From 8e3bad65a59915f2ddc40f62a180ad81695d8440 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 17 Nov 2008 10:59:59 +0100 Subject: mac80211: remove ieee80211_notify_mac Before ieee80211_notify_mac() was added, it was presented with the use case of using it to tell mac80211 that the association may have been lost because the firmware crashed/reset. Since then, it has also been used by iwlwifi to (slightly) speed up re-association after resume, a workaround around the fact that mac80211 has no suspend/resume handling yet. It is also not used by any other drivers, so clearly it cannot be necessary for "good enough" suspend/resume. Unfortunately, the callback suffers from a severe problem: It only works for station mode. If suspend/resume happens while in IBSS or any other mode (but station), then the callback is pointless. Recently, it has created a number of locking issues, first because it required rtnl locking rather than RCU due to calling sleeping functions within the critical section, and now because it's called by iwlwifi from the mac80211 workqueue that may not use the rtnl because it is flushed under rtnl. (cf. http://bugzilla.kernel.org/show_bug.cgi?id=12046) I think, therefore, that we should take a step back, remove it entirely for now and add the small feature it provided properly. For suspend and resume we will need to introduce new hooks, and for the case where the firmware was reset the driver will probably simply just pretend it has done a suspend/resume cycle to get mac80211 to reprogram the hardware completely, not just try to connect to the current AP again in station mode. When doing so, we will need to take into account locking issues and possibly defer to schedule_work from within mac80211 for the resume operation, while the suspend operation must be done directly. Proper suspend/resume should also not necessarily try to reconnect to the current AP, the time spent in suspend may have been short enough to not be disconnected from the AP, mac80211 will detect that the AP went out of range quickly if it did, and if the association is lost then the AP will disassoc as soon as a data frame is sent. We might also take into account WWOL then, and have mac80211 program the hardware into such a mode where it is available and requested. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- net/mac80211/mlme.c | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'net') diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 14d165f0df75..409bb7716236 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2560,25 +2560,3 @@ void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local) ieee80211_restart_sta_timer(sdata); rcu_read_unlock(); } - -/* driver notification call */ -void ieee80211_notify_mac(struct ieee80211_hw *hw, - enum ieee80211_notification_types notif_type) -{ - struct ieee80211_local *local = hw_to_local(hw); - struct ieee80211_sub_if_data *sdata; - - switch (notif_type) { - case IEEE80211_NOTIFY_RE_ASSOC: - rtnl_lock(); - list_for_each_entry(sdata, &local->interfaces, list) { - if (sdata->vif.type != NL80211_IFTYPE_STATION) - continue; - - ieee80211_sta_req_auth(sdata, &sdata->u.sta); - } - rtnl_unlock(); - break; - } -} -EXPORT_SYMBOL(ieee80211_notify_mac); -- cgit v1.2.3 From c3e388964baa00d8c3960f23e8c8a1fb3966759e Mon Sep 17 00:00:00 2001 From: Benjamin Thery Date: Wed, 19 Nov 2008 14:07:41 -0800 Subject: net: fix ip_mr_init() error path Similarly to IPv6 ip6_mr_init() (fixed last week), the order of cleanup operations in the error/exit section of ip_mr_init() is completely inversed. It should be the other way around. Also a del_timer() is missing in the error path. I should have guessed last week that this same error existed in ipmr.c too, as ip6mr.c is largely inspired by ipmr.c. Signed-off-by: Benjamin Thery Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b42e082cc170..25924b1eb2ef 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1945,13 +1945,14 @@ int __init ip_mr_init(void) goto proc_cache_fail; #endif return 0; -reg_notif_fail: - kmem_cache_destroy(mrt_cachep); #ifdef CONFIG_PROC_FS -proc_vif_fail: - unregister_netdevice_notifier(&ip_mr_notifier); proc_cache_fail: proc_net_remove(&init_net, "ip_mr_vif"); +proc_vif_fail: + unregister_netdevice_notifier(&ip_mr_notifier); #endif +reg_notif_fail: + del_timer(&ipmr_expire_timer); + kmem_cache_destroy(mrt_cachep); return err; } -- cgit v1.2.3 From bfdbc0acadcc761b94814d78f0acec90f0d760de Mon Sep 17 00:00:00 2001 From: Robert Olsson Date: Wed, 19 Nov 2008 14:09:47 -0800 Subject: pktgen: fix multiple queue warning As number of TX queues in unrelated to number of CPU's we remove this test and just make sure nxtq never gets exceeded. Signed-off-by: Robert Olsson Signed-off-by: David S. Miller --- net/core/pktgen.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a47f5bad110d..8997e912aaaf 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1973,13 +1973,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) /* make sure that we don't pick a non-existing transmit queue */ ntxq = pkt_dev->odev->real_num_tx_queues; - if (ntxq > num_online_cpus() && (pkt_dev->flags & F_QUEUE_MAP_CPU)) { - printk(KERN_WARNING "pktgen: WARNING: QUEUE_MAP_CPU " - "disabled because CPU count (%d) exceeds number " - "of tx queues (%d) on %s\n", num_online_cpus(), ntxq, - pkt_dev->odev->name); - pkt_dev->flags &= ~F_QUEUE_MAP_CPU; - } + if (ntxq <= pkt_dev->queue_map_min) { printk(KERN_WARNING "pktgen: WARNING: Requested " "queue_map_min (zero-based) (%d) exceeds valid range " @@ -2202,6 +2196,7 @@ static void set_cur_queue_map(struct pktgen_dev *pkt_dev) } pkt_dev->cur_queue_map = t; } + pkt_dev->cur_queue_map = pkt_dev->cur_queue_map % pkt_dev->odev->real_num_tx_queues; } /* Increment/randomize headers according to flags and current values -- cgit v1.2.3 From 566521d63720ab47576afb85147e5652993bf1e6 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 19 Nov 2008 14:17:41 -0800 Subject: phonet: fix compilation with gcc-3.4 CC [M] net/phonet/af_phonet.o net/phonet/af_phonet.c: In function `pn_socket_create': net/phonet/af_phonet.c:38: sorry, unimplemented: inlining failed in call to 'phonet_proto_put': function body not available net/phonet/af_phonet.c:99: sorry, unimplemented: called from here make[3]: *** [net/phonet/af_phonet.o] Error 1 Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- net/phonet/af_phonet.c | 52 +++++++++++++++++++++++--------------------------- 1 file changed, 24 insertions(+), 28 deletions(-) (limited to 'net') diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index 7ab30f668b5a..9d211f12582b 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -33,9 +33,30 @@ #include #include -static struct net_proto_family phonet_proto_family; -static struct phonet_protocol *phonet_proto_get(int protocol); -static inline void phonet_proto_put(struct phonet_protocol *pp); +/* Transport protocol registration */ +static struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly; +static DEFINE_SPINLOCK(proto_tab_lock); + +static struct phonet_protocol *phonet_proto_get(int protocol) +{ + struct phonet_protocol *pp; + + if (protocol >= PHONET_NPROTO) + return NULL; + + spin_lock(&proto_tab_lock); + pp = proto_tab[protocol]; + if (pp && !try_module_get(pp->prot->owner)) + pp = NULL; + spin_unlock(&proto_tab_lock); + + return pp; +} + +static inline void phonet_proto_put(struct phonet_protocol *pp) +{ + module_put(pp->prot->owner); +} /* protocol family functions */ @@ -375,10 +396,6 @@ static struct packet_type phonet_packet_type = { .func = phonet_rcv, }; -/* Transport protocol registration */ -static struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly; -static DEFINE_SPINLOCK(proto_tab_lock); - int __init_or_module phonet_proto_register(int protocol, struct phonet_protocol *pp) { @@ -412,27 +429,6 @@ void phonet_proto_unregister(int protocol, struct phonet_protocol *pp) } EXPORT_SYMBOL(phonet_proto_unregister); -static struct phonet_protocol *phonet_proto_get(int protocol) -{ - struct phonet_protocol *pp; - - if (protocol >= PHONET_NPROTO) - return NULL; - - spin_lock(&proto_tab_lock); - pp = proto_tab[protocol]; - if (pp && !try_module_get(pp->prot->owner)) - pp = NULL; - spin_unlock(&proto_tab_lock); - - return pp; -} - -static inline void phonet_proto_put(struct phonet_protocol *pp) -{ - module_put(pp->prot->owner); -} - /* Module registration */ static int __init phonet_init(void) { -- cgit v1.2.3 From b47300168e770b60ab96c8924854c3b0eb4260eb Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 19 Nov 2008 15:33:54 -0800 Subject: net: Do not fire linkwatch events until the device is registered. Several device drivers try to do things like netif_carrier_off() before register_netdev() is invoked. This is bogus, but too many drivers do this to fix them all up in one go. Reported-by: Folkert van Heusden Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 93cd30ce6501..cdcd16fcfeda 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -270,6 +270,8 @@ static void dev_watchdog_down(struct net_device *dev) void netif_carrier_on(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) { + if (dev->reg_state == NETREG_UNINITIALIZED) + return; linkwatch_fire_event(dev); if (netif_running(dev)) __netdev_watchdog_up(dev); @@ -285,8 +287,11 @@ EXPORT_SYMBOL(netif_carrier_on); */ void netif_carrier_off(struct net_device *dev) { - if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) + if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) { + if (dev->reg_state == NETREG_UNINITIALIZED) + return; linkwatch_fire_event(dev); + } } EXPORT_SYMBOL(netif_carrier_off); -- cgit v1.2.3 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 --- arch/x86/include/asm/unistd_64.h | 4 +- include/linux/net.h | 6 +-- include/linux/syscalls.h | 3 +- kernel/sys_ni.c | 2 +- net/compat.c | 50 +++---------------------- net/socket.c | 80 +++++----------------------------------- 6 files changed, 21 insertions(+), 124 deletions(-) (limited to 'net') diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 834b2c1d89fb..d2e415e6666f 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -639,8 +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) +#define __NR_accept4 288 +__SYSCALL(__NR_accept4, sys_accept4) #define __NR_signalfd4 289 __SYSCALL(__NR_signalfd4, sys_signalfd4) #define __NR_eventfd2 290 diff --git a/include/linux/net.h b/include/linux/net.h index 6dc14a240042..4515efae4c39 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -40,7 +40,7 @@ #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) */ +#define SYS_ACCEPT4 18 /* sys_accept4(2) */ typedef enum { SS_FREE = 0, /* not allocated */ @@ -100,7 +100,7 @@ enum sock_type { * remaining bits are used as flags. */ #define SOCK_TYPE_MASK 0xf -/* Flags for socket, socketpair, paccept */ +/* Flags for socket, socketpair, accept4 */ #define SOCK_CLOEXEC O_CLOEXEC #ifndef SOCK_NONBLOCK #define SOCK_NONBLOCK O_NONBLOCK @@ -223,8 +223,6 @@ 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 d6ff145919ca..04fb47bfb920 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -410,8 +410,7 @@ 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 __user sigset_t *, size_t, int); +asmlinkage long sys_accept4(int, struct sockaddr __user *, int __user *, 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 a77b27b11b04..e14a23281707 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -31,7 +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_accept4); cond_syscall(sys_connect); cond_syscall(sys_getsockname); cond_syscall(sys_getpeername); diff --git a/net/compat.c b/net/compat.c index 6ce1a1cadcc0..a3a2ba0fac08 100644 --- a/net/compat.c +++ b/net/compat.c @@ -725,7 +725,7 @@ EXPORT_SYMBOL(compat_mc_getsockopt); 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(4)}; #undef AL asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags) @@ -738,52 +738,13 @@ 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_PACCEPT) + if (call < SYS_SOCKET || call > SYS_ACCEPT4) return -EINVAL; if (copy_from_user(a, args, nas[call])) return -EFAULT; @@ -804,7 +765,7 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args) ret = sys_listen(a0, a1); break; case SYS_ACCEPT: - ret = do_accept(a0, compat_ptr(a1), compat_ptr(a[2]), 0); + ret = sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), 0); break; case SYS_GETSOCKNAME: ret = sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2])); @@ -844,9 +805,8 @@ 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]); + case SYS_ACCEPT4: + ret = sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), a[3]); break; default: ret = -EINVAL; diff --git a/net/socket.c b/net/socket.c index 57550c3bcabe..92764d836891 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 v1.2.3 From a134f85c131ffd56720e38af2967ec6265480757 Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 20 Nov 2008 01:07:24 -0800 Subject: TPROXY: fill struct flowi->flags in udp_sendmsg() udp_sendmsg() didn't fill struct flowi->flags, which means that the route lookup would fail for non-local IPs even if the IP_TRANSPARENT sockopt was set. This prevents sendto() to work properly for UDP sockets, whereas bind(foreign-ip) + connect() + send() worked fine. Signed-off-by: Balazs Scheidler Signed-off-by: David S. Miller --- net/ipv4/udp.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index cf02701ced48..98c1fd09be88 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -633,6 +633,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, .saddr = saddr, .tos = tos } }, .proto = sk->sk_protocol, + .flags = inet_sk_flowi_flags(sk), .uli_u = { .ports = { .sport = inet->sport, .dport = dport } } }; -- cgit v1.2.3 From c82838458200ec4167ce7083b0a17474150c5bf7 Mon Sep 17 00:00:00 2001 From: Balazs Scheidler Date: Thu, 20 Nov 2008 01:08:06 -0800 Subject: TPROXY: supply a struct flowi->flags argument in inet_sk_rebuild_header() inet_sk_rebuild_header() does a new route lookup if the dst_entry associated with a socket becomes stale. However inet_sk_rebuild_header() didn't use struct flowi->flags, causing the route lookup to fail for foreign-bound IP_TRANSPARENT sockets, causing an error state to be set for the sockets in question. Signed-off-by: Balazs Scheidler Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 1fbff5fa4241..1aa2dc9e380e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1117,6 +1117,7 @@ int inet_sk_rebuild_header(struct sock *sk) }, }, .proto = sk->sk_protocol, + .flags = inet_sk_flowi_flags(sk), .uli_u = { .ports = { .sport = inet->sport, -- cgit v1.2.3 From 3aa4614da741f10b09559a5675c79e2eff5cccd8 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 20 Nov 2008 04:07:14 -0800 Subject: pkt_sched: fix missing check for packet overrun in qdisc_dump_stab() nla_nest_start() might return NULL, causing a NULL pointer dereference. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/sched/sch_api.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b16ad2972c6b..6ab4a2f92ca0 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -417,6 +417,8 @@ static int qdisc_dump_stab(struct sk_buff *skb, struct qdisc_size_table *stab) struct nlattr *nest; nest = nla_nest_start(skb, TCA_STAB); + if (nest == NULL) + goto nla_put_failure; NLA_PUT(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts); nla_nest_end(skb, nest); -- cgit v1.2.3 From eedd726efbc439dbed94fb8577e5533a986b341f Mon Sep 17 00:00:00 2001 From: Benjamin Thery Date: Thu, 20 Nov 2008 04:16:12 -0800 Subject: ipv6: use seq_release_private for ip6mr.c /proc entries In ip6mr.c, /proc entries /proc/net/ip6_mr_cache and /proc/net/ip6_mr_vif are opened with seq_open_private(), thus seq_release_private() should be used to release them. Should fix a small memory leak. Signed-off-by: Benjamin Thery Signed-off-by: David S. Miller --- net/ipv6/ip6mr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 52a7eb0e2c2c..0524769632e7 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -224,7 +224,7 @@ static struct file_operations ip6mr_vif_fops = { .open = ip6mr_vif_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) @@ -338,7 +338,7 @@ static struct file_operations ip6mr_mfc_fops = { .open = ipmr_mfc_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; #endif -- cgit v1.2.3 From 5ece6c2ddd6f7da9e95dc325c742c0f5afbcecbe Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 20 Nov 2008 04:20:10 -0800 Subject: net: fix tiny output corruption of /proc/net/snmp6 Because "name" is static, it can be occasionally be filled with somewhat garbage if two processes read /proc/net/snmp6. Also, remove useless casts and "-1" -- snprintf() correctly terminates it's output. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- net/ipv6/proc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 07f0b76e7427..97c17fdd6f75 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -132,7 +132,7 @@ static struct snmp_mib snmp6_udplite6_list[] = { static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) { - static char name[32]; + char name[32]; int i; /* print by name -- deprecated items */ @@ -144,7 +144,7 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) p = icmp6type2name[icmptype]; if (!p) /* don't print un-named types here */ continue; - (void) snprintf(name, sizeof(name)-1, "Icmp6%s%s", + snprintf(name, sizeof(name), "Icmp6%s%s", i & 0x100 ? "Out" : "In", p); seq_printf(seq, "%-32s\t%lu\n", name, snmp_fold_field(mib, i)); @@ -157,7 +157,7 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) val = snmp_fold_field(mib, i); if (!val) continue; - (void) snprintf(name, sizeof(name)-1, "Icmp6%sType%u", + snprintf(name, sizeof(name), "Icmp6%sType%u", i & 0x100 ? "Out" : "In", i & 0xff); seq_printf(seq, "%-32s\t%lu\n", name, val); } -- cgit v1.2.3 From 23918b03060f6e572168fdde1798a905679d2e06 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 20 Nov 2008 16:06:21 -0500 Subject: SUNRPC: Fix a performance regression in the RPC authentication code Fix a regression reported by Max Kellermann whereby kernel profiling showed that his clients were spending 45% of their time in rpcauth_lookup_credcache. It turns out that although his processes had identical uid/gid/groups, generic_match() was failing to detect this, because the task->group_info pointers were not shared. This again lead to the creation of a huge number of identical credentials at the RPC layer. The regression is fixed by comparing the contents of task->group_info if the actual pointers are not identical. Signed-off-by: Trond Myklebust Signed-off-by: Linus Torvalds --- net/sunrpc/auth_generic.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index 744b79fdcb19..4028502f0528 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -133,13 +133,29 @@ static int generic_match(struct auth_cred *acred, struct rpc_cred *cred, int flags) { struct generic_cred *gcred = container_of(cred, struct generic_cred, gc_base); + int i; if (gcred->acred.uid != acred->uid || gcred->acred.gid != acred->gid || - gcred->acred.group_info != acred->group_info || gcred->acred.machine_cred != acred->machine_cred) - return 0; + goto out_nomatch; + + /* Optimisation in the case where pointers are identical... */ + if (gcred->acred.group_info == acred->group_info) + goto out_match; + + /* Slow path... */ + if (gcred->acred.group_info->ngroups != acred->group_info->ngroups) + goto out_nomatch; + for (i = 0; i < gcred->acred.group_info->ngroups; i++) { + if (GROUP_AT(gcred->acred.group_info, i) != + GROUP_AT(acred->group_info, i)) + goto out_nomatch; + } +out_match: return 1; +out_nomatch: + return 0; } void __init rpc_init_generic_auth(void) -- cgit v1.2.3