Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/net/unix/Kconfig b/net/unix/Kconfig
index 8b31ab8..a23a5cc 100644
--- a/net/unix/Kconfig
+++ b/net/unix/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
#
# Unix Domain Sockets
#
@@ -19,6 +20,11 @@
Say Y unless you know what you are doing.
+config UNIX_SCM
+ bool
+ depends on UNIX
+ default y
+
config UNIX_DIAG
tristate "UNIX: socket monitoring interface"
depends on UNIX
diff --git a/net/unix/Makefile b/net/unix/Makefile
index ffd0a27..54e58cc 100644
--- a/net/unix/Makefile
+++ b/net/unix/Makefile
@@ -10,3 +10,5 @@
obj-$(CONFIG_UNIX_DIAG) += unix_diag.o
unix_diag-y := diag.o
+
+obj-$(CONFIG_UNIX_SCM) += scm.o
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c754f3a..0d8da80 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* NET4: Implementation of BSD Unix domain sockets.
*
* Authors: Alan Cox, <alan@lxorguk.ukuu.org.uk>
*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
* Fixes:
* Linus Torvalds : Assorted bug cures.
* Niibe Yutaka : async I/O support.
@@ -49,7 +45,6 @@
* the core infrastructure is doing that
* for all net proto families now (2.5.69+)
*
- *
* Known differences from reference BSD that was tested:
*
* [TO FIX]
@@ -119,6 +114,8 @@
#include <linux/freezer.h>
#include <linux/file.h>
+#include "scm.h"
+
struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE];
EXPORT_SYMBOL_GPL(unix_socket_table);
DEFINE_SPINLOCK(unix_table_lock);
@@ -225,6 +222,8 @@
static int unix_mkname(struct sockaddr_un *sunaddr, int len, unsigned int *hashp)
{
+ *hashp = 0;
+
if (len <= sizeof(short) || len > sizeof(*sunaddr))
return -EINVAL;
if (!sunaddr || sunaddr->sun_family != AF_UNIX)
@@ -888,7 +887,7 @@
addr->hash ^= sk->sk_type;
__unix_remove_socket(sk);
- u->addr = addr;
+ smp_store_release(&u->addr, addr);
__unix_insert_socket(&unix_socket_table[addr->hash], sk);
spin_unlock(&unix_table_lock);
err = 0;
@@ -1058,7 +1057,7 @@
err = 0;
__unix_remove_socket(sk);
- u->addr = addr;
+ smp_store_release(&u->addr, addr);
__unix_insert_socket(list, sk);
out_unlock:
@@ -1329,15 +1328,29 @@
RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
otheru = unix_sk(other);
- /* copy address information from listening to new sock*/
- if (otheru->addr) {
- refcount_inc(&otheru->addr->refcnt);
- newu->addr = otheru->addr;
- }
+ /* copy address information from listening to new sock
+ *
+ * The contents of *(otheru->addr) and otheru->path
+ * are seen fully set up here, since we have found
+ * otheru in hash under unix_table_lock. Insertion
+ * into the hash chain we'd found it in had been done
+ * in an earlier critical area protected by unix_table_lock,
+ * the same one where we'd set *(otheru->addr) contents,
+ * as well as otheru->path and otheru->addr itself.
+ *
+ * Using smp_store_release() here to set newu->addr
+ * is enough to make those stores, as well as stores
+ * to newu->path visible to anyone who gets newu->addr
+ * by smp_load_acquire(). IOW, the same warranties
+ * as for unix_sock instances bound in unix_bind() or
+ * in unix_autobind().
+ */
if (otheru->path.dentry) {
path_get(&otheru->path);
newu->path = otheru->path;
}
+ refcount_inc(&otheru->addr->refcnt);
+ smp_store_release(&newu->addr, otheru->addr);
/* Set credentials */
copy_peercred(sk, other);
@@ -1451,7 +1464,7 @@
static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
{
struct sock *sk = sock->sk;
- struct unix_sock *u;
+ struct unix_address *addr;
DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr);
int err = 0;
@@ -1466,85 +1479,20 @@
sock_hold(sk);
}
- u = unix_sk(sk);
- unix_state_lock(sk);
- if (!u->addr) {
+ addr = smp_load_acquire(&unix_sk(sk)->addr);
+ if (!addr) {
sunaddr->sun_family = AF_UNIX;
sunaddr->sun_path[0] = 0;
err = sizeof(short);
} else {
- struct unix_address *addr = u->addr;
-
err = addr->len;
memcpy(sunaddr, addr->name, addr->len);
}
- unix_state_unlock(sk);
sock_put(sk);
out:
return err;
}
-static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
-{
- int i;
-
- scm->fp = UNIXCB(skb).fp;
- UNIXCB(skb).fp = NULL;
-
- for (i = scm->fp->count-1; i >= 0; i--)
- unix_notinflight(scm->fp->user, scm->fp->fp[i]);
-}
-
-static void unix_destruct_scm(struct sk_buff *skb)
-{
- struct scm_cookie scm;
- memset(&scm, 0, sizeof(scm));
- scm.pid = UNIXCB(skb).pid;
- if (UNIXCB(skb).fp)
- unix_detach_fds(&scm, skb);
-
- /* Alas, it calls VFS */
- /* So fscking what? fput() had been SMP-safe since the last Summer */
- scm_destroy(&scm);
- sock_wfree(skb);
-}
-
-/*
- * The "user->unix_inflight" variable is protected by the garbage
- * collection lock, and we just read it locklessly here. If you go
- * over the limit, there might be a tiny race in actually noticing
- * it across threads. Tough.
- */
-static inline bool too_many_unix_fds(struct task_struct *p)
-{
- struct user_struct *user = current_user();
-
- if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
- return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
- return false;
-}
-
-static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
-{
- int i;
-
- if (too_many_unix_fds(current))
- return -ETOOMANYREFS;
-
- /*
- * Need to duplicate file references for the sake of garbage
- * collection. Otherwise a socket in the fps might become a
- * candidate for GC while the skb is not yet queued.
- */
- UNIXCB(skb).fp = scm_fp_dup(scm->fp);
- if (!UNIXCB(skb).fp)
- return -ENOMEM;
-
- for (i = scm->fp->count - 1; i >= 0; i--)
- unix_inflight(scm->fp->user, scm->fp->fp[i]);
- return 0;
-}
-
static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
{
int err = 0;
@@ -2071,11 +2019,11 @@
static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
{
- struct unix_sock *u = unix_sk(sk);
+ struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr);
- if (u->addr) {
- msg->msg_namelen = u->addr->len;
- memcpy(msg->msg_name, u->addr->name, u->addr->len);
+ if (addr) {
+ msg->msg_namelen = addr->len;
+ memcpy(msg->msg_name, addr->name, addr->len);
}
}
@@ -2087,8 +2035,8 @@
struct unix_sock *u = unix_sk(sk);
struct sk_buff *skb, *last;
long timeo;
+ int skip;
int err;
- int peeked, skip;
err = -EOPNOTSUPP;
if (flags&MSG_OOB)
@@ -2100,8 +2048,8 @@
mutex_lock(&u->iolock);
skip = sk_peek_offset(sk, flags);
- skb = __skb_try_recv_datagram(sk, flags, NULL, &peeked, &skip,
- &err, &last);
+ skb = __skb_try_recv_datagram(sk, flags, NULL, &skip, &err,
+ &last);
if (skb)
break;
@@ -2579,15 +2527,14 @@
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
return -EPERM;
- unix_state_lock(sk);
- path = unix_sk(sk)->path;
- if (!path.dentry) {
- unix_state_unlock(sk);
+ if (!smp_load_acquire(&unix_sk(sk)->addr))
return -ENOENT;
- }
+
+ path = unix_sk(sk)->path;
+ if (!path.dentry)
+ return -ENOENT;
path_get(&path);
- unix_state_unlock(sk);
fd = get_unused_fd_flags(O_CLOEXEC);
if (fd < 0)
@@ -2652,7 +2599,7 @@
mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
/* readable? */
- if (!skb_queue_empty(&sk->sk_receive_queue))
+ if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
@@ -2681,7 +2628,7 @@
mask = 0;
/* exceptional events? */
- if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+ if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
mask |= EPOLLERR |
(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
@@ -2691,7 +2638,7 @@
mask |= EPOLLHUP;
/* readable? */
- if (!skb_queue_empty(&sk->sk_receive_queue))
+ if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
@@ -2828,7 +2775,7 @@
(s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING),
sock_i_ino(s));
- if (u->addr) {
+ if (u->addr) { // under unix_table_lock here
int i, len;
seq_putc(seq, ' ');
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 384c84e..9ff64f9 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -1,16 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0-only
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/sock_diag.h>
#include <linux/unix_diag.h>
#include <linux/skbuff.h>
#include <linux/module.h>
+#include <linux/uidgid.h>
#include <net/netlink.h>
#include <net/af_unix.h>
#include <net/tcp_states.h>
+#include <net/sock.h>
static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
{
- struct unix_address *addr = unix_sk(sk)->addr;
+ /* might or might not have unix_table_lock */
+ struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr);
if (!addr)
return 0;
@@ -109,6 +113,12 @@
return nla_put(nlskb, UNIX_DIAG_RQLEN, sizeof(rql), &rql);
}
+static int sk_diag_dump_uid(struct sock *sk, struct sk_buff *nlskb)
+{
+ uid_t uid = from_kuid_munged(sk_user_ns(nlskb->sk), sock_i_uid(sk));
+ return nla_put(nlskb, UNIX_DIAG_UID, sizeof(uid_t), &uid);
+}
+
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
u32 portid, u32 seq, u32 flags, int sk_ino)
{
@@ -155,6 +165,10 @@
if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown))
goto out_nlmsg_trim;
+ if ((req->udiag_show & UDIAG_SHOW_UID) &&
+ sk_diag_dump_uid(sk, skb))
+ goto out_nlmsg_trim;
+
nlmsg_end(skb, nlh);
return 0;
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index c36757e..12e2dda 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -1,9 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* NET3: Garbage Collector For AF_UNIX sockets
*
* Garbage Collector:
* Copyright (C) Barak A. Pearlmutter.
- * Released under the GPL version 2 or later.
*
* Chopped about by Alan Cox 22/3/96 to make it fit the AF_UNIX socket problem.
* If it doesn't work blame me, it worked when Barak sent it.
@@ -24,11 +24,6 @@
*
* - don't just push entire root set; process in place
*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
* Fixes:
* Alan Cox 07 Sept 1997 Vmalloc internal stack as needed.
* Cope with changing max_files.
@@ -86,77 +81,13 @@
#include <net/scm.h>
#include <net/tcp_states.h>
+#include "scm.h"
+
/* Internal data structures and random procedures: */
-static LIST_HEAD(gc_inflight_list);
static LIST_HEAD(gc_candidates);
-static DEFINE_SPINLOCK(unix_gc_lock);
static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait);
-unsigned int unix_tot_inflight;
-
-struct sock *unix_get_socket(struct file *filp)
-{
- struct sock *u_sock = NULL;
- struct inode *inode = file_inode(filp);
-
- /* Socket ? */
- if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
- struct socket *sock = SOCKET_I(inode);
- struct sock *s = sock->sk;
-
- /* PF_UNIX ? */
- if (s && sock->ops && sock->ops->family == PF_UNIX)
- u_sock = s;
- }
- return u_sock;
-}
-
-/* Keep the number of times in flight count for the file
- * descriptor if it is for an AF_UNIX socket.
- */
-
-void unix_inflight(struct user_struct *user, struct file *fp)
-{
- struct sock *s = unix_get_socket(fp);
-
- spin_lock(&unix_gc_lock);
-
- if (s) {
- struct unix_sock *u = unix_sk(s);
-
- if (atomic_long_inc_return(&u->inflight) == 1) {
- BUG_ON(!list_empty(&u->link));
- list_add_tail(&u->link, &gc_inflight_list);
- } else {
- BUG_ON(list_empty(&u->link));
- }
- unix_tot_inflight++;
- }
- user->unix_inflight++;
- spin_unlock(&unix_gc_lock);
-}
-
-void unix_notinflight(struct user_struct *user, struct file *fp)
-{
- struct sock *s = unix_get_socket(fp);
-
- spin_lock(&unix_gc_lock);
-
- if (s) {
- struct unix_sock *u = unix_sk(s);
-
- BUG_ON(!atomic_long_read(&u->inflight));
- BUG_ON(list_empty(&u->link));
-
- if (atomic_long_dec_and_test(&u->inflight))
- list_del_init(&u->link);
- unix_tot_inflight--;
- }
- user->unix_inflight--;
- spin_unlock(&unix_gc_lock);
-}
-
static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
struct sk_buff_head *hitlist)
{
diff --git a/net/unix/scm.c b/net/unix/scm.c
new file mode 100644
index 0000000..8c40f2b
--- /dev/null
+++ b/net/unix/scm.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/socket.h>
+#include <linux/net.h>
+#include <linux/fs.h>
+#include <net/af_unix.h>
+#include <net/scm.h>
+#include <linux/init.h>
+
+#include "scm.h"
+
+unsigned int unix_tot_inflight;
+EXPORT_SYMBOL(unix_tot_inflight);
+
+LIST_HEAD(gc_inflight_list);
+EXPORT_SYMBOL(gc_inflight_list);
+
+DEFINE_SPINLOCK(unix_gc_lock);
+EXPORT_SYMBOL(unix_gc_lock);
+
+struct sock *unix_get_socket(struct file *filp)
+{
+ struct sock *u_sock = NULL;
+ struct inode *inode = file_inode(filp);
+
+ /* Socket ? */
+ if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
+ struct socket *sock = SOCKET_I(inode);
+ struct sock *s = sock->sk;
+
+ /* PF_UNIX ? */
+ if (s && sock->ops && sock->ops->family == PF_UNIX)
+ u_sock = s;
+ } else {
+ /* Could be an io_uring instance */
+ u_sock = io_uring_get_socket(filp);
+ }
+ return u_sock;
+}
+EXPORT_SYMBOL(unix_get_socket);
+
+/* Keep the number of times in flight count for the file
+ * descriptor if it is for an AF_UNIX socket.
+ */
+void unix_inflight(struct user_struct *user, struct file *fp)
+{
+ struct sock *s = unix_get_socket(fp);
+
+ spin_lock(&unix_gc_lock);
+
+ if (s) {
+ struct unix_sock *u = unix_sk(s);
+
+ if (atomic_long_inc_return(&u->inflight) == 1) {
+ BUG_ON(!list_empty(&u->link));
+ list_add_tail(&u->link, &gc_inflight_list);
+ } else {
+ BUG_ON(list_empty(&u->link));
+ }
+ unix_tot_inflight++;
+ }
+ user->unix_inflight++;
+ spin_unlock(&unix_gc_lock);
+}
+
+void unix_notinflight(struct user_struct *user, struct file *fp)
+{
+ struct sock *s = unix_get_socket(fp);
+
+ spin_lock(&unix_gc_lock);
+
+ if (s) {
+ struct unix_sock *u = unix_sk(s);
+
+ BUG_ON(!atomic_long_read(&u->inflight));
+ BUG_ON(list_empty(&u->link));
+
+ if (atomic_long_dec_and_test(&u->inflight))
+ list_del_init(&u->link);
+ unix_tot_inflight--;
+ }
+ user->unix_inflight--;
+ spin_unlock(&unix_gc_lock);
+}
+
+/*
+ * The "user->unix_inflight" variable is protected by the garbage
+ * collection lock, and we just read it locklessly here. If you go
+ * over the limit, there might be a tiny race in actually noticing
+ * it across threads. Tough.
+ */
+static inline bool too_many_unix_fds(struct task_struct *p)
+{
+ struct user_struct *user = current_user();
+
+ if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+ return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
+ return false;
+}
+
+int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+ int i;
+
+ if (too_many_unix_fds(current))
+ return -ETOOMANYREFS;
+
+ /*
+ * Need to duplicate file references for the sake of garbage
+ * collection. Otherwise a socket in the fps might become a
+ * candidate for GC while the skb is not yet queued.
+ */
+ UNIXCB(skb).fp = scm_fp_dup(scm->fp);
+ if (!UNIXCB(skb).fp)
+ return -ENOMEM;
+
+ for (i = scm->fp->count - 1; i >= 0; i--)
+ unix_inflight(scm->fp->user, scm->fp->fp[i]);
+ return 0;
+}
+EXPORT_SYMBOL(unix_attach_fds);
+
+void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+ int i;
+
+ scm->fp = UNIXCB(skb).fp;
+ UNIXCB(skb).fp = NULL;
+
+ for (i = scm->fp->count-1; i >= 0; i--)
+ unix_notinflight(scm->fp->user, scm->fp->fp[i]);
+}
+EXPORT_SYMBOL(unix_detach_fds);
+
+void unix_destruct_scm(struct sk_buff *skb)
+{
+ struct scm_cookie scm;
+
+ memset(&scm, 0, sizeof(scm));
+ scm.pid = UNIXCB(skb).pid;
+ if (UNIXCB(skb).fp)
+ unix_detach_fds(&scm, skb);
+
+ /* Alas, it calls VFS */
+ /* So fscking what? fput() had been SMP-safe since the last Summer */
+ scm_destroy(&scm);
+ sock_wfree(skb);
+}
+EXPORT_SYMBOL(unix_destruct_scm);
diff --git a/net/unix/scm.h b/net/unix/scm.h
new file mode 100644
index 0000000..5a255a4
--- /dev/null
+++ b/net/unix/scm.h
@@ -0,0 +1,10 @@
+#ifndef NET_UNIX_SCM_H
+#define NET_UNIX_SCM_H
+
+extern struct list_head gc_inflight_list;
+extern spinlock_t unix_gc_lock;
+
+int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb);
+void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb);
+
+#endif
diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c
index b3d5150..c09bea8 100644
--- a/net/unix/sysctl_net_unix.c
+++ b/net/unix/sysctl_net_unix.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* NET4: Sysctl interface to net af_unix subsystem.
*
* Authors: Mike Shaver.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
*/
#include <linux/mm.h>