Skip to content

Commit

Permalink
net: split out functions related to registering inflight socket files
Browse files Browse the repository at this point in the history
We need this functionality for the io_uring file registration, but
we cannot rely on it since CONFIG_UNIX can be modular. Move the helpers
to a separate file, that's always builtin to the kernel if CONFIG_UNIX is
m/y.

No functional changes in this patch, just moving code around.

Reviewed-by: Hannes Reinecke <hare@suse.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
  • Loading branch information
Jens Axboe committed Feb 28, 2019
1 parent edafcce commit f4e6587
Show file tree
Hide file tree
Showing 8 changed files with 174 additions and 131 deletions.
1 change: 1 addition & 0 deletions include/net/af_unix.h
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@

void unix_inflight(struct user_struct *user, struct file *fp);
void unix_notinflight(struct user_struct *user, struct file *fp);
void unix_destruct_scm(struct sk_buff *skb);
void unix_gc(void);
void wait_for_unix_gc(void);
struct sock *unix_get_socket(struct file *filp);
Expand Down
2 changes: 1 addition & 1 deletion net/Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/
obj-$(CONFIG_INET) += ipv4/
obj-$(CONFIG_TLS) += tls/
obj-$(CONFIG_XFRM) += xfrm/
obj-$(CONFIG_UNIX) += unix/
obj-$(CONFIG_UNIX_SCM) += unix/
obj-$(CONFIG_NET) += ipv6/
obj-$(CONFIG_BPFILTER) += bpfilter/
obj-$(CONFIG_PACKET) += packet/
Expand Down
5 changes: 5 additions & 0 deletions net/unix/Kconfig
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,11 @@ config UNIX

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
Expand Down
2 changes: 2 additions & 0 deletions net/unix/Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -10,3 +10,5 @@ unix-$(CONFIG_SYSCTL) += sysctl_net_unix.o

obj-$(CONFIG_UNIX_DIAG) += unix_diag.o
unix_diag-y := diag.o

obj-$(CONFIG_UNIX_SCM) += scm.o
63 changes: 2 additions & 61 deletions net/unix/af_unix.c
Original file line number Diff line number Diff line change
Expand Up @@ -119,6 +119,8 @@
#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);
Expand Down Expand Up @@ -1486,67 +1488,6 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
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;
Expand Down
71 changes: 2 additions & 69 deletions net/unix/garbage.c
Original file line number Diff line number Diff line change
Expand Up @@ -86,80 +86,13 @@
#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;
} else {
/* Could be an io_uring instance */
u_sock = io_uring_get_socket(filp);
}
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)
{
Expand Down
151 changes: 151 additions & 0 deletions net/unix/scm.c
Original file line number Diff line number Diff line change
@@ -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);
10 changes: 10 additions & 0 deletions net/unix/scm.h
Original file line number Diff line number Diff line change
@@ -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

0 comments on commit f4e6587

Please sign in to comment.