Merge master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:

	drivers/macintosh/adbhid.c

71 files changed, 3643 insertions, 2175 deletions

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index c64ce9c14207..6b066632e40c 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -63,3 +63,6 @@ config PREEMPT_BKL
 	  Say Y here if you are building a kernel for a desktop system.
 	  Say N if you are unsure.
 
+config PREEMPT_NOTIFIERS
+	bool
+
diff --git a/kernel/acct.c b/kernel/acct.c
index 70d0d88e5554..24f0f8b2ba72 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -468,7 +468,7 @@ static void do_acct_process(struct file *file)
 	}
 #endif
 	do_div(elapsed, AHZ);
-	ac.ac_btime = xtime.tv_sec - elapsed;
+	ac.ac_btime = get_seconds() - elapsed;
 	/* we really need to bite the bullet and change layout */
 	ac.ac_uid = current->uid;
 	ac.ac_gid = current->gid;
diff --git a/kernel/audit.c b/kernel/audit.c
index eb0f9165b401..2924251a6547 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -847,18 +847,10 @@ static void audit_receive_skb(struct sk_buff *skb)
 }
 
 /* Receive messages from netlink socket. */
-static void audit_receive(struct sock *sk, int length)
+static void audit_receive(struct sk_buff  *skb)
 {
-	struct sk_buff  *skb;
-	unsigned int qlen;
-
 	mutex_lock(&audit_cmd_mutex);
-
-	for (qlen = skb_queue_len(&sk->sk_receive_queue); qlen; qlen--) {
-		skb = skb_dequeue(&sk->sk_receive_queue);
-		audit_receive_skb(skb);
-		kfree_skb(skb);
-	}
+	audit_receive_skb(skb);
 	mutex_unlock(&audit_cmd_mutex);
 }
 
@@ -876,8 +868,8 @@ static int __init audit_init(void)
 
 	printk(KERN_INFO "audit: initializing netlink socket (%s)\n",
 	       audit_default ? "enabled" : "disabled");
-	audit_sock = netlink_kernel_create(NETLINK_AUDIT, 0, audit_receive,
-					   NULL, THIS_MODULE);
+	audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, 0,
+					   audit_receive, NULL, THIS_MODULE);
 	if (!audit_sock)
 		audit_panic("cannot initialize netlink socket");
 	else
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 1bf093dcffe0..359645cff5b2 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -304,7 +304,7 @@ int __init audit_register_class(int class, unsigned *list)
 
 int audit_match_class(int class, unsigned syscall)
 {
-	if (unlikely(syscall >= AUDIT_BITMASK_SIZE * sizeof(__u32)))
+	if (unlikely(syscall >= AUDIT_BITMASK_SIZE * 32))
 		return 0;
 	if (unlikely(class >= AUDIT_SYSCALL_CLASSES || !classes[class]))
 		return 0;
@@ -456,6 +456,13 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
 		case AUDIT_DEVMINOR:
 		case AUDIT_EXIT:
 		case AUDIT_SUCCESS:
+			/* bit ops are only useful on syscall args */
+			if (f->op == AUDIT_BIT_MASK ||
+						f->op == AUDIT_BIT_TEST) {
+				err = -EINVAL;
+				goto exit_free;
+			}
+			break;
 		case AUDIT_ARG0:
 		case AUDIT_ARG1:
 		case AUDIT_ARG2:
@@ -1566,6 +1573,10 @@ int audit_comparator(const u32 left, const u32 op, const u32 right)
 		return (left > right);
 	case AUDIT_GREATER_THAN_OR_EQUAL:
 		return (left >= right);
+	case AUDIT_BIT_MASK:
+		return (left & right);
+	case AUDIT_BIT_TEST:
+		return ((left & right) == right);
 	}
 	BUG();
 	return 0;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index b7640a5f382a..04f3ffb8d9d4 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -153,7 +153,7 @@ struct audit_aux_data_execve {
 	struct audit_aux_data	d;
 	int argc;
 	int envc;
-	char mem[0];
+	struct mm_struct *mm;
 };
 
 struct audit_aux_data_socketcall {
@@ -173,12 +173,6 @@ struct audit_aux_data_fd_pair {
 	int	fd[2];
 };
 
-struct audit_aux_data_path {
-	struct audit_aux_data	d;
-	struct dentry		*dentry;
-	struct vfsmount		*mnt;
-};
-
 struct audit_aux_data_pids {
 	struct audit_aux_data	d;
 	pid_t			target_pid[AUDIT_AUX_PIDS];
@@ -654,12 +648,6 @@ static inline void audit_free_aux(struct audit_context *context)
 	struct audit_aux_data *aux;
 
 	while ((aux = context->aux)) {
-		if (aux->type == AUDIT_AVC_PATH) {
-			struct audit_aux_data_path *axi = (void *)aux;
-			dput(axi->dentry);
-			mntput(axi->mnt);
-		}
-
 		context->aux = aux->next;
 		kfree(aux);
 	}
@@ -831,6 +819,57 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid,
 	return rc;
 }
 
+static void audit_log_execve_info(struct audit_buffer *ab,
+		struct audit_aux_data_execve *axi)
+{
+	int i;
+	long len, ret;
+	const char __user *p;
+	char *buf;
+
+	if (axi->mm != current->mm)
+		return; /* execve failed, no additional info */
+
+	p = (const char __user *)axi->mm->arg_start;
+
+	for (i = 0; i < axi->argc; i++, p += len) {
+		len = strnlen_user(p, MAX_ARG_STRLEN);
+		/*
+		 * We just created this mm, if we can't find the strings
+		 * we just copied into it something is _very_ wrong. Similar
+		 * for strings that are too long, we should not have created
+		 * any.
+		 */
+		if (!len || len > MAX_ARG_STRLEN) {
+			WARN_ON(1);
+			send_sig(SIGKILL, current, 0);
+		}
+
+		buf = kmalloc(len, GFP_KERNEL);
+		if (!buf) {
+			audit_panic("out of memory for argv string\n");
+			break;
+		}
+
+		ret = copy_from_user(buf, p, len);
+		/*
+		 * There is no reason for this copy to be short. We just
+		 * copied them here, and the mm hasn't been exposed to user-
+		 * space yet.
+		 */
+		if (ret) {
+			WARN_ON(1);
+			send_sig(SIGKILL, current, 0);
+		}
+
+		audit_log_format(ab, "a%d=", i);
+		audit_log_untrustedstring(ab, buf);
+		audit_log_format(ab, "\n");
+
+		kfree(buf);
+	}
+}
+
 static void audit_log_exit(struct audit_context *context, struct task_struct *tsk)
 {
 	int i, call_panic = 0;
@@ -946,7 +985,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		case AUDIT_IPC: {
 			struct audit_aux_data_ipcctl *axi = (void *)aux;
 			audit_log_format(ab, 
-				 "ouid=%u ogid=%u mode=%x",
+				 "ouid=%u ogid=%u mode=%#o",
 				 axi->uid, axi->gid, axi->mode);
 			if (axi->osid != 0) {
 				char *ctx = NULL;
@@ -965,19 +1004,13 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		case AUDIT_IPC_SET_PERM: {
 			struct audit_aux_data_ipcctl *axi = (void *)aux;
 			audit_log_format(ab,
-				"qbytes=%lx ouid=%u ogid=%u mode=%x",
+				"qbytes=%lx ouid=%u ogid=%u mode=%#o",
 				axi->qbytes, axi->uid, axi->gid, axi->mode);
 			break; }
 
 		case AUDIT_EXECVE: {
 			struct audit_aux_data_execve *axi = (void *)aux;
-			int i;
-			const char *p;
-			for (i = 0, p = axi->mem; i < axi->argc; i++) {
-				audit_log_format(ab, "a%d=", i);
-				p = audit_log_untrustedstring(ab, p);
-				audit_log_format(ab, "\n");
-			}
+			audit_log_execve_info(ab, axi);
 			break; }
 
 		case AUDIT_SOCKETCALL: {
@@ -995,11 +1028,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 			audit_log_hex(ab, axs->a, axs->len);
 			break; }
 
-		case AUDIT_AVC_PATH: {
-			struct audit_aux_data_path *axi = (void *)aux;
-			audit_log_d_path(ab, "path=", axi->dentry, axi->mnt);
-			break; }
-
 		case AUDIT_FD_PAIR: {
 			struct audit_aux_data_fd_pair *axs = (void *)aux;
 			audit_log_format(ab, "fd0=%d fd1=%d", axs->fd[0], axs->fd[1]);
@@ -1821,32 +1849,31 @@ int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode
 	return 0;
 }
 
+int audit_argv_kb = 32;
+
 int audit_bprm(struct linux_binprm *bprm)
 {
 	struct audit_aux_data_execve *ax;
 	struct audit_context *context = current->audit_context;
-	unsigned long p, next;
-	void *to;
 
 	if (likely(!audit_enabled || !context || context->dummy))
 		return 0;
 
-	ax = kmalloc(sizeof(*ax) + PAGE_SIZE * MAX_ARG_PAGES - bprm->p,
-				GFP_KERNEL);
+	/*
+	 * Even though the stack code doesn't limit the arg+env size any more,
+	 * the audit code requires that _all_ arguments be logged in a single
+	 * netlink skb. Hence cap it :-(
+	 */
+	if (bprm->argv_len > (audit_argv_kb << 10))
+		return -E2BIG;
+
+	ax = kmalloc(sizeof(*ax), GFP_KERNEL);
 	if (!ax)
 		return -ENOMEM;
 
 	ax->argc = bprm->argc;
 	ax->envc = bprm->envc;
-	for (p = bprm->p, to = ax->mem; p < MAX_ARG_PAGES*PAGE_SIZE; p = next) {
-		struct page *page = bprm->page[p / PAGE_SIZE];
-		void *kaddr = kmap(page);
-		next = (p + PAGE_SIZE) & ~(PAGE_SIZE - 1);
-		memcpy(to, kaddr + (p & (PAGE_SIZE - 1)), next - p);
-		to += next - p;
-		kunmap(page);
-	}
-
+	ax->mm = bprm->mm;
 	ax->d.type = AUDIT_EXECVE;
 	ax->d.next = context->aux;
 	context->aux = (void *)ax;
@@ -1949,36 +1976,6 @@ void __audit_ptrace(struct task_struct *t)
 }
 
 /**
- * audit_avc_path - record the granting or denial of permissions
- * @dentry: dentry to record
- * @mnt: mnt to record
- *
- * Returns 0 for success or NULL context or < 0 on error.
- *
- * Called from security/selinux/avc.c::avc_audit()
- */
-int audit_avc_path(struct dentry *dentry, struct vfsmount *mnt)
-{
-	struct audit_aux_data_path *ax;
-	struct audit_context *context = current->audit_context;
-
-	if (likely(!context))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->dentry = dget(dentry);
-	ax->mnt = mntget(mnt);
-
-	ax->d.type = AUDIT_AVC_PATH;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
-}
-
-/**
  * audit_signal_info - record signal info for shutting down audit subsystem
  * @sig: signal value
  * @t: task being signaled
@@ -1995,19 +1992,19 @@ int __audit_signal_info(int sig, struct task_struct *t)
 	extern uid_t audit_sig_uid;
 	extern u32 audit_sig_sid;
 
-	if (audit_pid && t->tgid == audit_pid &&
-	    (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1)) {
-		audit_sig_pid = tsk->pid;
-		if (ctx)
-			audit_sig_uid = ctx->loginuid;
-		else
-			audit_sig_uid = tsk->uid;
-		selinux_get_task_sid(tsk, &audit_sig_sid);
+	if (audit_pid && t->tgid == audit_pid) {
+		if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1) {
+			audit_sig_pid = tsk->pid;
+			if (ctx)
+				audit_sig_uid = ctx->loginuid;
+			else
+				audit_sig_uid = tsk->uid;
+			selinux_get_task_sid(tsk, &audit_sig_sid);
+		}
+		if (!audit_signals || audit_dummy_context())
+			return 0;
 	}
 
-	if (!audit_signals) /* audit_context checked in wrapper */
-		return 0;
-
 	/* optimize the common case by putting first signal recipient directly
 	 * in audit_context */
 	if (!ctx->target_pid) {
@@ -2026,7 +2023,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
 		axp->d.next = ctx->aux_pids;
 		ctx->aux_pids = (void *)axp;
 	}
-	BUG_ON(axp->pid_count > AUDIT_AUX_PIDS);
+	BUG_ON(axp->pid_count >= AUDIT_AUX_PIDS);
 
 	axp->target_pid[axp->pid_count] = t->tgid;
 	selinux_get_task_sid(t, &axp->target_sid[axp->pid_count]);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 181ae7086029..38033db8d8ec 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -273,7 +273,7 @@ int __cpuinit cpu_up(unsigned int cpu)
 	return err;
 }
 
-#ifdef CONFIG_SUSPEND_SMP
+#ifdef CONFIG_PM_SLEEP_SMP
 static cpumask_t frozen_cpus;
 
 int disable_nonboot_cpus(void)
@@ -334,4 +334,4 @@ void enable_nonboot_cpus(void)
 out:
 	mutex_unlock(&cpu_add_remove_lock);
 }
-#endif
+#endif /* CONFIG_PM_SLEEP_SMP */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b4796d850140..57e6448b171e 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -516,7 +516,7 @@ static void cpuset_release_agent(const char *pathbuf)
 	envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
 	envp[i] = NULL;
 
-	call_usermodehelper(argv[0], argv, envp, 0);
+	call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
 	kfree(pathbuf);
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index e8af8d0c2483..993369ee94d1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -24,7 +24,6 @@
 #include <linux/pid_namespace.h>
 #include <linux/ptrace.h>
 #include <linux/profile.h>
-#include <linux/signalfd.h>
 #include <linux/mount.h>
 #include <linux/proc_fs.h>
 #include <linux/kthread.h>
@@ -45,6 +44,7 @@
 #include <linux/resource.h>
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/freezer.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -85,14 +85,6 @@ static void __exit_signal(struct task_struct *tsk)
 	sighand = rcu_dereference(tsk->sighand);
 	spin_lock(&sighand->siglock);
 
-	/*
-	 * Notify that this sighand has been detached. This must
-	 * be called with the tsk->sighand lock held. Also, this
-	 * access tsk->sighand internally, so it must be called
-	 * before tsk->sighand is reset.
-	 */
-	signalfd_detach_locked(tsk);
-
 	posix_cpu_timers_exit(tsk);
 	if (atomic_dec_and_test(&sig->count))
 		posix_cpu_timers_exit_group(tsk);
@@ -594,6 +586,8 @@ static void exit_mm(struct task_struct * tsk)
 	tsk->mm = NULL;
 	up_read(&mm->mmap_sem);
 	enter_lazy_tlb(mm, current);
+	/* We don't want this task to be frozen prematurely */
+	clear_freeze_flag(tsk);
 	task_unlock(tsk);
 	mmput(mm);
 }
@@ -810,7 +804,7 @@ static void exit_notify(struct task_struct *tsk)
 		__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
 	}
 
-	/* Let father know we died 
+	/* Let father know we died
 	 *
 	 * Thread signals are configurable, but you aren't going to use
 	 * that to send signals to arbitary processes. 
@@ -823,9 +817,7 @@ static void exit_notify(struct task_struct *tsk)
 	 * If our self_exec id doesn't match our parent_exec_id then
 	 * we have changed execution domain as these two values started
 	 * the same after a fork.
-	 *	
 	 */
-	
 	if (tsk->exit_signal != SIGCHLD && tsk->exit_signal != -1 &&
 	    ( tsk->parent_exec_id != t->self_exec_id  ||
 	      tsk->self_exec_id != tsk->parent_exec_id)
@@ -845,9 +837,7 @@ static void exit_notify(struct task_struct *tsk)
 	}
 
 	state = EXIT_ZOMBIE;
-	if (tsk->exit_signal == -1 &&
-	    (likely(tsk->ptrace == 0) ||
-	     unlikely(tsk->parent->signal->flags & SIGNAL_GROUP_EXIT)))
+	if (tsk->exit_signal == -1 && likely(!tsk->ptrace))
 		state = EXIT_DEAD;
 	tsk->exit_state = state;
 
@@ -976,6 +966,7 @@ fastcall NORET_TYPE void do_exit(long code)
 	if (unlikely(tsk->audit_context))
 		audit_free(tsk);
 
+	tsk->exit_code = code;
 	taskstats_exit(tsk, group_dead);
 
 	exit_mm(tsk);
@@ -997,7 +988,6 @@ fastcall NORET_TYPE void do_exit(long code)
 	if (tsk->binfmt)
 		module_put(tsk->binfmt->module);
 
-	tsk->exit_code = code;
 	proc_exit_connector(tsk);
 	exit_task_namespaces(tsk);
 	exit_notify(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index ba39bdb2a7b8..5e67f90a1694 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -137,7 +137,7 @@ void __init fork_init(unsigned long mempages)
 	/* create a slab on which task_structs can be allocated */
 	task_struct_cachep =
 		kmem_cache_create("task_struct", sizeof(struct task_struct),
-			ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL, NULL);
+			ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL);
 #endif
 
 	/*
@@ -334,6 +334,8 @@ static struct mm_struct * mm_init(struct mm_struct * mm)
 	atomic_set(&mm->mm_count, 1);
 	init_rwsem(&mm->mmap_sem);
 	INIT_LIST_HEAD(&mm->mmlist);
+	mm->flags = (current->mm) ? current->mm->flags
+				  : MMF_DUMP_FILTER_DEFAULT;
 	mm->core_waiters = 0;
 	mm->nr_ptes = 0;
 	set_mm_counter(mm, file_rss, 0);
@@ -1436,7 +1438,7 @@ static void sighand_ctor(void *data, struct kmem_cache *cachep,
 	struct sighand_struct *sighand = data;
 
 	spin_lock_init(&sighand->siglock);
-	INIT_LIST_HEAD(&sighand->signalfd_list);
+	init_waitqueue_head(&sighand->signalfd_wqh);
 }
 
 void __init proc_caches_init(void)
@@ -1444,22 +1446,22 @@ void __init proc_caches_init(void)
 	sighand_cachep = kmem_cache_create("sighand_cache",
 			sizeof(struct sighand_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU,
-			sighand_ctor, NULL);
+			sighand_ctor);
 	signal_cachep = kmem_cache_create("signal_cache",
 			sizeof(struct signal_struct), 0,
-			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
-	files_cachep = kmem_cache_create("files_cache", 
+			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+	files_cachep = kmem_cache_create("files_cache",
 			sizeof(struct files_struct), 0,
-			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
-	fs_cachep = kmem_cac