@
}
#endif
- msg->msg_namelen = 0;
-
copied = data_skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 698814b..53c19a3 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1179,10 +1179,9 @@
sax->sax25_family = AF_NETROM;
skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call,
AX25_ADDR_LEN);
+ msg->msg_namelen = sizeof(*sax);
}
- msg->msg_namelen = sizeof(*sax);
-
skb_free_datagram(sk, skb);
release_sock(sk);
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index d308402b..824c605 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -807,8 +807,6 @@
pr_debug("%p %zu\n", sk, len);
- msg->msg_namelen = 0;
-
lock_sock(sk);
if (sk->sk_state == LLCP_CLOSED &&
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index cd958b3..66bcd2e 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -244,8 +244,6 @@
if (!skb)
return rc;
- msg->msg_namelen = 0;
-
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2e8286b..61bd50a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2660,7 +2660,6 @@
struct sock *sk = sock->sk;
struct sk_buff *skb;
int copied, err;
- struct sockaddr_ll *sll;
int vnet_hdr_len = 0;
err = -EINVAL;
@@ -2744,22 +2743,10 @@
goto out_free;
}
- /*
- * If the address length field is there to be filled in, we fill
- * it in now.
+ /* You lose any data beyond the buffer you gave. If it worries
+ * a user program they can ask the device for its MTU
+ * anyway.
*/
-
- sll = &PACKET_SKB_CB(skb)->sa.ll;
- if (sock->type == SOCK_PACKET)
- msg->msg_namelen = sizeof(struct sockaddr_pkt);
- else
- msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr);
-
- /*
- * You lose any data beyond the buffer you gave. If it worries a
- * user program they can ask the device for its MTU anyway.
- */
-
copied = skb->len;
if (copied > len) {
copied = len;
@@ -2772,9 +2759,20 @@
sock_recv_ts_and_drops(msg, sk, skb);
- if (msg->msg_name)
+ if (msg->msg_name) {
+ /* If the address length field is there to be filled
+ * in, we fill it in now.
+ */
+ if (sock->type == SOCK_PACKET) {
+ msg->msg_namelen = sizeof(struct sockaddr_pkt);
+ } else {
+ struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+ msg->msg_namelen = sll->sll_halen +
+ offsetof(struct sockaddr_ll, sll_addr);
+ }
memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
msg->msg_namelen);
+ }
if (pkt_sk(sk)->auxdata) {
struct tpacket_auxdata aux;
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 9f0f17c..de339b2 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -410,8 +410,6 @@
rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo);
- msg->msg_namelen = 0;
-
if (msg_flags & MSG_OOB)
goto out;
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index e98fcfb..33af772 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1216,7 +1216,6 @@
{
struct sock *sk = sock->sk;
struct rose_sock *rose = rose_sk(sk);
- struct sockaddr_rose *srose = (struct sockaddr_rose *)msg->msg_name;
size_t copied;
unsigned char *asmptr;
struct sk_buff *skb;
@@ -1252,8 +1251,11 @@
skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
- if (srose != NULL) {
- memset(srose, 0, msg->msg_namelen);
+ if (msg->msg_name) {
+ struct sockaddr_rose *srose;
+
+ memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose));
+ srose = msg->msg_name;
srose->srose_family = AF_ROSE;
srose->srose_addr = rose->dest_addr;
srose->srose_call = rose->dest_call;
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index 4b48687..898492a 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -143,10 +143,13 @@
/* copy the peer address and timestamp */
if (!continue_call) {
- if (msg->msg_name && msg->msg_namelen > 0)
+ if (msg->msg_name) {
+ size_t len =
+ sizeof(call->conn->trans->peer->srx);
memcpy(msg->msg_name,
- &call->conn->trans->peer->srx,
- sizeof(call->conn->trans->peer->srx));
+ &call->conn->trans->peer->srx, len);
+ msg->msg_namelen = len;
+ }
sock_recv_ts_and_drops(msg, &rx->sk, skb);
}
diff --git a/net/socket.c b/net/socket.c
index c226aceee..fc28556 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1840,8 +1840,10 @@
msg.msg_iov = &iov;
iov.iov_len = size;
iov.iov_base = ubuf;
- msg.msg_name = (struct sockaddr *)&address;
- msg.msg_namelen = sizeof(address);
+ /* Save some cycles and don't copy the address if not needed */
+ msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
+ /* We assume all kernel code knows the size of sockaddr_storage */
+ msg.msg_namelen = 0;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = sock_recvmsg(sock, &msg, size, flags);
@@ -2221,16 +2223,14 @@
goto out;
}
- /*
- * Save the user-mode address (verify_iovec will change the
- * kernel msghdr to use the kernel address space)
+ /* Save the user-mode address (verify_iovec will change the
+ * kernel msghdr to use the kernel address space)
*/
-
uaddr = (__force void __user *)msg_sys->msg_name;
uaddr_len = COMPAT_NAMELEN(msg);
- if (MSG_CMSG_COMPAT & flags) {
+ if (MSG_CMSG_COMPAT & flags)
err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
- } else
+ else
err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
if (err < 0)
goto out_freeiov;
@@ -2239,6 +2239,9 @@
cmsg_ptr = (unsigned long)msg_sys->msg_control;
msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
+ /* We assume all kernel code knows the size of sockaddr_storage */
+ msg_sys->msg_namelen = 0;
+
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3906527..3b61851 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -980,9 +980,6 @@
goto exit;
}
- /* will be updated in set_orig_addr() if needed */
- m->msg_namelen = 0;
-
timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
restart:
@@ -1091,9 +1088,6 @@
goto exit;
}
- /* will be updated in set_orig_addr() if needed */
- m->msg_namelen = 0;
-
target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);
timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c1f403b..01625ccc 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1754,7 +1754,6 @@
{
struct unix_sock *u = unix_sk(sk);
- msg->msg_namelen = 0;
if (u->addr) {
msg->msg_namelen = u->addr->len;
memcpy(msg->msg_name, u->addr->name, u->addr->len);
@@ -1778,8 +1777,6 @@
if (flags&MSG_OOB)
goto out;
- msg->msg_namelen = 0;
-
err = mutex_lock_interruptible(&u->readlock);
if (err) {
err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
@@ -1924,8 +1921,6 @@
target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
- msg->msg_namelen = 0;
-
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
*/
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 545c08b..5adfd94 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1662,8 +1662,6 @@
vsk = vsock_sk(sk);
err = 0;
- msg->msg_namelen = 0;
-
lock_sock(sk);
if (sk->sk_state != SS_CONNECTED) {
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 9d69866..687360d 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1746,8 +1746,6 @@
if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
return -EOPNOTSUPP;
- msg->msg_namelen = 0;
-
/* Retrieve the head sk_buff from the socket's receive queue. */
err = 0;
skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err);
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 45a3ab5..7622789 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1340,10 +1340,9 @@
if (sx25) {
sx25->sx25_family = AF_X25;
sx25->sx25_addr = x25->dest_addr;
+ msg->msg_namelen = sizeof(*sx25);
}
- msg->msg_namelen = sizeof(struct sockaddr_x25);
-
x25_check_rbuf(sk);
rc = copied;
out_free_dgram:
