mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-28 20:02:17 +00:00
![Ulrich Drepper](/assets/img/avatar_default.png)
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>
176 lines
4.9 KiB
C
176 lines
4.9 KiB
C
|
|
#include <linux/linkage.h>
|
|
#include <linux/errno.h>
|
|
|
|
#include <asm/unistd.h>
|
|
|
|
/* we can't #include <linux/syscalls.h> here,
|
|
but tell gcc to not warn with -Wmissing-prototypes */
|
|
asmlinkage long sys_ni_syscall(void);
|
|
|
|
/*
|
|
* Non-implemented system calls get redirected here.
|
|
*/
|
|
asmlinkage long sys_ni_syscall(void)
|
|
{
|
|
return -ENOSYS;
|
|
}
|
|
|
|
cond_syscall(sys_nfsservctl);
|
|
cond_syscall(sys_quotactl);
|
|
cond_syscall(sys32_quotactl);
|
|
cond_syscall(sys_acct);
|
|
cond_syscall(sys_lookup_dcookie);
|
|
cond_syscall(sys_swapon);
|
|
cond_syscall(sys_swapoff);
|
|
cond_syscall(sys_kexec_load);
|
|
cond_syscall(compat_sys_kexec_load);
|
|
cond_syscall(sys_init_module);
|
|
cond_syscall(sys_delete_module);
|
|
cond_syscall(sys_socketpair);
|
|
cond_syscall(sys_bind);
|
|
cond_syscall(sys_listen);
|
|
cond_syscall(sys_accept);
|
|
cond_syscall(sys_accept4);
|
|
cond_syscall(sys_connect);
|
|
cond_syscall(sys_getsockname);
|
|
cond_syscall(sys_getpeername);
|
|
cond_syscall(sys_sendto);
|
|
cond_syscall(sys_send);
|
|
cond_syscall(sys_recvfrom);
|
|
cond_syscall(sys_recv);
|
|
cond_syscall(sys_socket);
|
|
cond_syscall(sys_setsockopt);
|
|
cond_syscall(compat_sys_setsockopt);
|
|
cond_syscall(sys_getsockopt);
|
|
cond_syscall(compat_sys_getsockopt);
|
|
cond_syscall(sys_shutdown);
|
|
cond_syscall(sys_sendmsg);
|
|
cond_syscall(compat_sys_sendmsg);
|
|
cond_syscall(sys_recvmsg);
|
|
cond_syscall(compat_sys_recvmsg);
|
|
cond_syscall(sys_socketcall);
|
|
cond_syscall(sys_futex);
|
|
cond_syscall(compat_sys_futex);
|
|
cond_syscall(sys_set_robust_list);
|
|
cond_syscall(compat_sys_set_robust_list);
|
|
cond_syscall(sys_get_robust_list);
|
|
cond_syscall(compat_sys_get_robust_list);
|
|
cond_syscall(sys_epoll_create);
|
|
cond_syscall(sys_epoll_create1);
|
|
cond_syscall(sys_epoll_ctl);
|
|
cond_syscall(sys_epoll_wait);
|
|
cond_syscall(sys_epoll_pwait);
|
|
cond_syscall(compat_sys_epoll_pwait);
|
|
cond_syscall(sys_semget);
|
|
cond_syscall(sys_semop);
|
|
cond_syscall(sys_semtimedop);
|
|
cond_syscall(sys_semctl);
|
|
cond_syscall(sys_msgget);
|
|
cond_syscall(sys_msgsnd);
|
|
cond_syscall(sys_msgrcv);
|
|
cond_syscall(sys_msgctl);
|
|
cond_syscall(sys_shmget);
|
|
cond_syscall(sys_shmat);
|
|
cond_syscall(sys_shmdt);
|
|
cond_syscall(sys_shmctl);
|
|
cond_syscall(sys_mq_open);
|
|
cond_syscall(sys_mq_unlink);
|
|
cond_syscall(sys_mq_timedsend);
|
|
cond_syscall(sys_mq_timedreceive);
|
|
cond_syscall(sys_mq_notify);
|
|
cond_syscall(sys_mq_getsetattr);
|
|
cond_syscall(compat_sys_mq_open);
|
|
cond_syscall(compat_sys_mq_timedsend);
|
|
cond_syscall(compat_sys_mq_timedreceive);
|
|
cond_syscall(compat_sys_mq_notify);
|
|
cond_syscall(compat_sys_mq_getsetattr);
|
|
cond_syscall(sys_mbind);
|
|
cond_syscall(sys_get_mempolicy);
|
|
cond_syscall(sys_set_mempolicy);
|
|
cond_syscall(compat_sys_mbind);
|
|
cond_syscall(compat_sys_get_mempolicy);
|
|
cond_syscall(compat_sys_set_mempolicy);
|
|
cond_syscall(sys_add_key);
|
|
cond_syscall(sys_request_key);
|
|
cond_syscall(sys_keyctl);
|
|
cond_syscall(compat_sys_keyctl);
|
|
cond_syscall(compat_sys_socketcall);
|
|
cond_syscall(sys_inotify_init);
|
|
cond_syscall(sys_inotify_init1);
|
|
cond_syscall(sys_inotify_add_watch);
|
|
cond_syscall(sys_inotify_rm_watch);
|
|
cond_syscall(sys_migrate_pages);
|
|
cond_syscall(sys_move_pages);
|
|
cond_syscall(sys_chown16);
|
|
cond_syscall(sys_fchown16);
|
|
cond_syscall(sys_getegid16);
|
|
cond_syscall(sys_geteuid16);
|
|
cond_syscall(sys_getgid16);
|
|
cond_syscall(sys_getgroups16);
|
|
cond_syscall(sys_getresgid16);
|
|
cond_syscall(sys_getresuid16);
|
|
cond_syscall(sys_getuid16);
|
|
cond_syscall(sys_lchown16);
|
|
cond_syscall(sys_setfsgid16);
|
|
cond_syscall(sys_setfsuid16);
|
|
cond_syscall(sys_setgid16);
|
|
cond_syscall(sys_setgroups16);
|
|
cond_syscall(sys_setregid16);
|
|
cond_syscall(sys_setresgid16);
|
|
cond_syscall(sys_setresuid16);
|
|
cond_syscall(sys_setreuid16);
|
|
cond_syscall(sys_setuid16);
|
|
cond_syscall(sys_vm86old);
|
|
cond_syscall(sys_vm86);
|
|
cond_syscall(compat_sys_ipc);
|
|
cond_syscall(compat_sys_sysctl);
|
|
cond_syscall(sys_flock);
|
|
cond_syscall(sys_io_setup);
|
|
cond_syscall(sys_io_destroy);
|
|
cond_syscall(sys_io_submit);
|
|
cond_syscall(sys_io_cancel);
|
|
cond_syscall(sys_io_getevents);
|
|
|
|
/* arch-specific weak syscall entries */
|
|
cond_syscall(sys_pciconfig_read);
|
|
cond_syscall(sys_pciconfig_write);
|
|
cond_syscall(sys_pciconfig_iobase);
|
|
cond_syscall(sys32_ipc);
|
|
cond_syscall(sys32_sysctl);
|
|
cond_syscall(ppc_rtas);
|
|
cond_syscall(sys_spu_run);
|
|
cond_syscall(sys_spu_create);
|
|
cond_syscall(sys_subpage_prot);
|
|
|
|
/* mmu depending weak syscall entries */
|
|
cond_syscall(sys_mprotect);
|
|
cond_syscall(sys_msync);
|
|
cond_syscall(sys_mlock);
|
|
cond_syscall(sys_munlock);
|
|
cond_syscall(sys_mlockall);
|
|
cond_syscall(sys_munlockall);
|
|
cond_syscall(sys_mincore);
|
|
cond_syscall(sys_madvise);
|
|
cond_syscall(sys_mremap);
|
|
cond_syscall(sys_remap_file_pages);
|
|
cond_syscall(compat_sys_move_pages);
|
|
cond_syscall(compat_sys_migrate_pages);
|
|
|
|
/* block-layer dependent */
|
|
cond_syscall(sys_bdflush);
|
|
cond_syscall(sys_ioprio_set);
|
|
cond_syscall(sys_ioprio_get);
|
|
|
|
/* New file descriptors */
|
|
cond_syscall(sys_signalfd);
|
|
cond_syscall(sys_signalfd4);
|
|
cond_syscall(compat_sys_signalfd);
|
|
cond_syscall(compat_sys_signalfd4);
|
|
cond_syscall(sys_timerfd_create);
|
|
cond_syscall(sys_timerfd_settime);
|
|
cond_syscall(sys_timerfd_gettime);
|
|
cond_syscall(compat_sys_timerfd_settime);
|
|
cond_syscall(compat_sys_timerfd_gettime);
|
|
cond_syscall(sys_eventfd);
|
|
cond_syscall(sys_eventfd2);
|