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

7 files changed, 73 insertions, 297 deletions

diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index 88571ff8eee..f259b37874e 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -16,7 +16,7 @@ obj-y	:= debugtraps.o dma-nommu.o dumpstack.o 		\
            machvec.o nmi_debug.o process.o                              \
            process_$(BITS).o ptrace.o ptrace_$(BITS).o                  \
            reboot.o return_address.o                                    \
-           setup.o signal_$(BITS).o sys_sh.o sys_sh$(BITS).o            \
+           setup.o signal_$(BITS).o sys_sh.o                            \
            syscalls_$(BITS).o time.o topology.o traps.o                 \
            traps_$(BITS).o unwinder.o
 
@@ -25,6 +25,7 @@ obj-y				+= iomap.o
 obj-$(CONFIG_HAS_IOPORT)        += ioport.o
 endif
 
+obj-$(CONFIG_SUPERH32)          += sys_sh32.o
 obj-y                           += cpu/
 obj-$(CONFIG_VSYSCALL)          += vsyscall/
 obj-$(CONFIG_SMP)               += smp.o
diff --git a/arch/sh/kernel/cpu/sh5/entry.S b/arch/sh/kernel/cpu/sh5/entry.S
index 7e605b95592..0c8d0377d40 100644
--- a/arch/sh/kernel/cpu/sh5/entry.S
+++ b/arch/sh/kernel/cpu/sh5/entry.S
@@ -1228,6 +1228,25 @@ ret_from_fork:
         pta     ret_from_syscall, tr0
         blink   tr0, ZERO
 
+.global ret_from_kernel_thread
+ret_from_kernel_thread:
+
+        movi    schedule_tail,r5
+        ori     r5, 1, r5
+        ptabs   r5, tr0
+        blink   tr0, LINK
+
+        ld.q    SP, FRAME_R(2), r2
+        ld.q    SP, FRAME_R(3), r3
+        ptabs   r3, tr0
+        blink   tr0, LINK
+
+        ld.q    SP, FRAME_S(FSPC), r2
+        addi    r2, 4, r2               /* Move PC, being pre-execution event */
+        st.q    SP, FRAME_S(FSPC), r2
+        pta     ret_from_syscall, tr0
+        blink   tr0, ZERO
+
 syscall_allowed:
         /* Use LINK to deflect the exit point, default is syscall_ret */
         pta     syscall_ret, tr0
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index b96489d8b27..9b6e4beeb29 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -297,6 +297,19 @@ ret_from_fork:
          mov    r0, r4
         bra     syscall_exit
          nop
+
+        .align  2
+        .globl  ret_from_kernel_thread
+ret_from_kernel_thread:
+        mov.l   1f, r8
+        jsr     @r8
+         mov    r0, r4
+        mov.l   @(OFF_R5,r15), r5   ! fn
+        jsr     @r5
+         mov.l  @(OFF_R4,r15), r4   ! arg
+        bra     syscall_exit
+         nop
+
         .align  2
 1:      .long   schedule_tail
 
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index ba7345f37bc..73eb66fc625 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -68,38 +68,6 @@ void show_regs(struct pt_regs * regs)
         show_code(regs);
 }
 
-/*
- * Create a kernel thread
- */
-__noreturn void kernel_thread_helper(void *arg, int (*fn)(void *))
-{
-        do_exit(fn(arg));
-}
-
-/* Don't use this in BL=1(cli).  Or else, CPU resets! */
-int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
-{
-        struct pt_regs regs;
-        int pid;
-
-        memset(&regs, 0, sizeof(regs));
-        regs.regs[4] = (unsigned long)arg;
-        regs.regs[5] = (unsigned long)fn;
-
-        regs.pc = (unsigned long)kernel_thread_helper;
-        regs.sr = SR_MD;
-#if defined(CONFIG_SH_FPU)
-        regs.sr |= SR_FD;
-#endif
-
-        /* Ok, create the new process.. */
-        pid = do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0,
-                      &regs, 0, NULL, NULL);
-
-        return pid;
-}
-EXPORT_SYMBOL(kernel_thread);
-
 void start_thread(struct pt_regs *regs, unsigned long new_pc,
                   unsigned long new_sp)
 {
@@ -157,10 +125,10 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
 EXPORT_SYMBOL(dump_fpu);
 
 asmlinkage void ret_from_fork(void);
+asmlinkage void ret_from_kernel_thread(void);
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-                unsigned long unused,
-                struct task_struct *p, struct pt_regs *regs)
+                unsigned long arg, struct task_struct *p)
 {
         struct thread_info *ti = task_thread_info(p);
         struct pt_regs *childregs;
@@ -177,29 +145,35 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
         }
 #endif
 
-        childregs = task_pt_regs(p);
-        *childregs = *regs;
+        memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
 
-        if (user_mode(regs)) {
-                childregs->regs[15] = usp;
-                ti->addr_limit = USER_DS;
-        } else {
-                childregs->regs[15] = (unsigned long)childregs;
+        childregs = task_pt_regs(p);
+        p->thread.sp = (unsigned long) childregs;
+        if (unlikely(p->flags & PF_KTHREAD)) {
+                memset(childregs, 0, sizeof(struct pt_regs));
+                p->thread.pc = (unsigned long) ret_from_kernel_thread;
+                childregs->regs[4] = arg;
+                childregs->regs[5] = usp;
+                childregs->sr = SR_MD;
+#if defined(CONFIG_SH_FPU)
+                childregs->sr |= SR_FD;
+#endif
                 ti->addr_limit = KERNEL_DS;
                 ti->status &= ~TS_USEDFPU;
                 p->fpu_counter = 0;
+                return 0;
         }
+        *childregs = *current_pt_regs();
+
+        if (usp)
+                childregs->regs[15] = usp;
+        ti->addr_limit = USER_DS;
 
         if (clone_flags & CLONE_SETTLS)
                 childregs->gbr = childregs->regs[0];
 
         childregs->regs[0] = 0; /* Set return value for child */
-
-        p->thread.sp = (unsigned long) childregs;
         p->thread.pc = (unsigned long) ret_from_fork;
-
-        memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
-
         return 0;
 }
 
@@ -243,74 +217,6 @@ __switch_to(struct task_struct *prev, struct task_struct *next)
         return prev;
 }
 
-asmlinkage int sys_fork(unsigned long r4, unsigned long r5,
-                        unsigned long r6, unsigned long r7,
-                        struct pt_regs __regs)
-{
-#ifdef CONFIG_MMU
-        struct pt_regs *regs = RELOC_HIDE(&__regs, 0);
-        return do_fork(SIGCHLD, regs->regs[15], regs, 0, NULL, NULL);
-#else
-        /* fork almost works, enough to trick you into looking elsewhere :-( */
-        return -EINVAL;
-#endif
-}
-
-asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp,
-                         unsigned long parent_tidptr,
-                         unsigned long child_tidptr,
-                         struct pt_regs __regs)
-{
-        struct pt_regs *regs = RELOC_HIDE(&__regs, 0);
-        if (!newsp)
-                newsp = regs->regs[15];
-        return do_fork(clone_flags, newsp, regs, 0,
-                        (int __user *)parent_tidptr,
-                        (int __user *)child_tidptr);
-}
-
-/*
- * This is trivial, and on the face of it looks like it
- * could equally well be done in user mode.
- *
- * Not so, for quite unobvious reasons - register pressure.
- * In user mode vfork() cannot have a stack frame, and if
- * done by calling the "clone()" system call directly, you
- * do not have enough call-clobbered registers to hold all
- * the information you need.
- */
-asmlinkage int sys_vfork(unsigned long r4, unsigned long r5,
-                         unsigned long r6, unsigned long r7,
-                         struct pt_regs __regs)
-{
-        struct pt_regs *regs = RELOC_HIDE(&__regs, 0);
-        return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->regs[15], regs,
-                       0, NULL, NULL);
-}
-
-/*
- * sys_execve() executes a new program.
- */
-asmlinkage int sys_execve(const char __user *ufilename,
-                          const char __user *const __user *uargv,
-                          const char __user *const __user *uenvp,
-                          unsigned long r7, struct pt_regs __regs)
-{
-        struct pt_regs *regs = RELOC_HIDE(&__regs, 0);
-        int error;
-        struct filename *filename;
-
-        filename = getname(ufilename);
-        error = PTR_ERR(filename);
-        if (IS_ERR(filename))
-                goto out;
-
-        error = do_execve(filename->name, uargv, uenvp, regs);
-        putname(filename);
-out:
-        return error;
-}
-
 unsigned long get_wchan(struct task_struct *p)
 {
         unsigned long pc;
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index 98a709f0c3c..e611c85144b 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -285,39 +285,6 @@ void show_regs(struct pt_regs *regs)
 }
 
 /*
- * Create a kernel thread
- */
-__noreturn void kernel_thread_helper(void *arg, int (*fn)(void *))
-{
-        do_exit(fn(arg));
-}
-
-/*
- * This is the mechanism for creating a new kernel thread.
- *
- * NOTE! Only a kernel-only process(ie the swapper or direct descendants
- * who haven't done an "execve()") should use this: it will work within
- * a system call from a "real" process, but the process memory space will
- * not be freed until both the parent and the child have exited.
- */
-int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
-{
-        struct pt_regs regs;
-
-        memset(&regs, 0, sizeof(regs));
-        regs.regs[2] = (unsigned long)arg;
-        regs.regs[3] = (unsigned long)fn;
-
-        regs.pc = (unsigned long)kernel_thread_helper;
-        regs.sr = (1 << 30);
-
-        /* Ok, create the new process.. */
-        return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0,
-                      &regs, 0, NULL, NULL);
-}
-EXPORT_SYMBOL(kernel_thread);
-
-/*
  * Free current thread data structures etc..
  */
 void exit_thread(void)
@@ -401,26 +368,37 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
 EXPORT_SYMBOL(dump_fpu);
 
 asmlinkage void ret_from_fork(void);
+asmlinkage void ret_from_kernel_thread(void);
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-                unsigned long unused,
-                struct task_struct *p, struct pt_regs *regs)
+                unsigned long arg, struct task_struct *p)
 {
-        struct pt_regs *childregs;
+        struct pt_regs *childregs, *regs = current_pt_regs();
 
 #ifdef CONFIG_SH_FPU
-        if(last_task_used_math == current) {
+        /* can't happen for a kernel thread */
+        if (last_task_used_math == current) {
                 enable_fpu();
                 save_fpu(current);
                 disable_fpu();
                 last_task_used_math = NULL;
-                regs->sr |= SR_FD;
+                current_pt_regs()->sr |= SR_FD;
         }
 #endif
         /* Copy from sh version */
         childregs = (struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1;
+        p->thread.sp = (unsigned long) childregs;
 
-        *childregs = *regs;
+        if (unlikely(p->flags & PF_KTHREAD)) {
+                memset(childregs, 0, sizeof(struct pt_regs));
+                childregs->regs[2] = (unsigned long)arg;
+                childregs->regs[3] = (unsigned long)fn;
+                childregs->sr = (1 << 30); /* not user_mode */
+                childregs->sr |= SR_FD; /* Invalidate FPU flag */
+                p->thread.pc = (unsigned long) ret_from_kernel_thread;
+                return 0;
+        }
+        *childregs = *current_pt_regs();
 
         /*
          * Sign extend the edited stack.
@@ -428,85 +406,18 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
          * 32-bit wide and context switch must take care
          * of NEFF sign extension.
          */
-        if (user_mode(regs)) {
+        if (usp)
                 childregs->regs[15] = neff_sign_extend(usp);
-                p->thread.uregs = childregs;
-        } else {
-                childregs->regs[15] =
-                        neff_sign_extend((unsigned long)task_stack_page(p) +
-                                         THREAD_SIZE);
-        }
+        p->thread.uregs = childregs;
 
         childregs->regs[9] = 0; /* Set return value for child */
         childregs->sr |= SR_FD; /* Invalidate FPU flag */
 
-        p->thread.sp = (unsigned long) childregs;
         p->thread.pc = (unsigned long) ret_from_fork;
 
         return 0;
 }
 
-asmlinkage int sys_fork(unsigned long r2, unsigned long r3,
-                        unsigned long r4, unsigned long r5,
-                        unsigned long r6, unsigned long r7,
-                        struct pt_regs *pregs)
-{
-        return do_fork(SIGCHLD, pregs->regs[15], pregs, 0, 0, 0);
-}
-
-asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp,
-                         unsigned long r4, unsigned long r5,
-                         unsigned long r6, unsigned long r7,
-                         struct pt_regs *pregs)
-{
-        if (!newsp)
-                newsp = pregs->regs[15];
-        return do_fork(clone_flags, newsp, pregs, 0, 0, 0);
-}
-
-/*
- * This is trivial, and on the face of it looks like it
- * could equally well be done in user mode.
- *
- * Not so, for quite unobvious reasons - register pressure.
- * In user mode vfork() cannot have a stack frame, and if
- * done by calling the "clone()" system call directly, you
- * do not have enough call-clobbered registers to hold all
- * the information you need.
- */
-asmlinkage int sys_vfork(unsigned long r2, unsigned long r3,
-                         unsigned long r4, unsigned long r5,
-                         unsigned long r6, unsigned long r7,
-                         struct pt_regs *pregs)
-{
-        return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, pregs->regs[15], pregs, 0, 0, 0);
-}
-
-/*
- * sys_execve() executes a new program.
- */
-asmlinkage int sys_execve(const char *ufilename, char **uargv,
-                          char **uenvp, unsigned long r5,
-                          unsigned long r6, unsigned long r7,
-                          struct pt_regs *pregs)
-{
-        int error;
-        struct filename *filename;
-
-        filename = getname((char __user *)ufilename);
-        error = PTR_ERR(filename);
-        if (IS_ERR(filename))
-                goto out;
-
-        error = do_execve(filename->name,
-                          (const char __user *const __user *)uargv,
-                          (const char __user *const __user *)uenvp,
-                          pregs);
-        putname(filename);
-out:
-        return error;
-}
-
 #ifdef CONFIG_FRAME_POINTER
 static int in_sh64_switch_to(unsigned long pc)
 {
diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c
index f56b6fe5c5d..497bab3a040 100644
--- a/arch/sh/kernel/sys_sh32.c
+++ b/arch/sh/kernel/sys_sh32.c
@@ -60,27 +60,3 @@ asmlinkage int sys_fadvise64_64_wrapper(int fd, u32 offset0, u32 offset1,
                                 (u64)len0 << 32 | len1, advice);
 #endif
 }
-
-#if defined(CONFIG_CPU_SH2) || defined(CONFIG_CPU_SH2A)
-#define SYSCALL_ARG3    "trapa #0x23"
-#else
-#define SYSCALL_ARG3    "trapa #0x13"
-#endif
-
-/*
- * Do a system call from kernel instead of calling sys_execve so we
- * end up with proper pt_regs.
- */
-int kernel_execve(const char *filename,
-                  const char *const argv[],
-                  const char *const envp[])
-{
-        register long __sc0 __asm__ ("r3") = __NR_execve;
-        register long __sc4 __asm__ ("r4") = (long) filename;
-        register long __sc5 __asm__ ("r5") = (long) argv;
-        register long __sc6 __asm__ ("r6") = (long) envp;
-        __asm__ __volatile__ (SYSCALL_ARG3 : "=z" (__sc0)
-                        : "0" (__sc0), "r" (__sc4), "r" (__sc5), "r" (__sc6)
-                        : "memory");
-        return __sc0;
-}
diff --git a/arch/sh/kernel/sys_sh64.c b/arch/sh/kernel/sys_sh64.c
deleted file mode 100644
index c5a38c4bf41..00000000000
--- a/arch/sh/kernel/sys_sh64.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * arch/sh/kernel/sys_sh64.c
- *
- * Copyright (C) 2000, 2001  Paolo Alberelli
- *
- * This file contains various random system calls that
- * have a non-standard calling sequence on the Linux/SH5
- * platform.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/errno.h>
-#include <linux/rwsem.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/smp.h>
-#include <linux/sem.h>
-#include <linux/msg.h>
-#include <linux/shm.h>
-#include <linux/stat.h>
-#include <linux/mman.h>
-#include <linux/file.h>
-#include <linux/syscalls.h>
-#include <linux/ipc.h>
-#include <asm/uaccess.h>
-#include <asm/ptrace.h>
-#include <asm/unistd.h>
-
-/*
- * Do a system call from kernel instead of calling sys_execve so we
- * end up with proper pt_regs.
- */
-int kernel_execve(const char *filename,
-                  const char *const argv[],
-                  const char *const envp[])
-{
-        register unsigned long __sc0 __asm__ ("r9") = ((0x13 << 16) | __NR_execve);
-        register unsigned long __sc2 __asm__ ("r2") = (unsigned long) filename;
-        register unsigned long __sc3 __asm__ ("r3") = (unsigned long) argv;
-        register unsigned long __sc4 __asm__ ("r4") = (unsigned long) envp;
-        __asm__ __volatile__ ("trapa    %1 !\t\t\t execve(%2,%3,%4)"
-        : "=r" (__sc0)
-        : "r" (__sc0), "r" (__sc2), "r" (__sc3), "r" (__sc4) );
-        __asm__ __volatile__ ("!dummy   %0 %1 %2 %3"
-        : : "r" (__sc0), "r" (__sc2), "r" (__sc3), "r" (__sc4) : "memory");
-        return __sc0;
-}