aha/kernel
Ulrich Drepper de11defebf reintroduce accept4
Introduce a new accept4() system call.  The addition of this system call
matches analogous changes in 2.6.27 (dup3(), evenfd2(), signalfd4(),
inotify_init1(), epoll_create1(), pipe2()) which added new system calls
that differed from analogous traditional system calls in adding a flags
argument that can be used to access additional functionality.

The accept4() system call is exactly the same as accept(), except that
it adds a flags bit-mask argument.  Two flags are initially implemented.
(Most of the new system calls in 2.6.27 also had both of these flags.)

SOCK_CLOEXEC causes the close-on-exec (FD_CLOEXEC) flag to be enabled
for the new file descriptor returned by accept4().  This is a useful
security feature to avoid leaking information in a multithreaded
program where one thread is doing an accept() at the same time as
another thread is doing a fork() plus exec().  More details here:
http://udrepper.livejournal.com/20407.html "Secure File Descriptor Handling",
Ulrich Drepper).

The other flag is SOCK_NONBLOCK, which causes the O_NONBLOCK flag
to be enabled on the new open file description created by accept4().
(This flag is merely a convenience, saving the use of additional calls
fcntl(F_GETFL) and fcntl (F_SETFL) to achieve the same result.

Here's a test program.  Works on x86-32.  Should work on x86-64, but
I (mtk) don't have a system to hand to test with.

It tests accept4() with each of the four possible combinations of
SOCK_CLOEXEC and SOCK_NONBLOCK set/clear in 'flags', and verifies
that the appropriate flags are set on the file descriptor/open file
description returned by accept4().

I tested Ulrich's patch in this thread by applying against 2.6.28-rc2,
and it passes according to my test program.

/* test_accept4.c

  Copyright (C) 2008, Linux Foundation, written by Michael Kerrisk
       <mtk.manpages@gmail.com>

  Licensed under the GNU GPLv2 or later.
*/
#define _GNU_SOURCE
#include <unistd.h>
#include <sys/syscall.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <stdlib.h>
#include <fcntl.h>
#include <stdio.h>
#include <string.h>

#define PORT_NUM 33333

#define die(msg) do { perror(msg); exit(EXIT_FAILURE); } while (0)

/**********************************************************************/

/* The following is what we need until glibc gets a wrapper for
  accept4() */

/* Flags for socket(), socketpair(), accept4() */
#ifndef SOCK_CLOEXEC
#define SOCK_CLOEXEC    O_CLOEXEC
#endif
#ifndef SOCK_NONBLOCK
#define SOCK_NONBLOCK   O_NONBLOCK
#endif

#ifdef __x86_64__
#define SYS_accept4 288
#elif __i386__
#define USE_SOCKETCALL 1
#define SYS_ACCEPT4 18
#else
#error "Sorry -- don't know the syscall # on this architecture"
#endif

static int
accept4(int fd, struct sockaddr *sockaddr, socklen_t *addrlen, int flags)
{
   printf("Calling accept4(): flags = %x", flags);
   if (flags != 0) {
       printf(" (");
       if (flags & SOCK_CLOEXEC)
           printf("SOCK_CLOEXEC");
       if ((flags & SOCK_CLOEXEC) && (flags & SOCK_NONBLOCK))
           printf(" ");
       if (flags & SOCK_NONBLOCK)
           printf("SOCK_NONBLOCK");
       printf(")");
   }
   printf("\n");

#if USE_SOCKETCALL
   long args[6];

   args[0] = fd;
   args[1] = (long) sockaddr;
   args[2] = (long) addrlen;
   args[3] = flags;

   return syscall(SYS_socketcall, SYS_ACCEPT4, args);
#else
   return syscall(SYS_accept4, fd, sockaddr, addrlen, flags);
#endif
}

/**********************************************************************/

static int
do_test(int lfd, struct sockaddr_in *conn_addr,
       int closeonexec_flag, int nonblock_flag)
{
   int connfd, acceptfd;
   int fdf, flf, fdf_pass, flf_pass;
   struct sockaddr_in claddr;
   socklen_t addrlen;

   printf("=======================================\n");

   connfd = socket(AF_INET, SOCK_STREAM, 0);
   if (connfd == -1)
       die("socket");
   if (connect(connfd, (struct sockaddr *) conn_addr,
               sizeof(struct sockaddr_in)) == -1)
       die("connect");

   addrlen = sizeof(struct sockaddr_in);
   acceptfd = accept4(lfd, (struct sockaddr *) &claddr, &addrlen,
                      closeonexec_flag | nonblock_flag);
   if (acceptfd == -1) {
       perror("accept4()");
       close(connfd);
       return 0;
   }

   fdf = fcntl(acceptfd, F_GETFD);
   if (fdf == -1)
       die("fcntl:F_GETFD");
   fdf_pass = ((fdf & FD_CLOEXEC) != 0) ==
              ((closeonexec_flag & SOCK_CLOEXEC) != 0);
   printf("Close-on-exec flag is %sset (%s); ",
           (fdf & FD_CLOEXEC) ? "" : "not ",
           fdf_pass ? "OK" : "failed");

   flf = fcntl(acceptfd, F_GETFL);
   if (flf == -1)
       die("fcntl:F_GETFD");
   flf_pass = ((flf & O_NONBLOCK) != 0) ==
              ((nonblock_flag & SOCK_NONBLOCK) !=0);
   printf("nonblock flag is %sset (%s)\n",
           (flf & O_NONBLOCK) ? "" : "not ",
           flf_pass ? "OK" : "failed");

   close(acceptfd);
   close(connfd);

   printf("Test result: %s\n", (fdf_pass && flf_pass) ? "PASS" : "FAIL");
   return fdf_pass && flf_pass;
}

static int
create_listening_socket(int port_num)
{
   struct sockaddr_in svaddr;
   int lfd;
   int optval;

   memset(&svaddr, 0, sizeof(struct sockaddr_in));
   svaddr.sin_family = AF_INET;
   svaddr.sin_addr.s_addr = htonl(INADDR_ANY);
   svaddr.sin_port = htons(port_num);

   lfd = socket(AF_INET, SOCK_STREAM, 0);
   if (lfd == -1)
       die("socket");

   optval = 1;
   if (setsockopt(lfd, SOL_SOCKET, SO_REUSEADDR, &optval,
                  sizeof(optval)) == -1)
       die("setsockopt");

   if (bind(lfd, (struct sockaddr *) &svaddr,
            sizeof(struct sockaddr_in)) == -1)
       die("bind");

   if (listen(lfd, 5) == -1)
       die("listen");

   return lfd;
}

int
main(int argc, char *argv[])
{
   struct sockaddr_in conn_addr;
   int lfd;
   int port_num;
   int passed;

   passed = 1;

   port_num = (argc > 1) ? atoi(argv[1]) : PORT_NUM;

   memset(&conn_addr, 0, sizeof(struct sockaddr_in));
   conn_addr.sin_family = AF_INET;
   conn_addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
   conn_addr.sin_port = htons(port_num);

   lfd = create_listening_socket(port_num);

   if (!do_test(lfd, &conn_addr, 0, 0))
       passed = 0;
   if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, 0))
       passed = 0;
   if (!do_test(lfd, &conn_addr, 0, SOCK_NONBLOCK))
       passed = 0;
   if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, SOCK_NONBLOCK))
       passed = 0;

   close(lfd);

   exit(passed ? EXIT_SUCCESS : EXIT_FAILURE);
}

[mtk.manpages@gmail.com: rewrote changelog, updated test program]
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Tested-by: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <linux-api@vger.kernel.org>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-19 18:49:57 -08:00
..
irq irq: make variable static 2008-10-22 07:37:17 +02:00
power suspend: use WARN not WARN_ON to print the message 2008-11-18 08:07:36 -08:00
time nohz: disable tick_nohz_kick_tick() for now 2008-11-10 22:39:27 +01:00
trace function tracing: fix wrong pos computing when read buffer has been fulfilled 2008-11-16 08:32:05 +01:00
.gitignore
acct.c tty: Fix abusers of current->sighand->tty 2008-10-13 09:51:42 -07:00
audit.c [PATCH] Fix the bug of using AUDIT_STATUS_RATE_LIMIT when set fail, no error output. 2008-08-01 12:15:16 -04:00
audit.h
audit_tree.c Fix inotify watch removal/umount races 2008-11-15 12:26:44 -08:00
auditfilter.c Fix inotify watch removal/umount races 2008-11-15 12:26:44 -08:00
auditsc.c tty: Fix abusers of current->sighand->tty 2008-10-13 09:51:42 -07:00
backtracetest.c
bounds.c
capability.c security: Fix setting of PF_SUPERPRIV by __capable() 2008-08-14 22:59:43 +10:00
cgroup.c cgroups: fix invalid cgrp->dentry before cgroup has been completely removed 2008-11-06 15:41:19 -08:00
cgroup_debug.c cgroups: fix probable race with put_css_set[_taskexit] and find_css_set 2008-10-20 08:52:38 -07:00
cgroup_freezer.c freezer_cg: disable writing freezer.state of root cgroup 2008-11-12 17:17:16 -08:00
compat.c Merge branches 'timers/clocksource', 'timers/hrtimers', 'timers/nohz', 'timers/ntp', 'timers/posixtimers' and 'timers/debug' into v28-timers-for-linus 2008-10-20 13:14:06 +02:00
configs.c kernel/configs.c: remove useless comments 2008-10-20 08:52:34 -07:00
cpu.c cpumask: introduce new API, without changing anything 2008-11-06 09:05:33 +01:00
cpuset.c cpuset: fix regression when failed to generate sched domains 2008-11-18 08:44:51 +01:00
delayacct.c per-task-delay-accounting: update taskstats for memory reclaim delay 2008-07-25 10:53:47 -07:00
dma-coherent.c dma-coherent: export dma_[alloc|release]_from_coherent methods 2008-08-22 08:34:53 +02:00
dma.c kernel/dma.c: remove a CVS keyword 2008-10-16 11:21:30 -07:00
exec_domain.c proc: move /proc/execdomains to kernel/exec_domain.c 2008-10-23 14:30:41 +04:00
exit.c Move "exit_robust_list" into mm_release() 2008-11-15 10:20:36 -08:00
extable.c
fork.c Move "exit_robust_list" into mm_release() 2008-11-15 10:20:36 -08:00
freezer.c freezer_cg: use thaw_process() in unfreeze_cgroup() 2008-10-30 11:38:45 -07:00
futex.c hrtimer: make the futex() system call use the per process slack value 2008-09-11 07:17:00 -07:00
futex_compat.c
hrtimer.c hrtimer: clean up unused callback modes 2008-11-12 09:54:40 +01:00
itimer.c timers: fix itimer/many thread hang 2008-09-14 16:25:35 +02:00
kallsyms.c kernel/kallsyms.c: fix double return 2008-10-16 11:21:32 -07:00
Kconfig.freezer container freezer: implement freezer cgroup subsystem 2008-10-20 08:52:34 -07:00
Kconfig.hz sched: fix SCHED_HRTICK dependency 2008-07-28 14:37:38 +02:00
Kconfig.preempt
kexec.c kexec: fix crash_save_vmcoreinfo_init build problem 2008-10-20 15:28:50 -07:00
kfifo.c
kgdb.c kgdb: call touch_softlockup_watchdog on resume 2008-10-06 13:50:59 -05:00
kmod.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus 2008-10-16 12:38:34 -07:00
kprobes.c kernel/kprobes.c: don't pad kretprobe_table_locks[] on uniprocessor builds 2008-11-12 17:17:17 -08:00
ksysfs.c profiling: dynamically enable readprofile at runtime 2008-10-16 11:21:31 -07:00
kthread.c Merge branch 'tracing-v28-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2008-10-20 13:35:07 -07:00
latencytop.c
lockdep.c lockdep: fix irqs on/off ip tracing 2008-10-28 11:19:07 +01:00
lockdep_internals.h lockdep: build fix 2008-08-13 12:55:10 +02:00
lockdep_proc.c lockstat: fix numerical output rounding error 2008-08-26 10:37:46 +02:00
Makefile Remove -mno-spe flags as they dont belong 2008-11-17 13:24:35 -08:00
marker.c markers: bit-field is not thread-safe nor smp-safe 2008-10-14 10:38:45 +02:00
module.c Merge branch 'proc' of git://git.kernel.org/pub/scm/linux/kernel/git/adobriyan/proc 2008-10-23 12:04:37 -07:00
mutex-debug.c
mutex-debug.h
mutex.c locking: fix mutex @key parameter kernel-doc notation 2008-07-28 18:12:36 +02:00
mutex.h
notifier.c ftrace: ignore functions that cannot be kprobe-ed 2008-10-14 10:34:22 +02:00
ns_cgroup.c cgroup_clone: use pid of newly created task for new cgroup 2008-07-25 10:53:37 -07:00
nsproxy.c removed unused #include <linux/version.h>'s 2008-08-23 12:14:12 -07:00
panic.c Make panic= and panic_on_oops into core_params 2008-10-22 10:00:25 +11:00
params.c Fix compile warning in kernel/params.c 2008-10-23 12:09:00 -07:00
pid.c pidns: remove now unused find_pid function. 2008-07-25 10:53:45 -07:00
pid_namespace.c pid_ns: (BUG 11391) change ->child_reaper when init->group_leader exits 2008-09-02 19:21:38 -07:00
pm_qos_params.c pm_qos_requirement might sleep 2008-09-02 19:21:40 -07:00
posix-cpu-timers.c sched, signals: fix the racy usage of ->signal in account_group_xxx/run_posix_cpu_timers 2008-11-17 16:49:35 +01:00
posix-timers.c Merge branch 'timers/range-hrtimers' into v28-range-hrtimers-for-linus-v2 2008-10-22 09:48:06 +02:00
printk.c printk: remove unused code from kernel/printk.c 2008-10-23 21:54:29 +02:00
profile.c kernel/profile.c: fix section mismatch warning 2008-11-18 08:49:24 +01:00
ptrace.c make ptrace_untrace() static 2008-10-20 08:52:39 -07:00
rcuclassic.c rcu: RCU-based detection of stalled CPUs for Classic RCU, fix 2008-10-03 10:41:00 +02:00
rcupdate.c rcupdate: fix bug of rcu_barrier*() 2008-10-21 15:59:53 +02:00
rcupreempt.c byteorder: remove direct includes of linux/byteorder/swab[b].h 2008-10-20 08:52:40 -07:00
rcupreempt_trace.c rcu: trace fix possible mem-leak 2008-08-15 17:54:40 +02:00
rcutorture.c byteorder: remove direct includes of linux/byteorder/swab[b].h 2008-10-20 12:51:53 -07:00
relay.c relay: fix cpu offline problem 2008-11-18 15:08:56 +01:00
res_counter.c cgroup files: convert res_counter_write() to be a cgroups write_string() handler 2008-07-25 10:53:36 -07:00
resource.c reserve_region_with_split: Fix GFP_KERNEL usage under spinlock 2008-11-01 09:53:58 -07:00
rtmutex-debug.c
rtmutex-debug.h
rtmutex-tester.c
rtmutex.c hrtimer: convert kernel/* to the new hrtimer apis 2008-09-05 21:35:13 -07:00
rtmutex.h
rtmutex_common.h
rwsem.c
sched.c cpuset: fix regression when failed to generate sched domains 2008-11-18 08:44:51 +01:00
sched_clock.c sched_clock: prevent scd->clock from moving backwards 2008-10-10 11:17:04 +02:00
sched_cpupri.c
sched_cpupri.h
sched_debug.c sched: fix kernel warning on /proc/sched_debug access 2008-11-16 08:07:15 +01:00
sched_fair.c sched: release buddies on yield 2008-11-11 11:57:22 +01:00
sched_features.h sched: backward looking buddy 2008-11-05 10:30:14 +01:00
sched_idletask.c sched: add CONFIG_SMP consistency 2008-10-22 10:01:52 +02:00
sched_rt.c Merge commit 'v2.6.28-rc1' into sched/urgent 2008-10-24 12:48:46 +02:00
sched_stats.h sched, signals: fix the racy usage of ->signal in account_group_xxx/run_posix_cpu_timers 2008-11-17 16:49:35 +01:00
seccomp.c
semaphore.c semaphore: __down_common: use signal_pending_state() 2008-08-05 14:33:47 -07:00
signal.c 'kill sig -1' must only apply to caller's namespace 2008-10-30 11:38:46 -07:00
smp.c generic-ipi: fix the smp_mb() placement 2008-11-06 08:41:56 +01:00
softirq.c irq: call __irq_enter() before calling the tick_idle_check 2008-11-10 22:36:39 +01:00
softlockup.c Make the taint flags reliable 2008-10-16 11:21:31 -07:00
spinlock.c lockdep: spin_lock_nest_lock(), checkpatch fixes 2008-08-13 13:56:51 +02:00
srcu.c
stacktrace.c
stop_machine.c stop_machine: fix race with return value (fixes Bug #11989) 2008-11-16 15:09:52 -08:00
sys.c Merge branch 'timers/range-hrtimers' into v28-range-hrtimers-for-linus-v2 2008-10-22 09:48:06 +02:00
sys_ni.c reintroduce accept4 2008-11-19 18:49:57 -08:00
sysctl.c Merge commit 'v2.6.28-rc2' into tracing/urgent 2008-10-27 10:50:54 +01:00
sysctl_check.c sysctl: check for bogus modes 2008-07-25 10:53:45 -07:00
taskstats.c taskstats: remove initialization of static per-cpu variable 2008-07-25 10:53:47 -07:00
test_kprobes.c
time.c select: add a timespec_add_safe() function 2008-09-05 21:34:57 -07:00
timeconst.pl
timer.c Add round_jiffies_up and related routines 2008-11-06 08:42:48 +01:00
tracepoint.c tracepoint: check if the probe has been registered 2008-10-27 16:45:46 +01:00
tsacct.c task IO accounting: move all IO statistics in struct task_io_accounting 2008-07-27 16:12:28 -07:00
uid16.c
user.c sched: rt-bandwidth for user grouping interface 2008-08-19 13:10:09 +02:00
user_namespace.c removed unused #include <linux/version.h>'s 2008-08-23 12:14:12 -07:00
utsname.c removed unused #include <linux/version.h>'s 2008-08-23 12:14:12 -07:00
utsname_sysctl.c sysctl: simplify ->strategy 2008-10-16 11:21:47 -07:00
wait.c wait: kill is_sync_wait() 2008-10-16 11:21:31 -07:00
workqueue.c cpumask: introduce new API, without changing anything 2008-11-06 09:05:33 +01:00