From 5f17156fc55abac476d180e480bedb0f07f01b14 Mon Sep 17 00:00:00 2001 From: Atsushi Nemoto Date: Mon, 21 Jul 2008 14:21:37 -0700 Subject: Fix build on COMPAT platforms when CONFIG_EPOLL is disabled Add missing cond_syscall() entry for compat_sys_epoll_pwait. Signed-off-by: Atsushi Nemoto Cc: Davide Libenzi Cc: [2.6.25.x, 2.6.26.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys_ni.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/sys_ni.c') diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 5b9b467de070..0fea0ee12da9 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -59,6 +59,7 @@ cond_syscall(sys_epoll_create); 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); -- cgit v1.2.3 From aaca0bdca573f3f51ea03139f9c7289541e7bca3 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:20 -0700 Subject: flag parameters: paccept 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 --- include/asm-alpha/socket.h | 5 +++ include/asm-parisc/socket.h | 5 +++ include/asm-x86/unistd_64.h | 2 ++ include/linux/net.h | 3 ++ include/linux/syscalls.h | 2 ++ kernel/sys_ni.c | 1 + net/compat.c | 52 ++++++++++++++++++++++++++--- net/socket.c | 81 ++++++++++++++++++++++++++++++++++++++++----- 8 files changed, 139 insertions(+), 12 deletions(-) (limited to 'kernel/sys_ni.c') diff --git a/include/asm-alpha/socket.h b/include/asm-alpha/socket.h index 08c979319929..a1057c2d95e7 100644 --- a/include/asm-alpha/socket.h +++ b/include/asm-alpha/socket.h @@ -62,4 +62,9 @@ #define SO_MARK 36 +/* O_NONBLOCK clashes with the bits used for socket types. Therefore we + * have to define SOCK_NONBLOCK to a different value here. + */ +#define SOCK_NONBLOCK 0x40000000 + #endif /* _ASM_SOCKET_H */ diff --git a/include/asm-parisc/socket.h b/include/asm-parisc/socket.h index 69a7a0d30b02..fba402c95ac2 100644 --- a/include/asm-parisc/socket.h +++ b/include/asm-parisc/socket.h @@ -54,4 +54,9 @@ #define SO_MARK 0x401f +/* O_NONBLOCK clashes with the bits used for socket types. Therefore we + * have to define SOCK_NONBLOCK to a different value here. + */ +#define SOCK_NONBLOCK 0x40000000 + #endif /* _ASM_SOCKET_H */ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index 9c1a4a3470d9..e323994a370f 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -639,6 +639,8 @@ __SYSCALL(__NR_fallocate, sys_fallocate) __SYSCALL(__NR_timerfd_settime, sys_timerfd_settime) #define __NR_timerfd_gettime 287 __SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime) +#define __NR_paccept 288 +__SYSCALL(__NR_paccept, sys_paccept) #ifndef __NO_STUBS diff --git a/include/linux/net.h b/include/linux/net.h index 8b5383c45b45..3a9b06d4d0fe 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -47,6 +47,7 @@ struct net; #define SYS_GETSOCKOPT 15 /* sys_getsockopt(2) */ #define SYS_SENDMSG 16 /* sys_sendmsg(2) */ #define SYS_RECVMSG 17 /* sys_recvmsg(2) */ +#define SYS_PACCEPT 18 /* sys_paccept(2) */ typedef enum { SS_FREE = 0, /* not allocated */ @@ -219,6 +220,8 @@ extern int sock_map_fd(struct socket *sock, int flags); extern struct socket *sockfd_lookup(int fd, int *err); #define sockfd_put(sock) fput(sock->file) extern int net_ratelimit(void); +extern long do_accept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags); #define net_random() random32() #define net_srandom(seed) srandom32((__force u32)seed) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 4394dadff813..2a2a40af6b2c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -409,6 +409,8 @@ asmlinkage long sys_getsockopt(int fd, int level, int optname, asmlinkage long sys_bind(int, struct sockaddr __user *, int); asmlinkage long sys_connect(int, struct sockaddr __user *, int); asmlinkage long sys_accept(int, struct sockaddr __user *, int __user *); +asmlinkage long sys_paccept(int, struct sockaddr __user *, int __user *, + const sigset_t *, size_t, int); asmlinkage long sys_getsockname(int, struct sockaddr __user *, int __user *); asmlinkage long sys_getpeername(int, struct sockaddr __user *, int __user *); asmlinkage long sys_send(int, void __user *, size_t, unsigned); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 0fea0ee12da9..2f0b8a2e600f 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -31,6 +31,7 @@ cond_syscall(sys_socketpair); cond_syscall(sys_bind); cond_syscall(sys_listen); cond_syscall(sys_accept); +cond_syscall(sys_paccept); cond_syscall(sys_connect); cond_syscall(sys_getsockname); cond_syscall(sys_getpeername); diff --git a/net/compat.c b/net/compat.c index 6e1b03b51933..67fb6a3834a3 100644 --- a/net/compat.c +++ b/net/compat.c @@ -722,9 +722,10 @@ EXPORT_SYMBOL(compat_mc_getsockopt); /* Argument list sizes for compat_sys_socketcall */ #define AL(x) ((x) * sizeof(u32)) -static unsigned char nas[18]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), +static unsigned char nas[19]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), AL(3),AL(3),AL(4),AL(4),AL(4),AL(6), - AL(6),AL(2),AL(5),AL(5),AL(3),AL(3)}; + AL(6),AL(2),AL(5),AL(5),AL(3),AL(3), + AL(6)}; #undef AL asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags) @@ -737,13 +738,52 @@ asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, uns return sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } +asmlinkage long compat_sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize, int flags) +{ + compat_sigset_t ss32; + sigset_t ksigmask, sigsaved; + int ret; + + if (sigmask) { + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&ss32, sigmask, sizeof(ss32))) + return -EFAULT; + sigset_from_compat(&ksigmask, &ss32); + + sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + + ret = do_accept(fd, upeer_sockaddr, upeer_addrlen, flags); + + if (ret == -ERESTARTNOHAND) { + /* + * Don't restore the signal mask yet. Let do_signal() deliver + * the signal on the way back to userspace, before the signal + * mask is restored. + */ + if (sigmask) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } + } else if (sigmask) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + return ret; +} + asmlinkage long compat_sys_socketcall(int call, u32 __user *args) { int ret; u32 a[6]; u32 a0, a1; - if (call < SYS_SOCKET || call > SYS_RECVMSG) + if (call < SYS_SOCKET || call > SYS_PACCEPT) return -EINVAL; if (copy_from_user(a, args, nas[call])) return -EFAULT; @@ -764,7 +804,7 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args) ret = sys_listen(a0, a1); break; case SYS_ACCEPT: - ret = sys_accept(a0, compat_ptr(a1), compat_ptr(a[2])); + ret = do_accept(a0, compat_ptr(a1), compat_ptr(a[2]), 0); break; case SYS_GETSOCKNAME: ret = sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2])); @@ -804,6 +844,10 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args) case SYS_RECVMSG: ret = compat_sys_recvmsg(a0, compat_ptr(a1), a[2]); break; + case SYS_PACCEPT: + ret = compat_sys_paccept(a0, compat_ptr(a1), compat_ptr(a[2]), + compat_ptr(a[3]), a[4], a[5]); + break; default: ret = -EINVAL; break; diff --git a/net/socket.c b/net/socket.c index 64601f900352..a0ce8ad72252 100644 --- a/net/socket.c +++ b/net/socket.c @@ -63,6 +63,7 @@ #include #include #include +#include #include #include #include @@ -1225,6 +1226,9 @@ asmlinkage long sys_socket(int family, int type, int protocol) return -EINVAL; type &= SOCK_TYPE_MASK; + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + retval = sock_create(family, type, protocol, &sock); if (retval < 0) goto out; @@ -1259,6 +1263,9 @@ asmlinkage long sys_socketpair(int family, int type, int protocol, return -EINVAL; type &= SOCK_TYPE_MASK; + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + /* * Obtain the first socket and check if the underlying protocol * supports the socketpair call. @@ -1413,14 +1420,20 @@ asmlinkage long sys_listen(int fd, int backlog) * clean when we restucture accept also. */ -asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen) +long do_accept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; int err, len, newfd, fput_needed; struct sockaddr_storage address; + if (flags & ~SOCK_CLOEXEC) + return -EINVAL; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1438,7 +1451,7 @@ asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, */ __module_get(newsock->ops->owner); - newfd = sock_alloc_fd(&newfile, 0); + newfd = sock_alloc_fd(&newfile, flags & O_CLOEXEC); if (unlikely(newfd < 0)) { err = newfd; sock_release(newsock); @@ -1491,6 +1504,50 @@ out_fd: goto out_put; } +asmlinkage long sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, + const sigset_t __user *sigmask, + size_t sigsetsize, int flags) +{ + sigset_t ksigmask, sigsaved; + int ret; + + if (sigmask) { + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask))) + return -EFAULT; + + sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + + ret = do_accept(fd, upeer_sockaddr, upeer_addrlen, flags); + + if (ret < 0 && signal_pending(current)) { + /* + * Don't restore the signal mask yet. Let do_signal() deliver + * the signal on the way back to userspace, before the signal + * mask is restored. + */ + if (sigmask) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } + } else if (sigmask) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + return ret; +} + +asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen) +{ + return do_accept(fd, upeer_sockaddr, upeer_addrlen, 0); +} + /* * Attempt to connect to a socket with the server address. The address * is in user space so we verify it is OK and move it to kernel space. @@ -2011,10 +2068,11 @@ out: /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) -static const unsigned char nargs[18]={ +static const unsigned char nargs[19]={ AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), AL(3),AL(3),AL(4),AL(4),AL(4),AL(6), - AL(6),AL(2),AL(5),AL(5),AL(3),AL(3) + AL(6),AL(2),AL(5),AL(5),AL(3),AL(3), + AL(6) }; #undef AL @@ -2033,7 +2091,7 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) unsigned long a0, a1; int err; - if (call < 1 || call > SYS_RECVMSG) + if (call < 1 || call > SYS_PACCEPT) return -EINVAL; /* copy_from_user should be SMP safe. */ @@ -2062,8 +2120,8 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) break; case SYS_ACCEPT: err = - sys_accept(a0, (struct sockaddr __user *)a1, - (int __user *)a[2]); + do_accept(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = @@ -2110,6 +2168,13 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) case SYS_RECVMSG: err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]); break; + case SYS_PACCEPT: + err = + sys_paccept(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], + (const sigset_t __user *) a[3], + a[4], a[5]); + break; default: err = -EINVAL; break; -- cgit v1.2.3 From 9deb27baedb79759c3ab9435a7d8b841842d56e9 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:24 -0700 Subject: flag parameters: signalfd 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 --- arch/x86/ia32/ia32entry.S | 1 + arch/x86/kernel/syscall_table_32.S | 1 + fs/compat.c | 14 ++++++++++---- fs/signalfd.c | 14 ++++++++++++-- include/asm-x86/unistd_32.h | 1 + include/asm-x86/unistd_64.h | 2 ++ include/linux/signalfd.h | 5 +++++ include/linux/syscalls.h | 1 + kernel/sys_ni.c | 1 + 9 files changed, 34 insertions(+), 6 deletions(-) (limited to 'kernel/sys_ni.c') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 021d71bc69b5..c308128b9251 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -826,4 +826,5 @@ ia32_sys_call_table: .quad sys32_fallocate .quad compat_sys_timerfd_settime /* 325 */ .quad compat_sys_timerfd_gettime + .quad compat_sys_signalfd4 ia32_syscall_end: diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index adff5562f5fd..c12a36c9fd51 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -326,3 +326,4 @@ ENTRY(sys_call_table) .long sys_fallocate .long sys_timerfd_settime /* 325 */ .long sys_timerfd_gettime + .long sys_signalfd4 diff --git a/fs/compat.c b/fs/compat.c index b46604281766..106eba28ec5a 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -2131,9 +2131,9 @@ asmlinkage long compat_sys_epoll_pwait(int epfd, #ifdef CONFIG_SIGNALFD -asmlinkage long compat_sys_signalfd(int ufd, - const compat_sigset_t __user *sigmask, - compat_size_t sigsetsize) +asmlinkage long compat_sys_signalfd4(int ufd, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize, int flags) { compat_sigset_t ss32; sigset_t tmp; @@ -2148,9 +2148,15 @@ asmlinkage long compat_sys_signalfd(int ufd, if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t))) return -EFAULT; - return sys_signalfd(ufd, ksigmask, sizeof(sigset_t)); + return sys_signalfd4(ufd, ksigmask, sizeof(sigset_t), flags); } +asmlinkage long compat_sys_signalfd(int ufd, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize) +{ + return compat_sys_signalfd4(ufd, sigmask, sigsetsize, 0); +} #endif /* CONFIG_SIGNALFD */ #ifdef CONFIG_TIMERFD diff --git a/fs/signalfd.c b/fs/signalfd.c index ddb328b74bde..c8609fa51a13 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -205,11 +205,15 @@ static const struct file_operations signalfd_fops = { .read = signalfd_read, }; -asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask) +asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, + size_t sizemask, int flags) { sigset_t sigmask; struct signalfd_ctx *ctx; + if (flags & ~SFD_CLOEXEC) + return -EINVAL; + if (sizemask != sizeof(sigset_t) || copy_from_user(&sigmask, user_mask, sizeof(sigmask))) return -EINVAL; @@ -228,7 +232,7 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas * anon_inode_getfd() will install the fd. */ ufd = anon_inode_getfd("[signalfd]", &signalfd_fops, ctx, - 0); + flags & O_CLOEXEC); if (ufd < 0) kfree(ctx); } else { @@ -250,3 +254,9 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas return ufd; } + +asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, + size_t sizemask) +{ + return sys_signalfd4(ufd, user_mask, sizemask, 0); +} diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index 8317d94771d3..c310371f5613 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -332,6 +332,7 @@ #define __NR_fallocate 324 #define __NR_timerfd_settime 325 #define __NR_timerfd_gettime 326 +#define __NR_signalfd4 327 #ifdef __KERNEL__ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index e323994a370f..e0a9b45b2346 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -641,6 +641,8 @@ __SYSCALL(__NR_timerfd_settime, sys_timerfd_settime) __SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime) #define __NR_paccept 288 __SYSCALL(__NR_paccept, sys_paccept) +#define __NR_signalfd4 289 +__SYSCALL(__NR_signalfd4, sys_signalfd4) #ifndef __NO_STUBS diff --git a/include/linux/signalfd.h b/include/linux/signalfd.h index ea037f28df91..8b3f7b7420a1 100644 --- a/include/linux/signalfd.h +++ b/include/linux/signalfd.h @@ -8,6 +8,11 @@ #ifndef _LINUX_SIGNALFD_H #define _LINUX_SIGNALFD_H +/* For O_CLOEXEC */ +#include + +/* Flags for signalfd4. */ +#define SFD_CLOEXEC O_CLOEXEC struct signalfd_siginfo { __u32 ssi_signo; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2a2a40af6b2c..1c2707797845 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -610,6 +610,7 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache); asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask); +asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, size_t sizemask, int flags); asmlinkage long sys_timerfd_create(int clockid, int flags); asmlinkage long sys_timerfd_settime(int ufd, int flags, const struct itimerspec __user *utmr, diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 2f0b8a2e600f..8627c89ae9e8 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -156,6 +156,7 @@ cond_syscall(sys_ioprio_get); /* New file descriptors */ cond_syscall(sys_signalfd); +cond_syscall(sys_signalfd4); cond_syscall(compat_sys_signalfd); cond_syscall(sys_timerfd_create); cond_syscall(sys_timerfd_settime); -- cgit v1.2.3 From b087498eb5605673b0f260a7620d91818cd72304 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:25 -0700 Subject: flag parameters: eventfd 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 --- arch/x86/ia32/ia32entry.S | 1 + arch/x86/kernel/syscall_table_32.S | 1 + fs/eventfd.c | 13 +++++++++++-- include/asm-x86/unistd_32.h | 1 + include/asm-x86/unistd_64.h | 2 ++ include/linux/eventfd.h | 6 ++++++ include/linux/syscalls.h | 1 + kernel/sys_ni.c | 1 + 8 files changed, 24 insertions(+), 2 deletions(-) (limited to 'kernel/sys_ni.c') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index c308128b9251..cf0eb31745ca 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -827,4 +827,5 @@ ia32_sys_call_table: .quad compat_sys_timerfd_settime /* 325 */ .quad compat_sys_timerfd_gettime .quad compat_sys_signalfd4 + .quad sys_eventfd2 ia32_syscall_end: diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index c12a36c9fd51..cf112cb11c37 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -327,3 +327,4 @@ ENTRY(sys_call_table) .long sys_timerfd_settime /* 325 */ .long sys_timerfd_gettime .long sys_signalfd4 + .long sys_eventfd2 diff --git a/fs/eventfd.c b/fs/eventfd.c index 6094265ca409..bd420e6478ad 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -198,11 +198,14 @@ struct file *eventfd_fget(int fd) return file; } -asmlinkage long sys_eventfd(unsigned int count) +asmlinkage long sys_eventfd2(unsigned int count, int flags) { int fd; struct eventfd_ctx *ctx; + if (flags & ~EFD_CLOEXEC) + return -EINVAL; + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; @@ -214,9 +217,15 @@ asmlinkage long sys_eventfd(unsigned int count) * When we call this, the initialization must be complete, since * anon_inode_getfd() will install the fd. */ - fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx, 0); + fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx, + flags & O_CLOEXEC); if (fd < 0) kfree(ctx); return fd; } +asmlinkage long sys_eventfd(unsigned int count) +{ + return sys_eventfd2(count, 0); +} + diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index c310371f5613..edbd8723c939 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -333,6 +333,7 @@ #define __NR_timerfd_settime 325 #define __NR_timerfd_gettime 326 #define __NR_signalfd4 327 +#define __NR_eventfd2 328 #ifdef __KERNEL__ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index e0a9b45b2346..fb059a6feeb1 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -643,6 +643,8 @@ __SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime) __SYSCALL(__NR_paccept, sys_paccept) #define __NR_signalfd4 289 __SYSCALL(__NR_signalfd4, sys_signalfd4) +#define __NR_eventfd2 290 +__SYSCALL(__NR_eventfd2, sys_eventfd2) #ifndef __NO_STUBS diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index a701399b7fed..a6c0eaedb1b0 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -10,6 +10,12 @@ #ifdef CONFIG_EVENTFD +/* For O_CLOEXEC */ +#include + +/* Flags for eventfd2. */ +#define EFD_CLOEXEC O_CLOEXEC + struct file *eventfd_fget(int fd); int eventfd_signal(struct file *file, int n); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1c2707797845..9ab09926a7f2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -617,6 +617,7 @@ asmlinkage long sys_timerfd_settime(int ufd, int flags, struct itimerspec __user *otmr); asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); asmlinkage long sys_eventfd(unsigned int count); +asmlinkage long sys_eventfd2(unsigned int count, int flags); asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); int kernel_execve(const char *filename, char *const argv[], char *const envp[]); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 8627c89ae9e8..2a361ccdc7ca 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -164,3 +164,4 @@ 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); -- cgit v1.2.3 From 4006553b06306b34054529477b06b68a1c66249b Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:32 -0700 Subject: flag parameters: inotify_init 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 --- arch/x86/ia32/ia32entry.S | 1 + arch/x86/kernel/syscall_table_32.S | 1 + fs/inotify_user.c | 12 ++++++++++-- include/asm-x86/unistd_32.h | 1 + include/asm-x86/unistd_64.h | 2 ++ include/linux/inotify.h | 5 +++++ include/linux/syscalls.h | 1 + kernel/sys_ni.c | 1 + 8 files changed, 22 insertions(+), 2 deletions(-) (limited to 'kernel/sys_ni.c') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 18808b164570..4541073dd837 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -831,4 +831,5 @@ ia32_sys_call_table: .quad sys_epoll_create2 .quad sys_dup3 /* 330 */ .quad sys_pipe2 + .quad sys_inotify_init1 ia32_syscall_end: diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 66154769d52f..f59aba5ff0f0 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -331,3 +331,4 @@ ENTRY(sys_call_table) .long sys_epoll_create2 .long sys_dup3 /* 330 */ .long sys_pipe2 + .long sys_inotify_init1 diff --git a/fs/inotify_user.c b/fs/inotify_user.c index 6676c06bb7c1..851005998cd4 100644 --- a/fs/inotify_user.c +++ b/fs/inotify_user.c @@ -566,7 +566,7 @@ static const struct inotify_operations inotify_user_ops = { .destroy_watch = free_inotify_user_watch, }; -asmlinkage long sys_inotify_init(void) +asmlinkage long sys_inotify_init1(int flags) { struct inotify_device *dev; struct inotify_handle *ih; @@ -574,7 +574,10 @@ asmlinkage long sys_inotify_init(void) struct file *filp; int fd, ret; - fd = get_unused_fd(); + if (flags & ~IN_CLOEXEC) + return -EINVAL; + + fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; @@ -638,6 +641,11 @@ out_put_fd: return ret; } +asmlinkage long sys_inotify_init(void) +{ + return sys_inotify_init1(0); +} + asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask) { struct inode *inode; diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index 748a05c77da4..b3daf503ab93 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -337,6 +337,7 @@ #define __NR_epoll_create2 329 #define __NR_dup3 330 #define __NR_pipe2 331 +#define __NR_inotify_init1 332 #ifdef __KERNEL__ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index d2284b43ad58..c8cb88d70c6b 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -651,6 +651,8 @@ __SYSCALL(__NR_epoll_create2, sys_epoll_create2) __SYSCALL(__NR_dup3, sys_dup3) #define __NR_pipe2 293 __SYSCALL(__NR_pipe2, sys_pipe2) +#define __NR_inotify_init1 294 +__SYSCALL(__NR_inotify_init1, sys_inotify_init1) #ifndef __NO_STUBS diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 742b917e7d1b..72ef82120512 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -7,6 +7,8 @@ #ifndef _LINUX_INOTIFY_H #define _LINUX_INOTIFY_H +/* For O_CLOEXEC */ +#include #include /* @@ -63,6 +65,9 @@ struct inotify_event { IN_MOVED_TO | IN_DELETE | IN_CREATE | IN_DELETE_SELF | \ IN_MOVE_SELF) +/* Flags for sys_inotify_init1. */ +#define IN_CLOEXEC O_CLOEXEC + #ifdef __KERNEL__ #include diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 034d3358549e..93a7e7f017a6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -547,6 +547,7 @@ asmlinkage long sys_get_mempolicy(int __user *policy, unsigned long addr, unsigned long flags); asmlinkage long sys_inotify_init(void); +asmlinkage long sys_inotify_init1(int flags); asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask); asmlinkage long sys_inotify_rm_watch(int fd, u32 wd); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 2a361ccdc7ca..bd66ac5406f3 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -96,6 +96,7 @@ 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); -- cgit v1.2.3 From 5df439ef06d4173357711a04740aa8bfcf50d621 Mon Sep 17 00:00:00 2001 From: Wang Chen Date: Fri, 25 Jul 2008 01:45:23 -0700 Subject: flag parameters: fix compile error of sys_epoll_create1 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 --- kernel/sys_ni.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/sys_ni.c') diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index bd66ac5406f3..55eca1594da9 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -57,6 +57,7 @@ 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); -- cgit v1.2.3 From 9b81361631bbb1d85c99ddec677d42afe516737b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 25 Jul 2008 13:02:37 +0200 Subject: signalfd: fix undefined reference to `compat_sys_signalfd4' when !CONFIG_SIGNALFD 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 --- kernel/sys_ni.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/sys_ni.c') diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 55eca1594da9..08d6e1bb99ac 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -160,6 +160,7 @@ cond_syscall(sys_ioprio_get); 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); -- cgit v1.2.3