Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal

Pull big execve/kernel_thread/fork unification series from Al Viro:
 "All architectures are converted to new model.  Quite a bit of that
  stuff is actually shared with architecture trees; in such cases it's
  literally shared branch pulled by both, not a cherry-pick.

  A lot of ugliness and black magic is gone (-3KLoC total in this one):

   - kernel_thread()/kernel_execve()/sys_execve() redesign.

     We don't do syscalls from kernel anymore for either kernel_thread()
     or kernel_execve():

     kernel_thread() is essentially clone(2) with callback run before we
     return to userland, the callbacks either never return or do
     successful do_execve() before returning.

     kernel_execve() is a wrapper for do_execve() - it doesn't need to
     do transition to user mode anymore.

     As a result kernel_thread() and kernel_execve() are
     arch-independent now - they live in kernel/fork.c and fs/exec.c
     resp.  sys_execve() is also in fs/exec.c and it's completely
     architecture-independent.

   - daemonize() is gone, along with its parts in fs/*.c

   - struct pt_regs * is no longer passed to do_fork/copy_process/
     copy_thread/do_execve/search_binary_handler/->load_binary/do_coredump.

   - sys_fork()/sys_vfork()/sys_clone() unified; some architectures
     still need wrappers (ones with callee-saved registers not saved in
     pt_regs on syscall entry), but the main part of those suckers is in
     kernel/fork.c now."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal: (113 commits)
  do_coredump(): get rid of pt_regs argument
  print_fatal_signal(): get rid of pt_regs argument
  ptrace_signal(): get rid of unused arguments
  get rid of ptrace_signal_deliver() arguments
  new helper: signal_pt_regs()
  unify default ptrace_signal_deliver
  flagday: kill pt_regs argument of do_fork()
  death to idle_regs()
  don't pass regs to copy_process()
  flagday: don't pass regs to copy_thread()
  bfin: switch to generic vfork, get rid of pointless wrappers
  xtensa: switch to generic clone()
  openrisc: switch to use of generic fork and clone
  unicore32: switch to generic clone(2)
  score: switch to generic fork/vfork/clone
  c6x: sanitize copy_thread(), get rid of clone(2) wrapper, switch to generic clone()
  take sys_fork/sys_vfork/sys_clone prototypes to linux/syscalls.h
  mn10300: switch to generic fork/vfork/clone
  h8300: switch to generic fork/vfork/clone
  tile: switch to generic clone()
  ...

Conflicts:
	arch/microblaze/include/asm/Kbuild

4 files changed, 76 insertions, 197 deletions

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index fc7376bf86ea..e37e6a12c5e3 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -200,7 +200,6 @@ struct audit_context {
         struct list_head    names_list; /* anchor for struct audit_names->list */
         char *              filterkey;  /* key for rule that triggered record */
         struct path         pwd;
-        struct audit_context *previous; /* For nested syscalls */
         struct audit_aux_data *aux;
         struct audit_aux_data *aux_pids;
         struct sockaddr_storage *sockaddr;
@@ -1091,29 +1090,13 @@ int audit_alloc(struct task_struct *tsk)
 
 static inline void audit_free_context(struct audit_context *context)
 {
-        struct audit_context *previous;
-        int                  count = 0;
-
-        do {
-                previous = context->previous;
-                if (previous || (count &&  count < 10)) {
-                        ++count;
-                        printk(KERN_ERR "audit(:%d): major=%d name_count=%d:"
-                               " freeing multiple contexts (%d)\n",
-                               context->serial, context->major,
-                               context->name_count, count);
-                }
-                audit_free_names(context);
-                unroll_tree_refs(context, NULL, 0);
-                free_tree_refs(context);
-                audit_free_aux(context);
-                kfree(context->filterkey);
-                kfree(context->sockaddr);
-                kfree(context);
-                context  = previous;
-        } while (context);
-        if (count >= 10)
-                printk(KERN_ERR "audit: freed %d contexts\n", count);
+        audit_free_names(context);
+        unroll_tree_refs(context, NULL, 0);
+        free_tree_refs(context);
+        audit_free_aux(context);
+        kfree(context->filterkey);
+        kfree(context->sockaddr);
+        kfree(context);
 }
 
 void audit_log_task_context(struct audit_buffer *ab)
@@ -1783,42 +1766,6 @@ void __audit_syscall_entry(int arch, int major,
         if (!context)
                 return;
 
-        /*
-         * This happens only on certain architectures that make system
-         * calls in kernel_thread via the entry.S interface, instead of
-         * with direct calls.  (If you are porting to a new
-         * architecture, hitting this condition can indicate that you
-         * got the _exit/_leave calls backward in entry.S.)
-         *
-         * i386     no
-         * x86_64   no
-         * ppc64    yes (see arch/powerpc/platforms/iseries/misc.S)
-         *
-         * This also happens with vm86 emulation in a non-nested manner
-         * (entries without exits), so this case must be caught.
-         */
-        if (context->in_syscall) {
-                struct audit_context *newctx;
-
-#if AUDIT_DEBUG
-                printk(KERN_ERR
-                       "audit(:%d) pid=%d in syscall=%d;"
-                       " entering syscall=%d\n",
-                       context->serial, tsk->pid, context->major, major);
-#endif
-                newctx = audit_alloc_context(context->state);
-                if (newctx) {
-                        newctx->previous   = context;
-                        context            = newctx;
-                        tsk->audit_context = newctx;
-                } else  {
-                        /* If we can't alloc a new context, the best we
-                         * can do is to leak memory (any pending putname
-                         * will be lost).  The only other alternative is
-                         * to abandon auditing. */
-                        audit_zero_context(context, context->state);
-                }
-        }
         BUG_ON(context->in_syscall || context->name_count);
 
         if (!audit_enabled)
@@ -1881,28 +1828,21 @@ void __audit_syscall_exit(int success, long return_code)
         if (!list_empty(&context->killed_trees))
                 audit_kill_trees(&context->killed_trees);
 
-        if (context->previous) {
-                struct audit_context *new_context = context->previous;
-                context->previous  = NULL;
-                audit_free_context(context);
-                tsk->audit_context = new_context;
-        } else {
-                audit_free_names(context);
-                unroll_tree_refs(context, NULL, 0);
-                audit_free_aux(context);
-                context->aux = NULL;
-                context->aux_pids = NULL;
-                context->target_pid = 0;
-                context->target_sid = 0;
-                context->sockaddr_len = 0;
-                context->type = 0;
-                context->fds[0] = -1;
-                if (context->state != AUDIT_RECORD_CONTEXT) {
-                        kfree(context->filterkey);
-                        context->filterkey = NULL;
-                }
-                tsk->audit_context = context;
+        audit_free_names(context);
+        unroll_tree_refs(context, NULL, 0);
+        audit_free_aux(context);
+        context->aux = NULL;
+        context->aux_pids = NULL;
+        context->target_pid = 0;
+        context->target_sid = 0;
+        context->sockaddr_len = 0;
+        context->type = 0;
+        context->fds[0] = -1;
+        if (context->state != AUDIT_RECORD_CONTEXT) {
+                kfree(context->filterkey);
+                context->filterkey = NULL;
         }
+        tsk->audit_context = context;
 }
 
 static inline void handle_one(const struct inode *inode)
diff --git a/kernel/exit.c b/kernel/exit.c
index 618f7ee56003..50d2e93c36ea 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -322,43 +322,6 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
         }
 }
 
-/**
- * reparent_to_kthreadd - Reparent the calling kernel thread to kthreadd
- *
- * If a kernel thread is launched as a result of a system call, or if
- * it ever exits, it should generally reparent itself to kthreadd so it
- * isn't in the way of other processes and is correctly cleaned up on exit.
- *
- * The various task state such as scheduling policy and priority may have
- * been inherited from a user process, so we reset them to sane values here.
- *
- * NOTE that reparent_to_kthreadd() gives the caller full capabilities.
- */
-static void reparent_to_kthreadd(void)
-{
-        write_lock_irq(&tasklist_lock);
-
-        ptrace_unlink(current);
-        /* Reparent to init */
-        current->real_parent = current->parent = kthreadd_task;
-        list_move_tail(&current->sibling, &current->real_parent->children);
-
-        /* Set the exit signal to SIGCHLD so we signal init on exit */
-        current->exit_signal = SIGCHLD;
-
-        if (task_nice(current) < 0)
-                set_user_nice(current, 0);
-        /* cpus_allowed? */
-        /* rt_priority? */
-        /* signals? */
-        memcpy(current->signal->rlim, init_task.signal->rlim,
-               sizeof(current->signal->rlim));
-
-        atomic_inc(&init_cred.usage);
-        commit_creds(&init_cred);
-        write_unlock_irq(&tasklist_lock);
-}
-
 void __set_special_pids(struct pid *pid)
 {
         struct task_struct *curr = current->group_leader;
@@ -370,13 +333,6 @@ void __set_special_pids(struct pid *pid)
                 change_pid(curr, PIDTYPE_PGID, pid);
 }
 
-static void set_special_pids(struct pid *pid)
-{
-        write_lock_irq(&tasklist_lock);
-        __set_special_pids(pid);
-        write_unlock_irq(&tasklist_lock);
-}
-
 /*
  * Let kernel threads use this to say that they allow a certain signal.
  * Must not be used if kthread was cloned with CLONE_SIGHAND.
@@ -416,54 +372,6 @@ int disallow_signal(int sig)
 
 EXPORT_SYMBOL(disallow_signal);
 
-/*
- *      Put all the gunge required to become a kernel thread without
- *      attached user resources in one place where it belongs.
- */
-
-void daemonize(const char *name, ...)
-{
-        va_list args;
-        sigset_t blocked;
-
-        va_start(args, name);
-        vsnprintf(current->comm, sizeof(current->comm), name, args);
-        va_end(args);
-
-        /*
-         * If we were started as result of loading a module, close all of the
-         * user space pages.  We don't need them, and if we didn't close them
-         * they would be locked into memory.
-         */
-        exit_mm(current);
-        /*
-         * We don't want to get frozen, in case system-wide hibernation
-         * or suspend transition begins right now.
-         */
-        current->flags |= (PF_NOFREEZE | PF_KTHREAD);
-
-        if (current->nsproxy != &init_nsproxy) {
-                get_nsproxy(&init_nsproxy);
-                switch_task_namespaces(current, &init_nsproxy);
-        }
-        set_special_pids(&init_struct_pid);
-        proc_clear_tty(current);
-
-        /* Block and flush all signals */
-        sigfillset(&blocked);
-        sigprocmask(SIG_BLOCK, &blocked, NULL);
-        flush_signals(current);
-
-        /* Become as one with the init task */
-
-        daemonize_fs_struct();
-        daemonize_descriptors();
-
-        reparent_to_kthreadd();
-}
-
-EXPORT_SYMBOL(daemonize);
-
 #ifdef CONFIG_MM_OWNER
 /*
  * A task is exiting.   If it owned this mm, find a new owner for the mm.
diff --git a/kernel/fork.c b/kernel/fork.c
index 79de9f99a48d..3c31e874afad 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1129,7 +1129,6 @@ static void posix_cpu_timers_init(struct task_struct *tsk)
  */
 static struct task_struct *copy_process(unsigned long clone_flags,
                                         unsigned long stack_start,
-                                        struct pt_regs *regs,
                                         unsigned long stack_size,
                                         int __user *child_tidptr,
                                         struct pid *pid,
@@ -1321,7 +1320,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         retval = copy_io(clone_flags, p);
         if (retval)
                 goto bad_fork_cleanup_namespaces;
-        retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
+        retval = copy_thread(clone_flags, stack_start, stack_size, p);
         if (retval)
                 goto bad_fork_cleanup_io;
 
@@ -1510,12 +1509,6 @@ fork_out:
         return ERR_PTR(retval);
 }
 
-noinline struct pt_regs * __cpuinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
-{
-        memset(regs, 0, sizeof(struct pt_regs));
-        return regs;
-}
-
 static inline void init_idle_pids(struct pid_link *links)
 {
         enum pid_type type;
@@ -1529,10 +1522,7 @@ static inline void init_idle_pids(struct pid_link *links)
 struct task_struct * __cpuinit fork_idle(int cpu)
 {
         struct task_struct *task;
-        struct pt_regs regs;
-
-        task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL,
-                            &init_struct_pid, 0);
+        task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0);
         if (!IS_ERR(task)) {
                 init_idle_pids(task->pids);
                 init_idle(task, cpu);
@@ -1549,7 +1539,6 @@ struct task_struct * __cpuinit fork_idle(int cpu)
  */
 long do_fork(unsigned long clone_flags,
               unsigned long stack_start,
-              struct pt_regs *regs,
               unsigned long stack_size,
               int __user *parent_tidptr,
               int __user *child_tidptr)
@@ -1579,7 +1568,7 @@ long do_fork(unsigned long clone_flags,
          * requested, no event is reported; otherwise, report if the event
          * for the type of forking is enabled.
          */
-        if (!(clone_flags & CLONE_UNTRACED) && likely(user_mode(regs))) {
+        if (!(clone_flags & CLONE_UNTRACED)) {
                 if (clone_flags & CLONE_VFORK)
                         trace = PTRACE_EVENT_VFORK;
                 else if ((clone_flags & CSIGNAL) != SIGCHLD)
@@ -1591,7 +1580,7 @@ long do_fork(unsigned long clone_flags,
                         trace = 0;
         }
 
-        p = copy_process(clone_flags, stack_start, regs, stack_size,
+        p = copy_process(clone_flags, stack_start, stack_size,
                          child_tidptr, NULL, trace);
         /*
          * Do this prior waking up the new thread - the thread pointer
@@ -1635,11 +1624,54 @@ long do_fork(unsigned long clone_flags,
  */
 pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 {
-        return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn, NULL,
+        return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn,
                 (unsigned long)arg, NULL, NULL);
 }
 #endif
 
+#ifdef __ARCH_WANT_SYS_FORK
+SYSCALL_DEFINE0(fork)
+{
+#ifdef CONFIG_MMU
+        return do_fork(SIGCHLD, 0, 0, NULL, NULL);
+#else
+        /* can not support in nommu mode */
+        return(-EINVAL);
+#endif
+}
+#endif
+
+#ifdef __ARCH_WANT_SYS_VFORK
+SYSCALL_DEFINE0(vfork)
+{
+        return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, 
+                        0, NULL, NULL);
+}
+#endif
+
+#ifdef __ARCH_WANT_SYS_CLONE
+#ifdef CONFIG_CLONE_BACKWARDS
+SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
+                 int __user *, parent_tidptr,
+                 int, tls_val,
+                 int __user *, child_tidptr)
+#elif defined(CONFIG_CLONE_BACKWARDS2)
+SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags,
+                 int __user *, parent_tidptr,
+                 int __user *, child_tidptr,
+                 int, tls_val)
+#else
+SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
+                 int __user *, parent_tidptr,
+                 int __user *, child_tidptr,
+                 int, tls_val)
+#endif
+{
+        return do_fork(clone_flags, newsp, 0,
+                parent_tidptr, child_tidptr);
+}
+#endif
+
 #ifndef ARCH_MIN_MMSTRUCT_ALIGN
 #define ARCH_MIN_MMSTRUCT_ALIGN 0
 #endif
diff --git a/kernel/signal.c b/kernel/signal.c
index 5ffb5626e072..a49c7f36ceb3 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1159,8 +1159,9 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
         return __send_signal(sig, info, t, group, from_ancestor_ns);
 }
 
-static void print_fatal_signal(struct pt_regs *regs, int signr)
+static void print_fatal_signal(int signr)
 {
+        struct pt_regs *regs = signal_pt_regs();
         printk("%s/%d: potentially unexpected fatal signal %d.\n",
                 current->comm, task_pid_nr(current), signr);
 
@@ -2131,10 +2132,9 @@ static void do_jobctl_trap(void)
         }
 }
 
-static int ptrace_signal(int signr, siginfo_t *info,
-                         struct pt_regs *regs, void *cookie)
+static int ptrace_signal(int signr, siginfo_t *info)
 {
-        ptrace_signal_deliver(regs, cookie);
+        ptrace_signal_deliver();
         /*
          * We do not check sig_kernel_stop(signr) but set this marker
          * unconditionally because we do not know whether debugger will
@@ -2257,8 +2257,7 @@ relock:
                         break; /* will return 0 */
 
                 if (unlikely(current->ptrace) && signr != SIGKILL) {
-                        signr = ptrace_signal(signr, info,
-                                              regs, cookie);
+                        signr = ptrace_signal(signr, info);
                         if (!signr)
                                 continue;
                 }
@@ -2343,7 +2342,7 @@ relock:
 
                 if (sig_kernel_coredump(signr)) {
                         if (print_fatal_signals)
-                                print_fatal_signal(regs, info->si_signo);
+                                print_fatal_signal(info->si_signo);
                         /*
                          * If it was able to dump core, this kills all
                          * other threads in the group and synchronizes with
@@ -2352,7 +2351,7 @@ relock:
                          * first and our do_group_exit call below will use
                          * that value and ignore the one we pass it.
                          */
-                        do_coredump(info, regs);
+                        do_coredump(info);
                 }
 
                 /*