summaryrefslogtreecommitdiff
path: root/net/unix/af_unix.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/unix/af_unix.c')
-rw-r--r--net/unix/af_unix.c226
1 files changed, 64 insertions, 162 deletions
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e7728b57a8c7..123b35ddfd71 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -758,8 +758,6 @@ static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon
static int unix_shutdown(struct socket *, int);
static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int);
-static ssize_t unix_stream_sendpage(struct socket *, struct page *, int offset,
- size_t size, int flags);
static ssize_t unix_stream_splice_read(struct socket *, loff_t *ppos,
struct pipe_inode_info *, size_t size,
unsigned int flags);
@@ -852,7 +850,6 @@ static const struct proto_ops unix_stream_ops = {
.recvmsg = unix_stream_recvmsg,
.read_skb = unix_stream_read_skb,
.mmap = sock_no_mmap,
- .sendpage = unix_stream_sendpage,
.splice_read = unix_stream_splice_read,
.set_peek_off = unix_set_peek_off,
.show_fdinfo = unix_show_fdinfo,
@@ -878,7 +875,6 @@ static const struct proto_ops unix_dgram_ops = {
.read_skb = unix_read_skb,
.recvmsg = unix_dgram_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
.set_peek_off = unix_set_peek_off,
.show_fdinfo = unix_show_fdinfo,
};
@@ -902,7 +898,6 @@ static const struct proto_ops unix_seqpacket_ops = {
.sendmsg = unix_seqpacket_sendmsg,
.recvmsg = unix_seqpacket_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
.set_peek_off = unix_set_peek_off,
.show_fdinfo = unix_show_fdinfo,
};
@@ -921,11 +916,26 @@ static void unix_unhash(struct sock *sk)
*/
}
+static bool unix_bpf_bypass_getsockopt(int level, int optname)
+{
+ if (level == SOL_SOCKET) {
+ switch (optname) {
+ case SO_PEERPIDFD:
+ return true;
+ default:
+ return false;
+ }
+ }
+
+ return false;
+}
+
struct proto unix_dgram_proto = {
.name = "UNIX",
.owner = THIS_MODULE,
.obj_size = sizeof(struct unix_sock),
.close = unix_close,
+ .bpf_bypass_getsockopt = unix_bpf_bypass_getsockopt,
#ifdef CONFIG_BPF_SYSCALL
.psock_update_sk_prot = unix_dgram_bpf_update_proto,
#endif
@@ -937,6 +947,7 @@ struct proto unix_stream_proto = {
.obj_size = sizeof(struct unix_sock),
.close = unix_close,
.unhash = unix_unhash,
+ .bpf_bypass_getsockopt = unix_bpf_bypass_getsockopt,
#ifdef CONFIG_BPF_SYSCALL
.psock_update_sk_prot = unix_stream_bpf_update_proto,
#endif
@@ -1361,7 +1372,8 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
if (err)
goto out;
- if (test_bit(SOCK_PASSCRED, &sock->flags) &&
+ if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
!unix_sk(sk)->addr) {
err = unix_autobind(sk);
if (err)
@@ -1469,7 +1481,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
if (err)
goto out;
- if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) {
+ if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
err = unix_autobind(sk);
if (err)
goto out;
@@ -1670,6 +1683,8 @@ static void unix_sock_inherit_flags(const struct socket *old,
{
if (test_bit(SOCK_PASSCRED, &old->flags))
set_bit(SOCK_PASSCRED, &new->flags);
+ if (test_bit(SOCK_PASSPIDFD, &old->flags))
+ set_bit(SOCK_PASSPIDFD, &new->flags);
if (test_bit(SOCK_PASSSEC, &old->flags))
set_bit(SOCK_PASSSEC, &new->flags);
}
@@ -1819,8 +1834,10 @@ static bool unix_passcred_enabled(const struct socket *sock,
const struct sock *other)
{
return test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags) ||
!other->sk_socket ||
- test_bit(SOCK_PASSCRED, &other->sk_socket->flags);
+ test_bit(SOCK_PASSCRED, &other->sk_socket->flags) ||
+ test_bit(SOCK_PASSPIDFD, &other->sk_socket->flags);
}
/*
@@ -1839,24 +1856,6 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
}
}
-static int maybe_init_creds(struct scm_cookie *scm,
- struct socket *socket,
- const struct sock *other)
-{
- int err;
- struct msghdr msg = { .msg_controllen = 0 };
-
- err = scm_send(socket, &msg, scm, false);
- if (err)
- return err;
-
- if (unix_passcred_enabled(socket, other)) {
- scm->pid = get_pid(task_tgid(current));
- current_uid_gid(&scm->creds.uid, &scm->creds.gid);
- }
- return err;
-}
-
static bool unix_skb_scm_eq(struct sk_buff *skb,
struct scm_cookie *scm)
{
@@ -1922,7 +1921,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
goto out;
}
- if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) {
+ if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
err = unix_autobind(sk);
if (err)
goto out;
@@ -2200,19 +2200,25 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
while (sent < len) {
size = len - sent;
- /* Keep two messages in the pipe so it schedules better */
- size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64);
+ if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
+ skb = sock_alloc_send_pskb(sk, 0, 0,
+ msg->msg_flags & MSG_DONTWAIT,
+ &err, 0);
+ } else {
+ /* Keep two messages in the pipe so it schedules better */
+ size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64);
- /* allow fallback to order-0 allocations */
- size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ);
+ /* allow fallback to order-0 allocations */
+ size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ);
- data_len = max_t(int, 0, size - SKB_MAX_HEAD(0));
+ data_len = max_t(int, 0, size - SKB_MAX_HEAD(0));
- data_len = min_t(size_t, size, PAGE_ALIGN(data_len));
+ data_len = min_t(size_t, size, PAGE_ALIGN(data_len));
- skb = sock_alloc_send_pskb(sk, size - data_len, data_len,
- msg->msg_flags & MSG_DONTWAIT, &err,
- get_order(UNIX_SKB_FRAGS_SZ));
+ skb = sock_alloc_send_pskb(sk, size - data_len, data_len,
+ msg->msg_flags & MSG_DONTWAIT, &err,
+ get_order(UNIX_SKB_FRAGS_SZ));
+ }
if (!skb)
goto out_err;
@@ -2224,13 +2230,24 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
}
fds_sent = true;
- skb_put(skb, size - data_len);
- skb->data_len = data_len;
- skb->len = size;
- err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
- if (err) {
- kfree_skb(skb);
- goto out_err;
+ if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
+ err = skb_splice_from_iter(skb, &msg->msg_iter, size,
+ sk->sk_allocation);
+ if (err < 0) {
+ kfree_skb(skb);
+ goto out_err;
+ }
+ size = err;
+ refcount_add(size, &sk->sk_wmem_alloc);
+ } else {
+ skb_put(skb, size - data_len);
+ skb->data_len = data_len;
+ skb->len = size;
+ err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+ if (err) {
+ kfree_skb(skb);
+ goto out_err;
+ }
}
unix_state_lock(other);
@@ -2272,122 +2289,6 @@ out_err:
return sent ? : err;
}
-static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
- int offset, size_t size, int flags)
-{
- int err;
- bool send_sigpipe = false;
- bool init_scm = true;
- struct scm_cookie scm;
- struct sock *other, *sk = socket->sk;
- struct sk_buff *skb, *newskb = NULL, *tail = NULL;
-
- if (flags & MSG_OOB)
- return -EOPNOTSUPP;
-
- other = unix_peer(sk);
- if (!other || sk->sk_state != TCP_ESTABLISHED)
- return -ENOTCONN;
-
- if (false) {
-alloc_skb:
- unix_state_unlock(other);
- mutex_unlock(&unix_sk(other)->iolock);
- newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
- &err, 0);
- if (!newskb)
- goto err;
- }
-
- /* we must acquire iolock as we modify already present
- * skbs in the sk_receive_queue and mess with skb->len
- */
- err = mutex_lock_interruptible(&unix_sk(other)->iolock);
- if (err) {
- err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
- goto err;
- }
-
- if (sk->sk_shutdown & SEND_SHUTDOWN) {
- err = -EPIPE;
- send_sigpipe = true;
- goto err_unlock;
- }
-
- unix_state_lock(other);
-
- if (sock_flag(other, SOCK_DEAD) ||
- other->sk_shutdown & RCV_SHUTDOWN) {
- err = -EPIPE;
- send_sigpipe = true;
- goto err_state_unlock;
- }
-
- if (init_scm) {
- err = maybe_init_creds(&scm, socket, other);
- if (err)
- goto err_state_unlock;
- init_scm = false;
- }
-
- skb = skb_peek_tail(&other->sk_receive_queue);
- if (tail && tail == skb) {
- skb = newskb;
- } else if (!skb || !unix_skb_scm_eq(skb, &scm)) {
- if (newskb) {
- skb = newskb;
- } else {
- tail = skb;
- goto alloc_skb;
- }
- } else if (newskb) {
- /* this is fast path, we don't necessarily need to
- * call to kfree_skb even though with newskb == NULL
- * this - does no harm
- */
- consume_skb(newskb);
- newskb = NULL;
- }
-
- if (skb_append_pagefrags(skb, page, offset, size)) {
- tail = skb;
- goto alloc_skb;
- }
-
- skb->len += size;
- skb->data_len += size;
- skb->truesize += size;
- refcount_add(size, &sk->sk_wmem_alloc);
-
- if (newskb) {
- err = unix_scm_to_skb(&scm, skb, false);
- if (err)
- goto err_state_unlock;
- spin_lock(&other->sk_receive_queue.lock);
- __skb_queue_tail(&other->sk_receive_queue, newskb);
- spin_unlock(&other->sk_receive_queue.lock);
- }
-
- unix_state_unlock(other);
- mutex_unlock(&unix_sk(other)->iolock);
-
- other->sk_data_ready(other);
- scm_destroy(&scm);
- return size;
-
-err_state_unlock:
- unix_state_unlock(other);
-err_unlock:
- mutex_unlock(&unix_sk(other)->iolock);
-err:
- kfree_skb(newskb);
- if (send_sigpipe && !(flags & MSG_NOSIGNAL))
- send_sig(SIGPIPE, current, 0);
- if (!init_scm)
- scm_destroy(&scm);
- return err;
-}
-
static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg,
size_t len)
{
@@ -2526,7 +2427,7 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
}
err = (flags & MSG_TRUNC) ? skb->len - skip : size;
- scm_recv(sock, msg, &scm, flags);
+ scm_recv_unix(sock, msg, &scm, flags);
out_free:
skb_free_datagram(sk, skb);
@@ -2821,7 +2722,8 @@ unlock:
/* Never glue messages from different writers */
if (!unix_skb_scm_eq(skb, &scm))
break;
- } else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
+ } else if (test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) {
/* Copy credentials */
scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
unix_set_secdata(&scm, skb);
@@ -2906,7 +2808,7 @@ unlock:
mutex_unlock(&u->iolock);
if (state->msg)
- scm_recv(sock, state->msg, &scm, flags);
+ scm_recv_unix(sock, state->msg, &scm, flags);
else
scm_destroy(&scm);
out: