From 95a5afca4a8d2e1cb77e1d4bc6ff9f718dc32f7a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 16 Oct 2008 15:24:51 -0700 Subject: net: Remove CONFIG_KMOD from net/ (towards removing CONFIG_KMOD entirely) Some code here depends on CONFIG_KMOD to not try to load protocol modules or similar, replace by CONFIG_MODULES where more than just request_module depends on CONFIG_KMOD and and also use try_then_request_module in ebtables. Signed-off-by: Johannes Berg Signed-off-by: Rusty Russell Signed-off-by: David S. Miller --- net/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 3e8d4e3..2b7a4b5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1142,7 +1142,7 @@ static int __sock_create(struct net *net, int family, int type, int protocol, sock->type = type; -#if defined(CONFIG_KMOD) +#ifdef CONFIG_MODULES /* Attempt to load a protocol module if the find failed. * * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user -- cgit v1.1 From 233e70f4228e78eb2f80dc6650f65d3ae3dbf17c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 31 Oct 2008 23:28:30 +0000 Subject: saner FASYNC handling on file close As it is, all instances of ->release() for files that have ->fasync() need to remember to evict file from fasync lists; forgetting that creates a hole and we actually have a bunch that *does* forget. So let's keep our lives simple - let __fput() check FASYNC in file->f_flags and call ->fasync() there if it's been set. And lose that crap in ->release() instances - leaving it there is still valid, but we don't have to bother anymore. Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- net/socket.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 2b7a4b5..57550c3 100644 --- a/net/socket.c +++ b/net/socket.c @@ -990,7 +990,6 @@ static int sock_close(struct inode *inode, struct file *filp) printk(KERN_DEBUG "sock_close: NULL inode\n"); return 0; } - sock_fasync(-1, filp, 0); sock_release(SOCKET_I(inode)); return 0; } -- cgit v1.1 From ab2910921064b657610a3b501358a305e13087ea Mon Sep 17 00:00:00 2001 From: Jianjun Kong Date: Mon, 3 Nov 2008 18:23:09 -0800 Subject: net: remove two duplicated #include Removed duplicated #include in net/9p/trans_rdma.c and #include in net/socket.c Signed-off-by: Jianjun Kong Signed-off-by: David S. Miller --- net/socket.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 2b7a4b5..d23cdba 100644 --- a/net/socket.c +++ b/net/socket.c @@ -69,7 +69,6 @@ #include #include #include -#include #include #include #include -- cgit v1.1 From 8192b0c482d7078fcdcb4854341b977426f6f09b Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:10 +1100 Subject: CRED: Wrap task credential accesses in the networking subsystem Wrap access to task credentials so that they can be separated more easily from the task_struct during the introduction of COW creds. Change most current->(|e|s|fs)[ug]id to current_(|e|s|fs)[ug]id(). Change some task->e?[ug]id to task_e?[ug]id(). In some places it makes more sense to use RCU directly rather than a convenient wrapper; these will be addressed by later patches. Signed-off-by: David Howells Reviewed-by: James Morris Acked-by: Serge Hallyn Cc: netdev@vger.kernel.org Signed-off-by: James Morris --- net/socket.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 57550c3..62c7729 100644 --- a/net/socket.c +++ b/net/socket.c @@ -491,8 +491,8 @@ static struct socket *sock_alloc(void) sock = SOCKET_I(inode); inode->i_mode = S_IFSOCK | S_IRWXUGO; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); get_cpu_var(sockets_in_use)++; put_cpu_var(sockets_in_use); -- cgit v1.1 From de11defebf00007677fb7ee91d9b089b78786fbb Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 19 Nov 2008 15:36:14 -0800 Subject: 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 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 --- net/socket.c | 80 ++++++++---------------------------------------------------- 1 file changed, 10 insertions(+), 70 deletions(-) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 57550c3..92764d8 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1426,8 +1426,8 @@ asmlinkage long sys_listen(int fd, int backlog) * clean when we restucture accept also. */ -long do_accept(int fd, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags) +asmlinkage long sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; @@ -1510,66 +1510,10 @@ out_fd: goto out_put; } -#if 0 -#ifdef HAVE_SET_RESTORE_SIGMASK -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; -} -#else -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) -{ - /* The platform does not support restoring the signal mask in the - * return path. So we do not allow using paccept() with a signal - * mask. */ - if (sigmask) - return -EINVAL; - - return do_accept(fd, upeer_sockaddr, upeer_addrlen, flags); -} -#endif -#endif - asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen) { - return do_accept(fd, upeer_sockaddr, upeer_addrlen, 0); + return sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0); } /* @@ -2096,7 +2040,7 @@ 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(4) }; #undef AL @@ -2115,7 +2059,7 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) unsigned long a0, a1; int err; - if (call < 1 || call > SYS_PACCEPT) + if (call < 1 || call > SYS_ACCEPT4) return -EINVAL; /* copy_from_user should be SMP safe. */ @@ -2143,9 +2087,8 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) err = sys_listen(a0, a1); break; case SYS_ACCEPT: - err = - do_accept(a0, (struct sockaddr __user *)a1, - (int __user *)a[2], 0); + err = sys_accept4(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = @@ -2192,12 +2135,9 @@ 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]); + case SYS_ACCEPT4: + err = sys_accept4(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], a[3]); break; default: err = -EINVAL; -- cgit v1.1 From 1b08534e562dae7b084326f8aa8cc12a4c1b6593 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Thu, 18 Dec 2008 19:35:10 -0800 Subject: net: Fix module refcount leak in kernel_accept() The kernel_accept() does not hold the module refcount of newsock->ops->owner, so we need __module_get(newsock->ops->owner) code after call kernel_accept() by hand. In sunrpc, the module refcount is missing to hold. So this cause kernel panic. Used following script to reproduct: while [ 1 ]; do mount -t nfs4 192.168.0.19:/ /mnt touch /mnt/file umount /mnt lsmod | grep ipv6 done This patch fixed the problem by add __module_get(newsock->ops->owner) to kernel_accept(). So we do not need to used __module_get(newsock->ops->owner) in every place when used kernel_accept(). Signed-off-by: Wei Yongjun Signed-off-by: David S. Miller --- net/socket.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 92764d8..76ba80a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2307,6 +2307,7 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) } (*newsock)->ops = sock->ops; + __module_get((*newsock)->ops->owner); done: return err; -- cgit v1.1