user/sven/linux.git/kernel/sys_ni.c, branch v2.6.29.2

[CVE-2009-0029] Make sys_syslog a conditional system call

2009-01-14T13:15:16Z

Remove the -ENOSYS implementation for !CONFIG_PRINTK and use the cond_syscall infrastructure instead. Acked-by: Kyle McMartin Signed-off-by: Heiko Carstens

reintroduce accept4

2008-11-20T02:49:57Z

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 Licensed under the GNU GPLv2 or later. */ #define _GNU_SOURCE #include #include #include #include #include #include #include #include #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 Tested-by: Michael Kerrisk Acked-by: Michael Kerrisk Cc: Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

Configure out AIO support

2008-10-16T18:21:51Z

This patchs adds the CONFIG_AIO option which allows to remove support for asynchronous I/O operations, that are not necessarly used by applications, particularly on embedded devices. As this is a size-reduction option, it depends on CONFIG_EMBEDDED. It allows to save ~7 kilobytes of kernel code/data: text data bss dec hex filename 1115067 119180 217088 1451335 162547 vmlinux 1108025 119048 217088 1444161 160941 vmlinux.new -7042 -132 0 -7174 -1C06 +/- This patch has been originally written by Matt Mackall , and is part of the Linux Tiny project. [randy.dunlap@oracle.com: build fix] Signed-off-by: Thomas Petazzoni Cc: Benjamin LaHaise Cc: Zach Brown Signed-off-by: Matt Mackall Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

Configure out file locking features

2008-09-29T21:56:57Z

This patch adds the CONFIG_FILE_LOCKING option which allows to remove support for advisory locks. With this patch enabled, the flock() system call, the F_GETLK, F_SETLK and F_SETLKW operations of fcntl() and NFS support are disabled. These features are not necessarly needed on embedded systems. It allows to save ~11 Kb of kernel code and data: text data bss dec hex filename 1125436 118764 212992 1457192 163c28 vmlinux.old 1114299 118564 212992 1445855 160fdf vmlinux -11137 -200 0 -11337 -2C49 +/- This patch has originally been written by Matt Mackall , and is part of the Linux Tiny project. Signed-off-by: Thomas Petazzoni Signed-off-by: Matt Mackall Cc: matthew@wil.cx Cc: linux-fsdevel@vger.kernel.org Cc: mpm@selenic.com Cc: akpm@linux-foundation.org Signed-off-by: J. Bruce Fields

signalfd: fix undefined reference to `compat_sys_signalfd4' when !CONFIG_SIGNALFD

2008-07-25T18:35:41Z

fix: arch/x86/ia32/built-in.o: In function `ia32_sys_call_table': (.rodata+0xa38): undefined reference to `compat_sys_signalfd4' on !CONFIG_SIGNALFD. Signed-off-by: Ingo Molnar Signed-off-by: Linus Torvalds

flag parameters: fix compile error of sys_epoll_create1

2008-07-25T17:53:26Z

GEN .version CHK include/linux/compile.h UPD include/linux/compile.h CC init/version.o LD init/built-in.o LD vmlinux arch/x86/kernel/built-in.o: In function `sys_call_table': (.rodata+0x8a4): undefined reference to `sys_epoll_create1' make: *** [vmlinux] Error 1 Signed-off-by: Wang Chen Cc: Ulrich Drepper Cc: Davide Libenzi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

flag parameters: inotify_init

2008-07-24T17:47:28Z

This patch introduces the new syscall inotify_init1 (note: the 1 stands for the one parameter the syscall takes, as opposed to no parameter before). The values accepted for this parameter are function-specific and defined in the inotify.h header. Here the values must match the O_* flags, though. In this patch CLOEXEC support is introduced. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_inotify_init1 # ifdef __x86_64__ # define __NR_inotify_init1 294 # elif defined __i386__ # define __NR_inotify_init1 332 # else # error "need __NR_inotify_init1" # endif #endif #define IN_CLOEXEC O_CLOEXEC int main (void) { int fd; fd = syscall (__NR_inotify_init1, 0); if (fd == -1) { puts ("inotify_init1(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("inotify_init1(0) set close-on-exit"); return 1; } close (fd); fd = syscall (__NR_inotify_init1, IN_CLOEXEC); if (fd == -1) { puts ("inotify_init1(IN_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("inotify_init1(O_CLOEXEC) does not set close-on-exit"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

flag parameters: eventfd

2008-07-24T17:47:27Z

This patch adds the new eventfd2 syscall. It extends the old eventfd syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is EFD_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name EFD_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_eventfd2 # ifdef __x86_64__ # define __NR_eventfd2 290 # elif defined __i386__ # define __NR_eventfd2 328 # else # error "need __NR_eventfd2" # endif #endif #define EFD_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_eventfd2, 1, 0); if (fd == -1) { puts ("eventfd2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("eventfd2(0) sets close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_eventfd2, 1, EFD_CLOEXEC); if (fd == -1) { puts ("eventfd2(EFD_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("eventfd2(EFD_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

flag parameters: signalfd

2008-07-24T17:47:27Z

This patch adds the new signalfd4 syscall. It extends the old signalfd syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is SFD_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name SFD_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_signalfd4 # ifdef __x86_64__ # define __NR_signalfd4 289 # elif defined __i386__ # define __NR_signalfd4 327 # else # error "need __NR_signalfd4" # endif #endif #define SFD_CLOEXEC O_CLOEXEC int main (void) { sigset_t ss; sigemptyset (&ss); sigaddset (&ss, SIGUSR1); int fd = syscall (__NR_signalfd4, -1, &ss, 8, 0); if (fd == -1) { puts ("signalfd4(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("signalfd4(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_signalfd4, -1, &ss, 8, SFD_CLOEXEC); if (fd == -1) { puts ("signalfd4(SFD_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("signalfd4(SFD_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

flag parameters: paccept

2008-07-24T17:47:27Z

This patch is by far the most complex in the series. It adds a new syscall paccept. This syscall differs from accept in that it adds (at the userlevel) two additional parameters: - a signal mask - a flags value The flags parameter can be used to set flag like SOCK_CLOEXEC. This is imlpemented here as well. Some people argued that this is a property which should be inherited from the file desriptor for the server but this is against POSIX. Additionally, we really want the signal mask parameter as well (similar to pselect, ppoll, etc). So an interface change in inevitable. The flag value is the same as for socket and socketpair. I think diverging here will only create confusion. Similar to the filesystem interfaces where the use of the O_* constants differs, it is acceptable here. The signal mask is handled as for pselect etc. The mask is temporarily installed for the thread and removed before the call returns. I modeled the code after pselect. If there is a problem it's likely also in pselect. For architectures which use socketcall I maintained this interface instead of adding a system call. The symmetry shouldn't be broken. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #include #include #include #include #ifndef __NR_paccept # ifdef __x86_64__ # define __NR_paccept 288 # elif defined __i386__ # define SYS_PACCEPT 18 # define USE_SOCKETCALL 1 # else # error "need __NR_paccept" # endif #endif #ifdef USE_SOCKETCALL # define paccept(fd, addr, addrlen, mask, flags) \ ({ long args[6] = { \ (long) fd, (long) addr, (long) addrlen, (long) mask, 8, (long) flags }; \ syscall (__NR_socketcall, SYS_PACCEPT, args); }) #else # define paccept(fd, addr, addrlen, mask, flags) \ syscall (__NR_paccept, fd, addr, addrlen, mask, 8, flags) #endif #define PORT 57392 #define SOCK_CLOEXEC O_CLOEXEC static pthread_barrier_t b; static void * tf (void *arg) { pthread_barrier_wait (&b); int s = socket (AF_INET, SOCK_STREAM, 0); struct sockaddr_in sin; sin.sin_family = AF_INET; sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK); sin.sin_port = htons (PORT); connect (s, (const struct sockaddr *) &sin, sizeof (sin)); close (s); pthread_barrier_wait (&b); s = socket (AF_INET, SOCK_STREAM, 0); sin.sin_port = htons (PORT); connect (s, (const struct sockaddr *) &sin, sizeof (sin)); close (s); pthread_barrier_wait (&b); pthread_barrier_wait (&b); sleep (2); pthread_kill ((pthread_t) arg, SIGUSR1); return NULL; } static void handler (int s) { } int main (void) { pthread_barrier_init (&b, NULL, 2); struct sockaddr_in sin; pthread_t th; if (pthread_create (&th, NULL, tf, (void *) pthread_self ()) != 0) { puts ("pthread_create failed"); return 1; } int s = socket (AF_INET, SOCK_STREAM, 0); int reuse = 1; setsockopt (s, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof (reuse)); sin.sin_family = AF_INET; sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK); sin.sin_port = htons (PORT); bind (s, (struct sockaddr *) &sin, sizeof (sin)); listen (s, SOMAXCONN); pthread_barrier_wait (&b); int s2 = paccept (s, NULL, 0, NULL, 0); if (s2 < 0) { puts ("paccept(0) failed"); return 1; } int coe = fcntl (s2, F_GETFD); if (coe & FD_CLOEXEC) { puts ("paccept(0) set close-on-exec-flag"); return 1; } close (s2); pthread_barrier_wait (&b); s2 = paccept (s, NULL, 0, NULL, SOCK_CLOEXEC); if (s2 < 0) { puts ("paccept(SOCK_CLOEXEC) failed"); return 1; } coe = fcntl (s2, F_GETFD); if ((coe & FD_CLOEXEC) == 0) { puts ("paccept(SOCK_CLOEXEC) does not set close-on-exec flag"); return 1; } close (s2); pthread_barrier_wait (&b); struct sigaction sa; sa.sa_handler = handler; sa.sa_flags = 0; sigemptyset (&sa.sa_mask); sigaction (SIGUSR1, &sa, NULL); sigset_t ss; pthread_sigmask (SIG_SETMASK, NULL, &ss); sigaddset (&ss, SIGUSR1); pthread_sigmask (SIG_SETMASK, &ss, NULL); sigdelset (&ss, SIGUSR1); alarm (4); pthread_barrier_wait (&b); errno = 0 ; s2 = paccept (s, NULL, 0, &ss, 0); if (s2 != -1 || errno != EINTR) { puts ("paccept did not fail with EINTR"); return 1; } close (s); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: make it compile] [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Cc: "David S. Miller" Cc: Roland McGrath Cc: Kyle McMartin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds