ia64: switch to generic kernel_thread()/kernel_execve()

Acked-by: Tony Luck <tony.luck@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

5 files changed, 82 insertions, 107 deletions

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 3279646120e3..670600468128 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -42,6 +42,8 @@ config IA64
 	select GENERIC_TIME_VSYSCALL_OLD
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
+	select GENERIC_KERNEL_THREAD
+	select GENERIC_KERNEL_EXECVE
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 944152a50912..e0a899a1a8a6 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -340,22 +340,6 @@ struct task_struct;
  */
 #define release_thread(dead_task)
 
-/*
- * This is the mechanism for creating a new kernel thread.
- *
- * NOTE 1: 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 free'd until both the parent and
- * the child have exited.
- *
- * NOTE 2: This MUST NOT be an inlined function.  Otherwise, we get
- * into trouble in init/main.c when the child thread returns to
- * do_basic_setup() and the timing is such that free_initmem() has
- * been called already.
- */
-extern pid_t kernel_thread (int (*fn)(void *), void *arg, unsigned long flags);
-
 /* Get wait channel for task P.  */
 extern unsigned long get_wchan (struct task_struct *p);
 
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 6b0648d97b4c..0dea684e1905 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -484,13 +484,6 @@ GLOBAL_ENTRY(prefetch_stack)
 	br.ret.sptk.many rp
 END(prefetch_stack)
 
-GLOBAL_ENTRY(kernel_execve)
-	rum psr.ac
-	mov r15=__NR_execve			// put syscall number in place
-	break __BREAK_SYSCALL
-	br.ret.sptk.many rp
-END(kernel_execve)
-
 	/*
 	 * Invoke a system call, but do some tracing before and after the call.
 	 * We MUST preserve the current register frame throughout this routine
@@ -594,6 +587,27 @@ GLOBAL_ENTRY(ia64_strace_leave_kernel)
 .ret4:	br.cond.sptk ia64_leave_kernel
 END(ia64_strace_leave_kernel)
 
+ENTRY(call_payload)
+	.prologue ASM_UNW_PRLG_RP|ASM_UNW_PRLG_PFS, ASM_UNW_PRLG_GRSAVE(0)
+	/* call the kernel_thread payload; fn is in r4, arg - in r5 */
+	alloc loc1=ar.pfs,0,3,1,0
+	mov loc0=rp
+	mov loc2=gp
+	mov out0=r5		// arg
+	ld8 r14 = [r4], 8	// fn.address
+	;;
+	mov b6 = r14
+	ld8 gp = [r4]		// fn.gp
+	;;
+	br.call.sptk.many rp=b6	// fn(arg)
+.ret12:	mov gp=loc2
+	mov rp=loc0
+	mov ar.pfs=loc1
+	/* ... and if it has returned, we are going to userland */
+	cmp.ne pKStk,pUStk=r0,r0
+	br.ret.sptk.many rp
+END(call_payload)
+
 GLOBAL_ENTRY(ia64_ret_from_clone)
 	PT_REGS_UNWIND_INFO(0)
 {	/*
@@ -610,6 +624,7 @@ GLOBAL_ENTRY(ia64_ret_from_clone)
 	br.call.sptk.many rp=ia64_invoke_schedule_tail
 }
 .ret8:
+(pKStk)	br.call.sptk.many rp=call_payload
 	adds r2=TI_FLAGS+IA64_TASK_SIZE,r13
 	;;
 	ld4 r2=[r2]
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index 629a250f7c19..4738ff7bd66a 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -1093,19 +1093,6 @@ GLOBAL_ENTRY(cycle_to_cputime)
 END(cycle_to_cputime)
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
-GLOBAL_ENTRY(start_kernel_thread)
-	.prologue
-	.save rp, r0				// this is the end of the call-chain
-	.body
-	alloc r2 = ar.pfs, 0, 0, 2, 0
-	mov out0 = r9
-	mov out1 = r11;;
-	br.call.sptk.many rp = kernel_thread_helper;;
-	mov out0 = r8
-	br.call.sptk.many rp = sys_exit;;
-1:	br.sptk.few 1b				// not reached
-END(start_kernel_thread)
-
 #ifdef CONFIG_IA64_BRL_EMU
 
 /*
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 6a48775d9363..37686dbfd264 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -401,55 +401,15 @@ copy_thread(unsigned long clone_flags,
 	struct pt_regs *child_ptregs;
 	int retval = 0;
 
-	stack = ((struct switch_stack *) regs) - 1;
-
 	child_ptregs = (struct pt_regs *) ((unsigned long) p + IA64_STK_OFFSET) - 1;
 	child_stack = (struct switch_stack *) child_ptregs - 1;
 
-	/* copy parent's switch_stack & pt_regs to child: */
-	memcpy(child_stack, stack, sizeof(*child_ptregs) + sizeof(*child_stack));
-
 	rbs = (unsigned long) current + IA64_RBS_OFFSET;
 	child_rbs = (unsigned long) p + IA64_RBS_OFFSET;
 
-	if (likely(user_mode(child_ptregs))) {
-		/* copy the parent's register backing store to the child: */
-		rbs_size = stack->ar_bspstore - rbs;
-		memcpy((void *) child_rbs, (void *) rbs, rbs_size);
-		if (clone_flags & CLONE_SETTLS)
-			child_ptregs->r13 = regs->r16;	/* see sys_clone2() in entry.S */
-		if (user_stack_base) {
-			child_ptregs->r12 = user_stack_base + user_stack_size - 16;
-			child_ptregs->ar_bspstore = user_stack_base;
-			child_ptregs->ar_rnat = 0;
-			child_ptregs->loadrs = 0;
-		}
-	} else {
-		/*
-		 * Note: we simply preserve the relative position of
-		 * the stack pointer here.  There is no need to
-		 * allocate a scratch area here, since that will have
-		 * been taken care of by the caller of sys_clone()
-		 * already.
-		 */
-		rbs_size = 0;
-		child_ptregs->r12 = (unsigned long) child_ptregs - 16; /* kernel sp */
-		child_ptregs->r13 = (unsigned long) p;		/* set `current' pointer */
-	}
-	child_stack->ar_bspstore = child_rbs + rbs_size;
-	child_stack->b0 = (unsigned long) &ia64_ret_from_clone;
-
 	/* copy parts of thread_struct: */
 	p->thread.ksp = (unsigned long) child_stack - 16;
 
-	/* stop some PSR bits from being inherited.
-	 * the psr.up/psr.pp bits must be cleared on fork but inherited on execve()
-	 * therefore we must specify them explicitly here and not include them in
-	 * IA64_PSR_BITS_TO_CLEAR.
-	 */
-	child_ptregs->cr_ipsr = ((child_ptregs->cr_ipsr | IA64_PSR_BITS_TO_SET)
-				 & ~(IA64_PSR_BITS_TO_CLEAR | IA64_PSR_PP | IA64_PSR_UP));
-
 	/*
 	 * NOTE: The calling convention considers all floating point
 	 * registers in the high partition (fph) to be scratch.  Since
@@ -471,8 +431,66 @@ copy_thread(unsigned long clone_flags,
 #	define THREAD_FLAGS_TO_SET	0
 	p->thread.flags = ((current->thread.flags & ~THREAD_FLAGS_TO_CLEAR)
 			   | THREAD_FLAGS_TO_SET);
+
 	ia64_drop_fpu(p);	/* don't pick up stale state from a CPU's fph */
 
+	if (unlikely(p->flags & PF_KTHREAD)) {
+		if (unlikely(!user_stack_base)) {
+			/* fork_idle() called us */
+			return 0;
+		}
+		memset(child_stack, 0, sizeof(*child_ptregs) + sizeof(*child_stack));
+		child_stack->r4 = user_stack_base;	/* payload */
+		child_stack->r5 = user_stack_size;	/* argument */
+		/*
+		 * Preserve PSR bits, except for bits 32-34 and 37-45,
+		 * which we can't read.
+		 */
+		child_ptregs->cr_ipsr = ia64_getreg(_IA64_REG_PSR) | IA64_PSR_BN;
+		/* mark as valid, empty frame */
+		child_ptregs->cr_ifs = 1UL << 63;
+		child_stack->ar_fpsr = child_ptregs->ar_fpsr
+			= ia64_getreg(_IA64_REG_AR_FPSR);
+		child_stack->pr = (1 << PRED_KERNEL_STACK);
+		child_stack->ar_bspstore = child_rbs;
+		child_stack->b0 = (unsigned long) &ia64_ret_from_clone;
+
+		/* stop some PSR bits from being inherited.
+		 * the psr.up/psr.pp bits must be cleared on fork but inherited on execve()
+		 * therefore we must specify them explicitly here and not include them in
+		 * IA64_PSR_BITS_TO_CLEAR.
+		 */
+		child_ptregs->cr_ipsr = ((child_ptregs->cr_ipsr | IA64_PSR_BITS_TO_SET)
+				 & ~(IA64_PSR_BITS_TO_CLEAR | IA64_PSR_PP | IA64_PSR_UP));
+
+		return 0;
+	}
+	stack = ((struct switch_stack *) regs) - 1;
+	/* copy parent's switch_stack & pt_regs to child: */
+	memcpy(child_stack, stack, sizeof(*child_ptregs) + sizeof(*child_stack));
+
+	/* copy the parent's register backing store to the child: */
+	rbs_size = stack->ar_bspstore - rbs;
+	memcpy((void *) child_rbs, (void *) rbs, rbs_size);
+	if (clone_flags & CLONE_SETTLS)
+		child_ptregs->r13 = regs->r16;	/* see sys_clone2() in entry.S */
+	if (user_stack_base) {
+		child_ptregs->r12 = user_stack_base + user_stack_size - 16;
+		child_ptregs->ar_bspstore = user_stack_base;
+		child_ptregs->ar_rnat = 0;
+		child_ptregs->loadrs = 0;
+	}
+	child_stack->ar_bspstore = child_rbs + rbs_size;
+	child_stack->b0 = (unsigned long) &ia64_ret_from_clone;
+
+	/* stop some PSR bits from being inherited.
+	 * the psr.up/psr.pp bits must be cleared on fork but inherited on execve()
+	 * therefore we must specify them explicitly here and not include them in
+	 * IA64_PSR_BITS_TO_CLEAR.
+	 */
+	child_ptregs->cr_ipsr = ((child_ptregs->cr_ipsr | IA64_PSR_BITS_TO_SET)
+				 & ~(IA64_PSR_BITS_TO_CLEAR | IA64_PSR_PP | IA64_PSR_UP));
+
 #ifdef CONFIG_PERFMON
 	if (current->thread.pfm_context)
 		pfm_inherit(p, child_ptregs);
@@ -618,37 +636,6 @@ out:
 	return error;
 }
 
-pid_t
-kernel_thread (int (*fn)(void *), void *arg, unsigned long flags)
-{
-	extern void start_kernel_thread (void);
-	unsigned long *helper_fptr = (unsigned long *) &start_kernel_thread;
-	struct {
-		struct switch_stack sw;
-		struct pt_regs pt;
-	} regs;
-
-	memset(&regs, 0, sizeof(regs));
-	regs.pt.cr_iip = helper_fptr[0];	/* set entry point (IP) */
-	regs.pt.r1 = helper_fptr[1];		/* set GP */
-	regs.pt.r9 = (unsigned long) fn;	/* 1st argument */
-	regs.pt.r11 = (unsigned long) arg;	/* 2nd argument */
-	/* Preserve PSR bits, except for bits 32-34 and 37-45, which we can't read.  */
-	regs.pt.cr_ipsr = ia64_getreg(_IA64_REG_PSR) | IA64_PSR_BN;
-	regs.pt.cr_ifs = 1UL << 63;		/* mark as valid, empty frame */
-	regs.sw.ar_fpsr = regs.pt.ar_fpsr = ia64_getreg(_IA64_REG_AR_FPSR);
-	regs.sw.pr = (1 << PRED_KERNEL_STACK);
-	return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs.pt, 0, NULL, NULL);
-}
-EXPORT_SYMBOL(kernel_thread);
-
-/* This gets called from kernel_thread() via ia64_invoke_thread_helper().  */
-int
-kernel_thread_helper (int (*fn)(void *), void *arg)
-{
-	return (*fn)(arg);
-}
-
 /*
  * Flush thread state.  This is called when a thread does an execve().
  */