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

…/git/viro/signal

Pull generic execve() changes from Al Viro:
 "This introduces the generic kernel_thread() and kernel_execve()
  functions, and switches x86, arm, alpha, um and s390 over to them."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal: (26 commits)
  s390: convert to generic kernel_execve()
  s390: switch to generic kernel_thread()
  s390: fold kernel_thread_helper() into ret_from_fork()
  s390: fold execve_tail() into start_thread(), convert to generic sys_execve()
  um: switch to generic kernel_thread()
  x86, um/x86: switch to generic sys_execve and kernel_execve
  x86: split ret_from_fork
  alpha: introduce ret_from_kernel_execve(), switch to generic kernel_execve()
  alpha: switch to generic kernel_thread()
  alpha: switch to generic sys_execve()
  arm: get rid of execve wrapper, switch to generic execve() implementation
  arm: optimized current_pt_regs()
  arm: introduce ret_from_kernel_execve(), switch to generic kernel_execve()
  arm: split ret_from_fork, simplify kernel_thread() [based on patch by rmk]
  generic sys_execve()
  generic kernel_execve()
  new helper: current_pt_regs()
  preparation for generic kernel_thread()
  um: kill thread->forking
  um: let signal_delivered() do SIGTRAP on singlestepping into handler
  ...

arch/Kconfig

@@ -271,6 +271,9 @@ config ARCH_WANT_OLD_COMPAT_IPC
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	bool
 
+config GENERIC_KERNEL_THREAD
+	bool
+
 config HAVE_ARCH_SECCOMP_FILTER
 	bool
 	help

arch/alpha/Kconfig

@@ -20,6 +20,7 @@ config ALPHA
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
+	select GENERIC_KERNEL_THREAD
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,

arch/alpha/include/asm/Kbuild

@@ -10,3 +10,4 @@ header-y += pal.h
 header-y += reg.h
 header-y += regdef.h
 header-y += sysinfo.h
+generic-y += exec.h

arch/alpha/include/asm/processor.h

@@ -49,9 +49,6 @@ extern void start_thread(struct pt_regs *, unsigned long, unsigned long);
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-/* Create a kernel thread without removing it from tasklists.  */
-extern long kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-
 unsigned long get_wchan(struct task_struct *p);
 
 #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc)

arch/alpha/include/asm/unistd.h

@@ -481,6 +481,8 @@
 #define __ARCH_WANT_SYS_OLDUMOUNT
 #define __ARCH_WANT_SYS_SIGPENDING
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_KERNEL_EXECVE
 
 /* "Conditional" syscalls.  What we want is
 

arch/alpha/kernel/alpha_ksyms.c

@@ -50,9 +50,6 @@ EXPORT_SYMBOL(alpha_read_fp_reg_s);
 EXPORT_SYMBOL(alpha_write_fp_reg);
 EXPORT_SYMBOL(alpha_write_fp_reg_s);
 
-/* entry.S */
-EXPORT_SYMBOL(kernel_thread);
-
 /* Networking helper routines. */
 EXPORT_SYMBOL(csum_tcpudp_magic);
 EXPORT_SYMBOL(ip_compute_csum);

arch/alpha/kernel/entry.S

@@ -609,59 +609,35 @@ ret_from_fork:
 .end ret_from_fork
 
 /*
- * kernel_thread(fn, arg, clone_flags)
+ * ... and new kernel threads - here
  */
 	.align 4
-	.globl	kernel_thread
-	.ent	kernel_thread
-kernel_thread:
-	/* We can be called from a module.  */
-	ldgp	$gp, 0($27)
-	.prologue 1
-	subq	$sp, SP_OFF+6*8, $sp
-	br	$1, 2f		/* load start address */
-
-	/* We've now "returned" from a fake system call.  */
-	unop
-	blt	$0, 1f		/* error?  */
-	ldi	$1, 0x3fff
-	beq	$20, 1f		/* parent or child?  */
-
-	bic	$sp, $1, $8	/* in child.  */
-	jsr	$26, ($27)
+	.globl	ret_from_kernel_thread
+	.ent	ret_from_kernel_thread
+ret_from_kernel_thread:
+	mov	$17, $16
+	jsr	$26, schedule_tail
+	mov	$9, $27
+	mov	$10, $16
+	jsr	$26, ($9)
 	ldgp	$gp, 0($26)
 	mov	$0, $16
 	mov	$31, $26
 	jmp	$31, sys_exit
+.end ret_from_kernel_thread
 
-1:	ret			/* in parent.  */
-
-	.align 4
-2:	/* Fake a system call stack frame, as we can't do system calls
-	   from kernel space.  Note that we store FN and ARG as they
-	   need to be set up in the child for the call.  Also store $8
-	   and $26 for use in the parent.  */
-	stq	$31, SP_OFF($sp)	/* ps */
-	stq	$1, SP_OFF+8($sp)	/* pc */
-	stq	$gp, SP_OFF+16($sp)	/* gp */
-	stq	$16, 136($sp)		/* $27; FN for child */
-	stq	$17, SP_OFF+24($sp)	/* $16; ARG for child */
-	stq	$8, 64($sp)		/* $8 */
-	stq	$26, 128($sp)		/* $26 */
+	.globl	ret_from_kernel_execve
+	.align	4
+	.ent	ret_from_kernel_execve
+ret_from_kernel_execve:
+	mov	$16, $sp
 	/* Avoid the HAE being gratuitously wrong, to avoid restoring it.  */
 	ldq	$2, alpha_mv+HAE_CACHE
 	stq	$2, 152($sp)		/* HAE */
+	mov	$31, $19		/* to disable syscall restarts */
+	br	$31, ret_to_user
 
-	/* Shuffle FLAGS to the front; add CLONE_VM.  */
-	ldi	$1, CLONE_VM|CLONE_UNTRACED
-	or	$18, $1, $16
-	bsr	$26, sys_clone
-
-	/* We don't actually care for a3 success widgetry in the kernel.
-	   Not for positive errno values.  */
-	stq	$0, 0($sp)		/* $0 */
-	br	ret_to_kernel
-.end kernel_thread
+.end	ret_from_kernel_execve
 
 
 /*
@@ -744,15 +720,6 @@ sys_rt_sigreturn:
 	br	ret_from_sys_call
 .end sys_rt_sigreturn
 
-	.align	4
-	.globl	sys_execve
-	.ent	sys_execve
-sys_execve:
-	.prologue 0
-	mov	$sp, $19
-	jmp	$31, do_sys_execve
-.end sys_execve
-
 	.align	4
 	.globl	alpha_ni_syscall
 	.ent	alpha_ni_syscall

arch/alpha/kernel/process.c

@@ -263,41 +263,42 @@ alpha_vfork(struct pt_regs *regs)
 
 /*
  * Copy an alpha thread..
- *
- * Note the "stack_offset" stuff: when returning to kernel mode, we need
- * to have some extra stack-space for the kernel stack that still exists
- * after the "ret_from_fork".  When returning to user mode, we only want
- * the space needed by the syscall stack frame (ie "struct pt_regs").
- * Use the passed "regs" pointer to determine how much space we need
- * for a kernel fork().
  */
 
 int
 copy_thread(unsigned long clone_flags, unsigned long usp,
-	    unsigned long unused,
+	    unsigned long arg,
 	    struct task_struct * p, struct pt_regs * regs)
 {
 	extern void ret_from_fork(void);
+	extern void ret_from_kernel_thread(void);
 
 	struct thread_info *childti = task_thread_info(p);
-	struct pt_regs * childregs;
-	struct switch_stack * childstack, *stack;
-	unsigned long stack_offset, settls;
-
-	stack_offset = PAGE_SIZE - sizeof(struct pt_regs);
-	if (!(regs->ps & 8))
-		stack_offset = (PAGE_SIZE-1) & (unsigned long) regs;
-	childregs = (struct pt_regs *)
-	  (stack_offset + PAGE_SIZE + task_stack_page(p));
-
+	struct pt_regs *childregs = task_pt_regs(p);
+	struct switch_stack *childstack, *stack;
+	unsigned long settls;
+
+	childstack = ((struct switch_stack *) childregs) - 1;
+	if (unlikely(!regs)) {
+		/* kernel thread */
+		memset(childstack, 0,
+			sizeof(struct switch_stack) + sizeof(struct pt_regs));
+		childstack->r26 = (unsigned long) ret_from_kernel_thread;
+		childstack->r9 = usp;	/* function */
+		childstack->r10 = arg;
+		childregs->hae = alpha_mv.hae_cache,
+		childti->pcb.usp = 0;
+		childti->pcb.ksp = (unsigned long) childstack;
+		childti->pcb.flags = 1;	/* set FEN, clear everything else */
+		return 0;
+	}
 	*childregs = *regs;
 	settls = regs->r20;
 	childregs->r0 = 0;
 	childregs->r19 = 0;
 	childregs->r20 = 1;	/* OSF/1 has some strange fork() semantics.  */
 	regs->r20 = 0;
 	stack = ((struct switch_stack *) regs) - 1;
-	childstack = ((struct switch_stack *) childregs) - 1;
 	*childstack = *stack;
 	childstack->r26 = (unsigned long) ret_from_fork;
 	childti->pcb.usp = usp;
@@ -385,27 +386,6 @@ dump_elf_task_fp(elf_fpreg_t *dest, struct task_struct *task)
 }
 EXPORT_SYMBOL(dump_elf_task_fp);
 
-/*
- * sys_execve() executes a new program.
- */
-asmlinkage int
-do_sys_execve(const char __user *ufilename,
-	      const char __user *const __user *argv,
-	      const char __user *const __user *envp, struct pt_regs *regs)
-{
-	int error;
-	char *filename;
-
-	filename = getname(ufilename);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-	error = do_execve(filename, argv, envp, regs);
-	putname(filename);
-out:
-	return error;
-}
-
 /*
  * Return saved PC of a blocked thread.  This assumes the frame
  * pointer is the 6th saved long on the kernel stack and that the
@@ -459,22 +439,3 @@ get_wchan(struct task_struct *p)
 	}
 	return pc;
 }
-
-int kernel_execve(const char *path, const char *const argv[], const char *const envp[])
-{
-	/* Avoid the HAE being gratuitously wrong, which would cause us
-	   to do the whole turn off interrupts thing and restore it.  */
-	struct pt_regs regs = {.hae = alpha_mv.hae_cache};
-	int err = do_execve(path, argv, envp, &regs);
-	if (!err) {
-		struct pt_regs *p = current_pt_regs();
-		/* copy regs to normal position and off to userland we go... */
-		*p = regs;
-		__asm__ __volatile__ (
-			"mov	%0, $sp;"
-			"br	$31, ret_from_sys_call"
-			: : "r"(p));
-	}
-	return err;
-}
-EXPORT_SYMBOL(kernel_execve);

arch/arm/Kconfig

@@ -52,6 +52,7 @@ config ARM
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select DCACHE_WORD_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && !CPU_BIG_ENDIAN
+	select GENERIC_KERNEL_THREAD
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and

arch/arm/include/asm/processor.h

@@ -85,11 +85,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define cpu_relax()			barrier()
 #endif
 
-/*
- * Create a new kernel thread
- */
-extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
 

arch/arm/include/asm/ptrace.h

@@ -254,6 +254,11 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs)
 	return regs->ARM_sp;
 }
 
+#define current_pt_regs(void) ({				\
+	register unsigned long sp asm ("sp");			\
+	(struct pt_regs *)((sp | (THREAD_SIZE - 1)) - 7) - 1;	\
+})
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */

arch/arm/include/asm/system.h

@@ -2,7 +2,6 @@
 #include <asm/barrier.h>
 #include <asm/compiler.h>
 #include <asm/cmpxchg.h>
-#include <asm/exec.h>
 #include <asm/switch_to.h>
 #include <asm/system_info.h>
 #include <asm/system_misc.h>

arch/arm/include/asm/unistd.h

@@ -478,6 +478,8 @@
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_SOCKETCALL
 #endif
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_KERNEL_EXECVE
 
 /*
  * "Conditional" syscalls

arch/arm/kernel/calls.S

@@ -20,7 +20,7 @@
 		CALL(sys_creat)
 		CALL(sys_link)
 /* 10 */	CALL(sys_unlink)
-		CALL(sys_execve_wrapper)
+		CALL(sys_execve)
 		CALL(sys_chdir)
 		CALL(OBSOLETE(sys_time))	/* used by libc4 */
 		CALL(sys_mknod)

arch/arm/kernel/entry-common.S

@@ -91,6 +91,30 @@ ENTRY(ret_from_fork)
 	b	ret_slow_syscall
 ENDPROC(ret_from_fork)
 
+ENTRY(ret_from_kernel_thread)
+ UNWIND(.fnstart)
+ UNWIND(.cantunwind)
+	bl	schedule_tail
+	mov	r0, r4
+	adr	lr, BSYM(1f)	@ kernel threads should not exit
+	mov	pc, r5
+1:	bl	do_exit
+	nop
+ UNWIND(.fnend)
+ENDPROC(ret_from_kernel_thread)
+
+/*
+ * turn a kernel thread into userland process
+ * use: ret_from_kernel_execve(struct pt_regs *normal)
+ */
+ENTRY(ret_from_kernel_execve)
+	mov	why, #0			@ not a syscall
+	str	why, [r0, #S_R0]	@ ... and we want 0 in ->ARM_r0 as well
+	get_thread_info tsk		@ thread structure
+	mov	sp, r0			@ stack pointer just under pt_regs
+	b	ret_slow_syscall
+ENDPROC(ret_from_kernel_execve)
+
 	.equ NR_syscalls,0
 #define CALL(x) .equ NR_syscalls,NR_syscalls+1
 #include "calls.S"
@@ -517,11 +541,6 @@ sys_vfork_wrapper:
 		b	sys_vfork
 ENDPROC(sys_vfork_wrapper)
 
-sys_execve_wrapper:
-		add	r3, sp, #S_OFF
-		b	sys_execve
-ENDPROC(sys_execve_wrapper)
-
 sys_clone_wrapper:
 		add	ip, sp, #S_OFF
 		str	ip, [sp, #4]