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

8 files changed, 90 insertions, 182 deletions

diff --git a/arch/tile/kernel/compat.c b/arch/tile/kernel/compat.c
index d67459b9ac2a..9cd7cb6041c0 100644
--- a/arch/tile/kernel/compat.c
+++ b/arch/tile/kernel/compat.c
@@ -102,9 +102,7 @@ long compat_sys_sched_rr_get_interval(compat_pid_t pid,
 #define compat_sys_fadvise64_64 sys32_fadvise64_64
 #define compat_sys_readahead sys32_readahead
 
-/* Call the trampolines to manage pt_regs where necessary. */
-#define compat_sys_execve _compat_sys_execve
-#define compat_sys_sigaltstack _compat_sys_sigaltstack
+/* Call the assembly trampolines where necessary. */
 #define compat_sys_rt_sigreturn _compat_sys_rt_sigreturn
 #define sys_clone _sys_clone
 
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index 08b4fe1717bb..2e4cc69224a6 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -197,8 +197,7 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
 }
 
 long compat_sys_sigaltstack(const struct compat_sigaltstack __user *uss_ptr,
-			    struct compat_sigaltstack __user *uoss_ptr,
-			    struct pt_regs *regs)
+			    struct compat_sigaltstack __user *uoss_ptr)
 {
 	stack_t uss, uoss;
 	int ret;
@@ -219,7 +218,7 @@ long compat_sys_sigaltstack(const struct compat_sigaltstack __user *uss_ptr,
 	set_fs(KERNEL_DS);
 	ret = do_sigaltstack(uss_ptr ? (stack_t __user __force *)&uss : NULL,
 			     (stack_t __user __force *)&uoss,
-			     (unsigned long)compat_ptr(regs->sp));
+			     (unsigned long)compat_ptr(current_pt_regs()->sp));
 	set_fs(seg);
 	if (ret >= 0 && uoss_ptr)  {
 		if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(*uoss_ptr)) ||
@@ -232,8 +231,9 @@ long compat_sys_sigaltstack(const struct compat_sigaltstack __user *uss_ptr,
 }
 
 /* The assembly shim for this function arranges to ignore the return value. */
-long compat_sys_rt_sigreturn(struct pt_regs *regs)
+long compat_sys_rt_sigreturn(void)
 {
+	struct pt_regs *regs = current_pt_regs();
 	struct compat_rt_sigframe __user *frame =
 		(struct compat_rt_sigframe __user *) compat_ptr(regs->sp);
 	sigset_t set;
@@ -248,7 +248,7 @@ long compat_sys_rt_sigreturn(struct pt_regs *regs)
 	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
 		goto badframe;
 
-	if (compat_sys_sigaltstack(&frame->uc.uc_stack, NULL, regs) != 0)
+	if (compat_sys_sigaltstack(&frame->uc.uc_stack, NULL) == -EFAULT)
 		goto badframe;
 
 	return 0;
diff --git a/arch/tile/kernel/entry.S b/arch/tile/kernel/entry.S
index c31637baff28..f116cb0bce20 100644
--- a/arch/tile/kernel/entry.S
+++ b/arch/tile/kernel/entry.S
@@ -28,17 +28,6 @@ STD_ENTRY(current_text_addr)
 	STD_ENDPROC(current_text_addr)
 
 /*
- * Implement execve().  The i386 code has a note that forking from kernel
- * space results in no copy on write until the execve, so we should be
- * careful not to write to the stack here.
- */
-STD_ENTRY(kernel_execve)
-	moveli TREG_SYSCALL_NR_NAME, __NR_execve
-	swint1
-	jrp lr
-	STD_ENDPROC(kernel_execve)
-
-/*
  * We don't run this function directly, but instead copy it to a page
  * we map into every user process.  See vdso_setup().
  *
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index 6943515100f8..f212bf7cea86 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -1291,6 +1291,21 @@ STD_ENTRY(ret_from_fork)
 	}
 	STD_ENDPROC(ret_from_fork)
 
+STD_ENTRY(ret_from_kernel_thread)
+	jal     sim_notify_fork
+	jal     schedule_tail
+	FEEDBACK_REENTER(ret_from_fork)
+	{
+	 move   r0, r31
+	 jalr   r30
+	}
+	FEEDBACK_REENTER(ret_from_kernel_thread)
+	{
+	 movei  r30, 0               /* not an NMI */
+	 j      .Lresume_userspace   /* jump into middle of interrupt_return */
+	}
+	STD_ENDPROC(ret_from_kernel_thread)
+
 	/*
 	 * Code for ill interrupt.
 	 */
@@ -1437,15 +1452,6 @@ STD_ENTRY_LOCAL(bad_intr)
 	panic   "Unhandled interrupt %#x: PC %#lx"
 	STD_ENDPROC(bad_intr)
 
-/* Put address of pt_regs in reg and jump. */
-#define PTREGS_SYSCALL(x, reg)                          \
-	STD_ENTRY(_##x);                                \
-	{                                               \
-	 PTREGS_PTR(reg, PTREGS_OFFSET_BASE);           \
-	 j      x                                       \
-	};                                              \
-	STD_ENDPROC(_##x)
-
 /*
  * Special-case sigreturn to not write r0 to the stack on return.
  * This is technically more efficient, but it also avoids difficulties
@@ -1461,12 +1467,9 @@ STD_ENTRY_LOCAL(bad_intr)
 	};                                              \
 	STD_ENDPROC(_##x)
 
-PTREGS_SYSCALL(sys_execve, r3)
-PTREGS_SYSCALL(sys_sigaltstack, r2)
 PTREGS_SYSCALL_SIGRETURN(sys_rt_sigreturn, r0)
-PTREGS_SYSCALL(sys_cmpxchg_badaddr, r1)
 
-/* Save additional callee-saves to pt_regs, put address in r4 and jump. */
+/* Save additional callee-saves to pt_regs and jump to standard function. */
 STD_ENTRY(_sys_clone)
 	push_extra_callee_saves r4
 	j       sys_clone
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
index 7c06d597ffd0..54bc9a6678e8 100644
--- a/arch/tile/kernel/intvec_64.S
+++ b/arch/tile/kernel/intvec_64.S
@@ -1150,6 +1150,21 @@ STD_ENTRY(ret_from_fork)
 	}
 	STD_ENDPROC(ret_from_fork)
 
+STD_ENTRY(ret_from_kernel_thread)
+	jal     sim_notify_fork
+	jal     schedule_tail
+	FEEDBACK_REENTER(ret_from_fork)
+	{
+	 move   r0, r31
+	 jalr   r30
+	}
+	FEEDBACK_REENTER(ret_from_kernel_thread)
+	{
+	 movei  r30, 0               /* not an NMI */
+	 j      .Lresume_userspace   /* jump into middle of interrupt_return */
+	}
+	STD_ENDPROC(ret_from_kernel_thread)
+
 /* Various stub interrupt handlers and syscall handlers */
 
 STD_ENTRY_LOCAL(_kernel_double_fault)
@@ -1166,15 +1181,6 @@ STD_ENTRY_LOCAL(bad_intr)
 	panic   "Unhandled interrupt %#x: PC %#lx"
 	STD_ENDPROC(bad_intr)
 
-/* Put address of pt_regs in reg and jump. */
-#define PTREGS_SYSCALL(x, reg)                          \
-	STD_ENTRY(_##x);                                \
-	{                                               \
-	 PTREGS_PTR(reg, PTREGS_OFFSET_BASE);           \
-	 j      x                                       \
-	};                                              \
-	STD_ENDPROC(_##x)
-
 /*
  * Special-case sigreturn to not write r0 to the stack on return.
  * This is technically more efficient, but it also avoids difficulties
@@ -1190,16 +1196,12 @@ STD_ENTRY_LOCAL(bad_intr)
 	};                                              \
 	STD_ENDPROC(_##x)
 
-PTREGS_SYSCALL(sys_execve, r3)
-PTREGS_SYSCALL(sys_sigaltstack, r2)
 PTREGS_SYSCALL_SIGRETURN(sys_rt_sigreturn, r0)
 #ifdef CONFIG_COMPAT
-PTREGS_SYSCALL(compat_sys_execve, r3)
-PTREGS_SYSCALL(compat_sys_sigaltstack, r2)
 PTREGS_SYSCALL_SIGRETURN(compat_sys_rt_sigreturn, r0)
 #endif
 
-/* Save additional callee-saves to pt_regs, put address in r4 and jump. */
+/* Save additional callee-saves to pt_regs and jump to standard function. */
 STD_ENTRY(_sys_clone)
 	push_extra_callee_saves r4
 	j       sys_clone
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 307d010696c9..0e5661e7d00d 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -157,24 +157,43 @@ void arch_release_thread_info(struct thread_info *info)
 static void save_arch_state(struct thread_struct *t);
 
 int copy_thread(unsigned long clone_flags, unsigned long sp,
-		unsigned long stack_size,
-		struct task_struct *p, struct pt_regs *regs)
+		unsigned long arg, struct task_struct *p)
 {
-	struct pt_regs *childregs;
+	struct pt_regs *childregs = task_pt_regs(p), *regs = current_pt_regs();
 	unsigned long ksp;
+	unsigned long *callee_regs;
 
 	/*
-	 * When creating a new kernel thread we pass sp as zero.
-	 * Assign it to a reasonable value now that we have the stack.
+	 * Set up the stack and stack pointer appropriately for the
+	 * new child to find itself woken up in __switch_to().
+	 * The callee-saved registers must be on the stack to be read;
+	 * the new task will then jump to assembly support to handle
+	 * calling schedule_tail(), etc., and (for userspace tasks)
+	 * returning to the context set up in the pt_regs.
 	 */
-	if (sp == 0 && regs->ex1 == PL_ICS_EX1(KERNEL_PL, 0))
-		sp = KSTK_TOP(p);
+	ksp = (unsigned long) childregs;
+	ksp -= C_ABI_SAVE_AREA_SIZE;   /* interrupt-entry save area */
+	((long *)ksp)[0] = ((long *)ksp)[1] = 0;
+	ksp -= CALLEE_SAVED_REGS_COUNT * sizeof(unsigned long);
+	callee_regs = (unsigned long *)ksp;
+	ksp -= C_ABI_SAVE_AREA_SIZE;   /* __switch_to() save area */
+	((long *)ksp)[0] = ((long *)ksp)[1] = 0;
+	p->thread.ksp = ksp;
 
-	/*
-	 * Do not clone step state from the parent; each thread
-	 * must make its own lazily.
-	 */
-	task_thread_info(p)->step_state = NULL;
+	/* Record the pid of the task that created this one. */
+	p->thread.creator_pid = current->pid;
+
+	if (unlikely(p->flags & PF_KTHREAD)) {
+		/* kernel thread */
+		memset(childregs, 0, sizeof(struct pt_regs));
+		memset(&callee_regs[2], 0,
+		       (CALLEE_SAVED_REGS_COUNT - 2) * sizeof(unsigned long));
+		callee_regs[0] = sp;   /* r30 = function */
+		callee_regs[1] = arg;  /* r31 = arg */
+		childregs->ex1 = PL_ICS_EX1(KERNEL_PL, 0);
+		p->thread.pc = (unsigned long) ret_from_kernel_thread;
+		return 0;
+	}
 
 	/*
 	 * Start new thread in ret_from_fork so it schedules properly
@@ -182,46 +201,33 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	 */
 	p->thread.pc = (unsigned long) ret_from_fork;
 
-	/* Save user stack top pointer so we can ID the stack vm area later. */
-	p->thread.usp0 = sp;
-
-	/* Record the pid of the process that created this one. */
-	p->thread.creator_pid = current->pid;
+	/*
+	 * Do not clone step state from the parent; each thread
+	 * must make its own lazily.
+	 */
+	task_thread_info(p)->step_state = NULL;
 
 	/*
 	 * Copy the registers onto the kernel stack so the
 	 * return-from-interrupt code will reload it into registers.
 	 */
-	childregs = task_pt_regs(p);
-	*childregs = *regs;
+	*childregs = *current_pt_regs();
 	childregs->regs[0] = 0;         /* return value is zero */
-	childregs->sp = sp;  /* override with new user stack pointer */
+	if (sp)
+		childregs->sp = sp;  /* override with new user stack pointer */
+	memcpy(callee_regs, &childregs->regs[CALLEE_SAVED_FIRST_REG],
+	       CALLEE_SAVED_REGS_COUNT * sizeof(unsigned long));
+
+	/* Save user stack top pointer so we can ID the stack vm area later. */
+	p->thread.usp0 = childregs->sp;
 
 	/*
 	 * If CLONE_SETTLS is set, set "tp" in the new task to "r4",
 	 * which is passed in as arg #5 to sys_clone().
 	 */
 	if (clone_flags & CLONE_SETTLS)
-		childregs->tp = regs->regs[4];
+		childregs->tp = childregs->regs[4];
 
-	/*
-	 * Copy the callee-saved registers from the passed pt_regs struct
-	 * into the context-switch callee-saved registers area.
-	 * This way when we start the interrupt-return sequence, the
-	 * callee-save registers will be correctly in registers, which
-	 * is how we assume the compiler leaves them as we start doing
-	 * the normal return-from-interrupt path after calling C code.
-	 * Zero out the C ABI save area to mark the top of the stack.
-	 */
-	ksp = (unsigned long) childregs;
-	ksp -= C_ABI_SAVE_AREA_SIZE;   /* interrupt-entry save area */
-	((long *)ksp)[0] = ((long *)ksp)[1] = 0;
-	ksp -= CALLEE_SAVED_REGS_COUNT * sizeof(unsigned long);
-	memcpy((void *)ksp, &regs->regs[CALLEE_SAVED_FIRST_REG],
-	       CALLEE_SAVED_REGS_COUNT * sizeof(unsigned long));
-	ksp -= C_ABI_SAVE_AREA_SIZE;   /* __switch_to() save area */
-	((long *)ksp)[0] = ((long *)ksp)[1] = 0;
-	p->thread.ksp = ksp;
 
 #if CHIP_HAS_TILE_DMA()
 	/*
@@ -577,62 +583,6 @@ int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
 	panic("work_pending: bad flags %#x\n", thread_info_flags);
 }
 
-/* Note there is an implicit fifth argument if (clone_flags & CLONE_SETTLS). */
-SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
-		void __user *, parent_tidptr, void __user *, child_tidptr,
-		struct pt_regs *, regs)
-{
-	if (!newsp)
-		newsp = regs->sp;
-	return do_fork(clone_flags, newsp, regs, 0,
-		       parent_tidptr, child_tidptr);
-}
-
-/*
- * sys_execve() executes a new program.
- */
-SYSCALL_DEFINE4(execve, const char __user *, path,
-		const char __user *const __user *, argv,
-		const char __user *const __user *, envp,
-		struct pt_regs *, regs)
-{
-	long error;
-	struct filename *filename;
-
-	filename = getname(path);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-	error = do_execve(filename->name, argv, envp, regs);
-	putname(filename);
-	if (error == 0)
-		single_step_execve();
-out:
-	return error;
-}
-
-#ifdef CONFIG_COMPAT
-long compat_sys_execve(const char __user *path,
-		       compat_uptr_t __user *argv,
-		       compat_uptr_t __user *envp,
-		       struct pt_regs *regs)
-{
-	long error;
-	struct filename *filename;
-
-	filename = getname(path);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-	error = compat_do_execve(filename->name, argv, envp, regs);
-	putname(filename);
-	if (error == 0)
-		single_step_execve();
-out:
-	return error;
-}
-#endif
-
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct KBacktraceIterator kbt;
@@ -650,37 +600,6 @@ unsigned long get_wchan(struct task_struct *p)
 	return 0;
 }
 
-/*
- * We pass in lr as zero (cleared in kernel_thread) and the caller
- * part of the backtrace ABI on the stack also zeroed (in copy_thread)
- * so that backtraces will stop with this function.
- * Note that we don't use r0, since copy_thread() clears it.
- */
-static void start_kernel_thread(int dummy, int (*fn)(int), int arg)
-{
-	do_exit(fn(arg));
-}
-
-/*
- * Create a kernel thread
- */
-int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
-{
-	struct pt_regs regs;
-
-	memset(&regs, 0, sizeof(regs));
-	regs.ex1 = PL_ICS_EX1(KERNEL_PL, 0);  /* run at kernel PL, no ICS */
-	regs.pc = (long) start_kernel_thread;
-	regs.flags = PT_FLAGS_CALLER_SAVES;   /* need to restore r1 and r2 */
-	regs.regs[1] = (long) fn;             /* function pointer */
-	regs.regs[2] = (long) arg;            /* parameter register */
-
-	/* Ok, create the new process.. */
-	return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs,
-		       0, NULL, NULL);
-}
-EXPORT_SYMBOL(kernel_thread);
-
 /* Flush thread state. */
 void flush_thread(void)
 {
diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c
index 67efb656d104..657a7ace4ab4 100644
--- a/arch/tile/kernel/signal.c
+++ b/arch/tile/kernel/signal.c
@@ -37,10 +37,10 @@
 
 #define DEBUG_SIG 0
 
-SYSCALL_DEFINE3(sigaltstack, const stack_t __user *, uss,
-		stack_t __user *, uoss, struct pt_regs *, regs)
+SYSCALL_DEFINE2(sigaltstack, const stack_t __user *, uss,
+		stack_t __user *, uoss)
 {
-	return do_sigaltstack(uss, uoss, regs->sp);
+	return do_sigaltstack(uss, uoss, current_pt_regs()->sp);
 }
 
 
@@ -83,8 +83,9 @@ void signal_fault(const char *type, struct pt_regs *regs,
 }
 
 /* The assembly shim for this function arranges to ignore the return value. */
-SYSCALL_DEFINE1(rt_sigreturn, struct pt_regs *, regs)
+SYSCALL_DEFINE0(rt_sigreturn)
 {
+	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe __user *frame =
 		(struct rt_sigframe __user *)(regs->sp);
 	sigset_t set;
diff --git a/arch/tile/kernel/sys.c b/arch/tile/kernel/sys.c
index b08095b402d6..b881a7be24bd 100644
--- a/arch/tile/kernel/sys.c
+++ b/arch/tile/kernel/sys.c
@@ -106,14 +106,10 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 #define sys_readahead sys32_readahead
 #endif
 
-/* Call the trampolines to manage pt_regs where necessary. */
-#define sys_execve _sys_execve
-#define sys_sigaltstack _sys_sigaltstack
+/* Call the assembly trampolines where necessary. */
+#undef sys_rt_sigreturn
 #define sys_rt_sigreturn _sys_rt_sigreturn
 #define sys_clone _sys_clone
-#ifndef __tilegx__
-#define sys_cmpxchg_badaddr _sys_cmpxchg_badaddr
-#endif
 
 /*
  * Note that we can't include <linux/unistd.h> here since the header