powerpc: Introduce entry_{32,64}.S, misc_{32,64}.S, systbl.S

The system call table has been consolidated into systbl.S.  We have
separate 32-bit and 64-bit versions of entry.S and misc.S since the
code is mostly sufficiently different to be not worth merging.
There are some common bits that will be extracted in future.

Signed-off-by: Paul Mackerras <paulus@samba.org>

1 files changed, 1002 insertions, 0 deletions

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
new file mode 100644
index 000000000000..094eea6fbd69
--- /dev/null
+++ b/arch/powerpc/kernel/entry_32.S
@@ -0,0 +1,1002 @@
+/*
+ *  PowerPC version
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *  Rewritten by Cort Dougan (cort@fsmlabs.com) for PReP
+ *    Copyright (C) 1996 Cort Dougan <cort@fsmlabs.com>
+ *  Adapted for Power Macintosh by Paul Mackerras.
+ *  Low-level exception handlers and MMU support
+ *  rewritten by Paul Mackerras.
+ *    Copyright (C) 1996 Paul Mackerras.
+ *  MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ *
+ *  This file contains the system call entry code, context switch
+ *  code, and exception/interrupt return code for PowerPC.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/sys.h>
+#include <linux/threads.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+#undef SHOW_SYSCALLS
+#undef SHOW_SYSCALLS_TASK
+
+/*
+ * MSR_KERNEL is > 0x10000 on 4xx/Book-E since it include MSR_CE.
+ */
+#if MSR_KERNEL >= 0x10000
+#define LOAD_MSR_KERNEL(r, x)	lis r,(x)@h; ori r,r,(x)@l
+#else
+#define LOAD_MSR_KERNEL(r, x)	li r,(x)
+#endif
+
+#ifdef CONFIG_BOOKE
+#include "head_booke.h"
+#define TRANSFER_TO_HANDLER_EXC_LEVEL(exc_level)	\
+	mtspr	exc_level##_SPRG,r8;			\
+	BOOKE_LOAD_EXC_LEVEL_STACK(exc_level);		\
+	lwz	r0,GPR10-INT_FRAME_SIZE(r8);		\
+	stw	r0,GPR10(r11);				\
+	lwz	r0,GPR11-INT_FRAME_SIZE(r8);		\
+	stw	r0,GPR11(r11);				\
+	mfspr	r8,exc_level##_SPRG
+
+	.globl	mcheck_transfer_to_handler
+mcheck_transfer_to_handler:
+	TRANSFER_TO_HANDLER_EXC_LEVEL(MCHECK)
+	b	transfer_to_handler_full
+
+	.globl	debug_transfer_to_handler
+debug_transfer_to_handler:
+	TRANSFER_TO_HANDLER_EXC_LEVEL(DEBUG)
+	b	transfer_to_handler_full
+
+	.globl	crit_transfer_to_handler
+crit_transfer_to_handler:
+	TRANSFER_TO_HANDLER_EXC_LEVEL(CRIT)
+	/* fall through */
+#endif
+
+#ifdef CONFIG_40x
+	.globl	crit_transfer_to_handler
+crit_transfer_to_handler:
+	lwz	r0,crit_r10@l(0)
+	stw	r0,GPR10(r11)
+	lwz	r0,crit_r11@l(0)
+	stw	r0,GPR11(r11)
+	/* fall through */
+#endif
+
+/*
+ * This code finishes saving the registers to the exception frame
+ * and jumps to the appropriate handler for the exception, turning
+ * on address translation.
+ * Note that we rely on the caller having set cr0.eq iff the exception
+ * occurred in kernel mode (i.e. MSR:PR = 0).
+ */
+	.globl	transfer_to_handler_full
+transfer_to_handler_full:
+	SAVE_NVGPRS(r11)
+	/* fall through */
+
+	.globl	transfer_to_handler
+transfer_to_handler:
+	stw	r2,GPR2(r11)
+	stw	r12,_NIP(r11)
+	stw	r9,_MSR(r11)
+	andi.	r2,r9,MSR_PR
+	mfctr	r12
+	mfspr	r2,SPRN_XER
+	stw	r12,_CTR(r11)
+	stw	r2,_XER(r11)
+	mfspr	r12,SPRN_SPRG3
+	addi	r2,r12,-THREAD
+	tovirt(r2,r2)			/* set r2 to current */
+	beq	2f			/* if from user, fix up THREAD.regs */
+	addi	r11,r1,STACK_FRAME_OVERHEAD
+	stw	r11,PT_REGS(r12)
+#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+	/* Check to see if the dbcr0 register is set up to debug.  Use the
+	   single-step bit to do this. */
+	lwz	r12,THREAD_DBCR0(r12)
+	andis.	r12,r12,DBCR0_IC@h
+	beq+	3f
+	/* From user and task is ptraced - load up global dbcr0 */
+	li	r12,-1			/* clear all pending debug events */
+	mtspr	SPRN_DBSR,r12
+	lis	r11,global_dbcr0@ha
+	tophys(r11,r11)
+	addi	r11,r11,global_dbcr0@l
+	lwz	r12,0(r11)
+	mtspr	SPRN_DBCR0,r12
+	lwz	r12,4(r11)
+	addi	r12,r12,-1
+	stw	r12,4(r11)
+#endif
+	b	3f
+2:	/* if from kernel, check interrupted DOZE/NAP mode and
+         * check for stack overflow
+         */
+#ifdef CONFIG_6xx
+	mfspr	r11,SPRN_HID0
+	mtcr	r11
+BEGIN_FTR_SECTION
+	bt-	8,power_save_6xx_restore	/* Check DOZE */
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
+BEGIN_FTR_SECTION
+	bt-	9,power_save_6xx_restore	/* Check NAP */
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+#endif /* CONFIG_6xx */
+	.globl transfer_to_handler_cont
+transfer_to_handler_cont:
+	lwz	r11,THREAD_INFO-THREAD(r12)
+	cmplw	r1,r11			/* if r1 <= current->thread_info */
+	ble-	stack_ovf		/* then the kernel stack overflowed */
+3:
+	mflr	r9
+	lwz	r11,0(r9)		/* virtual address of handler */
+	lwz	r9,4(r9)		/* where to go when done */
+	FIX_SRR1(r10,r12)
+	mtspr	SPRN_SRR0,r11
+	mtspr	SPRN_SRR1,r10
+	mtlr	r9
+	SYNC
+	RFI				/* jump to handler, enable MMU */
+
+/*
+ * On kernel stack overflow, load up an initial stack pointer
+ * and call StackOverflow(regs), which should not return.
+ */
+stack_ovf:
+	/* sometimes we use a statically-allocated stack, which is OK. */
+	lis	r11,_end@h
+	ori	r11,r11,_end@l
+	cmplw	r1,r11
+	ble	3b			/* r1 <= &_end is OK */
+	SAVE_NVGPRS(r11)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	lis	r1,init_thread_union@ha
+	addi	r1,r1,init_thread_union@l
+	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+	lis	r9,StackOverflow@ha
+	addi	r9,r9,StackOverflow@l
+	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+	FIX_SRR1(r10,r12)
+	mtspr	SPRN_SRR0,r9
+	mtspr	SPRN_SRR1,r10
+	SYNC
+	RFI
+
+/*
+ * Handle a system call.
+ */
+	.stabs	"arch/powerpc/kernel/",N_SO,0,0,0f
+	.stabs	"entry_32.S",N_SO,0,0,0f
+0:
+
+_GLOBAL(DoSyscall)
+	stw	r0,THREAD+LAST_SYSCALL(r2)
+	stw	r3,ORIG_GPR3(r1)
+	li	r12,0
+	stw	r12,RESULT(r1)
+	lwz	r11,_CCR(r1)	/* Clear SO bit in CR */
+	rlwinm	r11,r11,0,4,2
+	stw	r11,_CCR(r1)
+#ifdef SHOW_SYSCALLS
+	bl	do_show_syscall
+#endif /* SHOW_SYSCALLS */
+	rlwinm	r10,r1,0,0,18	/* current_thread_info() */
+	lwz	r11,TI_LOCAL_FLAGS(r10)
+	rlwinm	r11,r11,0,~_TIFL_FORCE_NOERROR
+	stw	r11,TI_LOCAL_FLAGS(r10)
+	lwz	r11,TI_FLAGS(r10)
+	andi.	r11,r11,_TIF_SYSCALL_T_OR_A
+	bne-	syscall_dotrace
+syscall_dotrace_cont:
+	cmplwi	0,r0,NR_syscalls
+	lis	r10,sys_call_table@h
+	ori	r10,r10,sys_call_table@l
+	slwi	r0,r0,2
+	bge-	66f
+	lwzx	r10,r10,r0	/* Fetch system call handler [ptr] */
+	mtlr	r10
+	addi	r9,r1,STACK_FRAME_OVERHEAD
+	PPC440EP_ERR42
+	blrl			/* Call handler */
+	.globl	ret_from_syscall
+ret_from_syscall:
+#ifdef SHOW_SYSCALLS
+	bl	do_show_syscall_exit
+#endif
+	mr	r6,r3
+	li	r11,-_LAST_ERRNO
+	cmplw	0,r3,r11
+	rlwinm	r12,r1,0,0,18	/* current_thread_info() */
+	blt+	30f
+	lwz	r11,TI_LOCAL_FLAGS(r12)
+	andi.	r11,r11,_TIFL_FORCE_NOERROR
+	bne	30f
+	neg	r3,r3
+	lwz	r10,_CCR(r1)	/* Set SO bit in CR */
+	oris	r10,r10,0x1000
+	stw	r10,_CCR(r1)
+
+	/* disable interrupts so current_thread_info()->flags can't change */
+30:	LOAD_MSR_KERNEL(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
+	SYNC
+	MTMSRD(r10)
+	lwz	r9,TI_FLAGS(r12)
+	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SIGPENDING|_TIF_NEED_RESCHED)
+	bne-	syscall_exit_work
+syscall_exit_cont:
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+	/* If the process has its own DBCR0 value, load it up.  The single
+	   step bit tells us that dbcr0 should be loaded. */
+	lwz	r0,THREAD+THREAD_DBCR0(r2)
+	andis.	r10,r0,DBCR0_IC@h
+	bnel-	load_dbcr0
+#endif
+	stwcx.	r0,0,r1			/* to clear the reservation */
+	lwz	r4,_LINK(r1)
+	lwz	r5,_CCR(r1)
+	mtlr	r4
+	mtcr	r5
+	lwz	r7,_NIP(r1)
+	lwz	r8,_MSR(r1)
+	FIX_SRR1(r8, r0)
+	lwz	r2,GPR2(r1)
+	lwz	r1,GPR1(r1)
+	mtspr	SPRN_SRR0,r7
+	mtspr	SPRN_SRR1,r8
+	SYNC
+	RFI
+
+66:	li	r3,-ENOSYS
+	b	ret_from_syscall
+
+	.globl	ret_from_fork
+ret_from_fork:
+	REST_NVGPRS(r1)
+	bl	schedule_tail
+	li	r3,0
+	b	ret_from_syscall
+
+/* Traced system call support */
+syscall_dotrace:
+	SAVE_NVGPRS(r1)
+	li	r0,0xc00
+	stw	r0,TRAP(r1)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	do_syscall_trace_enter
+	lwz	r0,GPR0(r1)	/* Restore original registers */
+	lwz	r3,GPR3(r1)
+	lwz	r4,GPR4(r1)
+	lwz	r5,GPR5(r1)
+	lwz	r6,GPR6(r1)
+	lwz	r7,GPR7(r1)
+	lwz	r8,GPR8(r1)
+	REST_NVGPRS(r1)
+	b	syscall_dotrace_cont
+
+syscall_exit_work:
+	stw	r6,RESULT(r1)	/* Save result */
+	stw	r3,GPR3(r1)	/* Update return value */
+	andi.	r0,r9,_TIF_SYSCALL_T_OR_A
+	beq	5f
+	ori	r10,r10,MSR_EE
+	SYNC
+	MTMSRD(r10)		/* re-enable interrupts */
+	lwz	r4,TRAP(r1)
+	andi.	r4,r4,1
+	beq	4f
+	SAVE_NVGPRS(r1)
+	li	r4,0xc00
+	stw	r4,TRAP(r1)
+4:
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	do_syscall_trace_leave
+	REST_NVGPRS(r1)
+2:
+	lwz	r3,GPR3(r1)
+	LOAD_MSR_KERNEL(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
+	SYNC
+	MTMSRD(r10)		/* disable interrupts again */
+	rlwinm	r12,r1,0,0,18	/* current_thread_info() */
+	lwz	r9,TI_FLAGS(r12)
+5:
+	andi.	r0,r9,_TIF_NEED_RESCHED
+	bne	1f
+	lwz	r5,_MSR(r1)
+	andi.	r5,r5,MSR_PR
+	beq	syscall_exit_cont
+	andi.	r0,r9,_TIF_SIGPENDING
+	beq	syscall_exit_cont
+	b	do_user_signal
+1:
+	ori	r10,r10,MSR_EE
+	SYNC
+	MTMSRD(r10)		/* re-enable interrupts */
+	bl	schedule
+	b	2b
+
+#ifdef SHOW_SYSCALLS
+do_show_syscall:
+#ifdef SHOW_SYSCALLS_TASK
+	lis	r11,show_syscalls_task@ha
+	lwz	r11,show_syscalls_task@l(r11)
+	cmp	0,r2,r11
+	bnelr
+#endif
+	stw	r31,GPR31(r1)
+	mflr	r31
+	lis	r3,7f@ha
+	addi	r3,r3,7f@l
+	lwz	r4,GPR0(r1)
+	lwz	r5,GPR3(r1)
+	lwz	r6,GPR4(r1)
+	lwz	r7,GPR5(r1)
+	lwz	r8,GPR6(r1)
+	lwz	r9,GPR7(r1)
+	bl	printk
+	lis	r3,77f@ha
+	addi	r3,r3,77f@l
+	lwz	r4,GPR8(r1)
+	mr	r5,r2
+	bl	printk
+	lwz	r0,GPR0(r1)
+	lwz	r3,GPR3(r1)
+	lwz	r4,GPR4(r1)
+	lwz	r5,GPR5(r1)
+	lwz	r6,GPR6(r1)
+	lwz	r7,GPR7(r1)
+	lwz	r8,GPR8(r1)
+	mtlr	r31
+	lwz	r31,GPR31(r1)
+	blr
+
+do_show_syscall_exit:
+#ifdef SHOW_SYSCALLS_TASK
+	lis	r11,show_syscalls_task@ha
+	lwz	r11,show_syscalls_task@l(r11)
+	cmp	0,r2,r11
+	bnelr
+#endif
+	stw	r31,GPR31(r1)
+	mflr	r31
+	stw	r3,RESULT(r1)	/* Save result */
+	mr	r4,r3
+	lis	r3,79f@ha
+	addi	r3,r3,79f@l
+	bl	printk
+	lwz	r3,RESULT(r1)
+	mtlr	r31
+	lwz	r31,GPR31(r1)
+	blr
+
+7:	.string	"syscall %d(%x, %x, %x, %x, %x, "
+77:	.string	"%x), current=%p\n"
+79:	.string	" -> %x\n"
+	.align	2,0
+
+#ifdef SHOW_SYSCALLS_TASK
+	.data
+	.globl	show_syscalls_task
+show_syscalls_task:
+	.long	-1
+	.text
+#endif
+#endif /* SHOW_SYSCALLS */
+
+/*
+ * The sigsuspend and rt_sigsuspend system calls can call do_signal
+ * and thus put the process into the stopped state where we might
+ * want to examine its user state with ptrace.  Therefore we need
+ * to save all the nonvolatile registers (r13 - r31) before calling
+ * the C code.
+ */
+	.globl	ppc_sigsuspend
+ppc_sigsuspend:
+	SAVE_NVGPRS(r1)
+	lwz	r0,TRAP(r1)
+	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
+	stw	r0,TRAP(r1)		/* register set saved */
+	b	sys_sigsuspend
+
+	.globl	ppc_rt_sigsuspend
+ppc_rt_sigsuspend:
+	SAVE_NVGPRS(r1)
+	lwz	r0,TRAP(r1)
+	rlwinm	r0,r0,0,0,30
+	stw	r0,TRAP(r1)
+	b	sys_rt_sigsuspend
+
+	.globl	ppc_fork
+ppc_fork:
+	SAVE_NVGPRS(r1)
+	lwz	r0,TRAP(r1)
+	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
+	stw	r0,TRAP(r1)		/* register set saved */
+	b	sys_fork
+
+	.globl	ppc_vfork
+ppc_vfork:
+	SAVE_NVGPRS(r1)
+	lwz	r0,TRAP(r1)
+	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
+	stw	r0,TRAP(r1)		/* register set saved */
+	b	sys_vfork
+
+	.globl	ppc_clone
+ppc_clone:
+	SAVE_NVGPRS(r1)
+	lwz	r0,TRAP(r1)
+	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
+	stw	r0,TRAP(r1)		/* register set saved */
+	b	sys_clone
+
+	.globl	ppc_swapcontext
+ppc_swapcontext:
+	SAVE_NVGPRS(r1)
+	lwz	r0,TRAP(r1)
+	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
+	stw	r0,TRAP(r1)		/* register set saved */
+	b	sys_swapcontext
+
+/*
+ * Top-level page fault handling.
+ * This is in assembler because if do_page_fault tells us that
+ * it is a bad kernel page fault, we want to save the non-volatile
+ * registers before calling bad_page_fault.
+ */
+	.globl	handle_page_fault
+handle_page_fault:
+	stw	r4,_DAR(r1)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	do_page_fault
+	cmpwi	r3,0
+	beq+	ret_from_except
+	SAVE_NVGPRS(r1)
+	lwz	r0,TRAP(r1)
+	clrrwi	r0,r0,1
+	stw	r0,TRAP(r1)
+	mr	r5,r3
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	lwz	r4,_DAR(r1)
+	bl	bad_page_fault
+	b	ret_from_except_full
+
+/*
+ * This routine switches between two different tasks.  The process
+ * state of one is saved on its kernel stack.  Then the state
+ * of the other is restored from its kernel stack.  The memory
+ * management hardware is updated to the second process's state.
+ * Finally, we can return to the second process.
+ * On entry, r3 points to the THREAD for the current task, r4
+ * points to the THREAD for the new task.
+ *
+ * This routine is always called with interrupts disabled.
+ *
+ * Note: there are two ways to get to the "going out" portion
+ * of this code; either by coming in via the entry (_switch)
+ * or via "fork" which must set up an environment equivalent
+ * to the "_switch" path.  If you change this , you'll have to
+ * change the fork code also.
+ *
+ * The code which creates the new task context is in 'copy_thread'
+ * in arch/ppc/kernel/process.c
+ */
+_GLOBAL(_switch)
+	stwu	r1,-INT_FRAME_SIZE(r1)
+	mflr	r0
+	stw	r0,INT_FRAME_SIZE+4(r1)
+	/* r3-r12 are caller saved -- Cort */
+	SAVE_NVGPRS(r1)
+	stw	r0,_NIP(r1)	/* Return to switch caller */
+	mfmsr	r11
+	li	r0,MSR_FP	/* Disable floating-point */
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+	oris	r0,r0,MSR_VEC@h	/* Disable altivec */
+	mfspr	r12,SPRN_VRSAVE	/* save vrsave register value */
+	stw	r12,THREAD+THREAD_VRSAVE(r2)
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+	oris	r0,r0,MSR_SPE@h	 /* Disable SPE */
+	mfspr	r12,SPRN_SPEFSCR /* save spefscr register value */
+	stw	r12,THREAD+THREAD_SPEFSCR(r2)
+#endif /* CONFIG_SPE */
+	and.	r0,r0,r11	/* FP or altivec or SPE enabled? */
+	beq+	1f
+	andc	r11,r11,r0
+	MTMSRD(r11)
+	isync
+1:	stw	r11,_MSR(r1)
+	mfcr	r10
+	stw	r10,_CCR(r1)
+	stw	r1,KSP(r3)	/* Set old stack pointer */
+
+#ifdef CONFIG_SMP
+	/* We need a sync somewhere here to make sure that if the
+	 * previous task gets rescheduled on another CPU, it sees all
+	 * stores it has performed on this one.
+	 */
+	sync
+#endif /* CONFIG_SMP */
+
+	tophys(r0,r4)
+	CLR_TOP32(r0)
+	mtspr	SPRN_SPRG3,r0	/* Update current THREAD phys addr */
+	lwz	r1,KSP(r4)	/* Load new stack pointer */
+
+	/* save the old current 'last' for return value */
+	mr	r3,r2
+	addi	r2,r4,-THREAD	/* Update current */
+
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+	lwz	r0,THREAD+THREAD_VRSAVE(r2)
+	mtspr	SPRN_VRSAVE,r0		/* if G4, restore VRSAVE reg */
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+	lwz	r0,THREAD+THREAD_SPEFSCR(r2)
+	mtspr	SPRN_SPEFSCR,r0		/* restore SPEFSCR reg */
+#endif /* CONFIG_SPE */
+
+	lwz	r0,_CCR(r1)
+	mtcrf	0xFF,r0
+	/* r3-r12 are destroyed -- Cort */
+	REST_NVGPRS(r1)
+
+	lwz	r4,_NIP(r1)	/* Return to _switch caller in new task */
+	mtlr	r4
+	addi	r1,r1,INT_FRAME_SIZE
+	blr
+
+	.globl	fast_exception_return
+fast_exception_return:
+#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
+	andi.	r10,r9,MSR_RI		/* check for recoverable interrupt */
+	beq	1f			/* if not, we've got problems */
+#endif
+
+2:	REST_4GPRS(3, r11)
+	lwz	r10,_CCR(r11)
+	REST_GPR(1, r11)
+	mtcr	r10
+	lwz	r10,_LINK(r11)
+	mtlr	r10
+	REST_GPR(10, r11)
+	mtspr	SPRN_SRR1,r9
+	mtspr	SPRN_SRR0,r12
+	REST_GPR(9, r11)
+	REST_GPR(12, r11)
+	lwz	r11,GPR11(r11)
+	SYNC
+	RFI
+
+#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
+/* check if the exception happened in a restartable section */
+1:	lis	r3,exc_exit_restart_end@ha
+	addi	r3,r3,exc_exit_restart_end@l
+	cmplw	r12,r3
+	bge	3f
+	lis	r4,exc_exit_restart@ha
+	addi	r4,r4,exc_exit_restart@l
+	cmplw	r12,r4
+	blt	3f
+	lis	r3,fee_restarts@ha
+	tophys(r3,r3)
+	lwz	r5,fee_restarts@l(r3)
+	addi	r5,r5,1
+	stw	r5,fee_restarts@l(r3)
+	mr	r12,r4		/* restart at exc_exit_restart */
+	b	2b
+
+	.comm	fee_restarts,4
+
+/* aargh, a nonrecoverable interrupt, panic */
+/* aargh, we don't know which trap this is */
+/* but the 601 doesn't implement the RI bit, so assume it's OK */
+3:
+BEGIN_FTR_SECTION
+	b	2b
+END_FTR_SECTION_IFSET(CPU_FTR_601)
+	li	r10,-1
+	stw	r10,TRAP(r11)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	lis	r10,MSR_KERNEL@h
+	ori	r10,r10,MSR_KERNEL@l
+	bl	transfer_to_handler_full
+	.long	nonrecoverable_exception
+	.long	ret_from_except
+#endif
+
+	.globl	sigreturn_exit
+sigreturn_exit:
+	subi	r1,r3,STACK_FRAME_OVERHEAD
+	rlwinm	r12,r1,0,0,18	/* current_thread_info() */
+	lwz	r9,TI_FLAGS(r12)
+	andi.	r0,r9,_TIF_SYSCALL_T_OR_A
+	bnel-	do_syscall_trace_leave
+	/* fall through */
+
+	.globl	ret_from_except_full
+ret_from_except_full:
+	REST_NVGPRS(r1)
+	/* fall through */
+
+	.globl	ret_from_except
+ret_from_except:
+	/* Hard-disable interrupts so that current_thread_info()->flags
+	 * can't change between when we test it and when we return
+	 * from the interrupt. */
+	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+	SYNC			/* Some chip revs have problems here... */
+	MTMSRD(r10)		/* disable interrupts */
+
+	lwz	r3,_MSR(r1)	/* Returning to user mode? */
+	andi.	r0,r3,MSR_PR
+	beq	resume_kernel
+
+user_exc_return:		/* r10 contains MSR_KERNEL here */
+	/* Check current_thread_info()->flags */
+	rlwinm	r9,r1,0,0,18
+	lwz	r9,TI_FLAGS(r9)
+	andi.	r0,r9,(_TIF_SIGPENDING|_TIF_NEED_RESCHED)
+	bne	do_work
+
+restore_user:
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+	/* Check whether this process has its own DBCR0 value.  The single
+	   step bit tells us that dbcr0 should be loaded. */
+	lwz	r0,THREAD+THREAD_DBCR0(r2)
+	andis.	r10,r0,DBCR0_IC@h
+	bnel-	load_dbcr0
+#endif
+
+#ifdef CONFIG_PREEMPT
+	b	restore
+
+/* N.B. the only way to get here is from the beq following ret_from_except. */
+resume_kernel:
+	/* check current_thread_info->preempt_count */
+	rlwinm	r9,r1,0,0,18
+	lwz	r0,TI_PREEMPT(r9)
+	cmpwi	0,r0,0		/* if non-zero, just restore regs and return */
+	bne	restore
+	lwz	r0,TI_FLAGS(r9)
+	andi.	r0,r0,_TIF_NEED_RESCHED
+	beq+	restore
+	andi.	r0,r3,MSR_EE	/* interrupts off? */
+	beq	restore		/* don't schedule if so */
+1:	bl	preempt_schedule_irq
+	rlwinm	r9,r1,0,0,18
+	lwz	r3,TI_FLAGS(r9)
+	andi.	r0,r3,_TIF_NEED_RESCHED
+	bne-	1b
+#else
+resume_kernel:
+#endif /* CONFIG_PREEMPT */
+
+	/* interrupts are hard-disabled at this point */
+restore:
+	lwz	r0,GPR0(r1)
+	lwz	r2,GPR2(r1)
+	REST_4GPRS(3, r1)
+	REST_2GPRS(7, r1)
+
+	lwz	r10,_XER(r1)
+	lwz	r11,_CTR(r1)
+	mtspr	SPRN_XER,r10
+	mtctr	r11
+
+	PPC405_ERR77(0,r1)
+	stwcx.	r0,0,r1			/* to clear the reservation */
+
+#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
+	lwz	r9,_MSR(r1)
+	andi.	r10,r9,MSR_RI		/* check if this exception occurred */
+	beql	nonrecoverable		/* at a bad place (MSR:RI = 0) */
+
+	lwz	r10,_CCR(r1)
+	lwz	r11,_LINK(r1)
+	mtcrf	0xFF,r10
+	mtlr	r11
+
+	/*
+	 * Once we put values in SRR0 and SRR1, we are in a state
+	 * where exceptions are not recoverable, since taking an
+	 * exception will trash SRR0 and SRR1.  Therefore we clear the
+	 * MSR:RI bit to indicate this.  If we do take an exception,
+	 * we can't return to the point of the exception but we
+	 * can restart the exception exit path at the label
+	 * exc_exit_restart below.  -- paulus
+	 */
+	LOAD_MSR_KERNEL(r10,MSR_KERNEL & ~MSR_RI)
+	SYNC
+	MTMSRD(r10)		/* clear the RI bit */
+	.globl exc_exit_restart
+exc_exit_restart:
+	lwz	r9,_MSR(r1)
+	lwz	r12,_NIP(r1)
+	FIX_SRR1(r9,r10)
+	mtspr	SPRN_SRR0,r12
+	mtspr	SPRN_SRR1,r9
+	REST_4GPRS(9, r1)
+	lwz	r1,GPR1(r1)
+	.globl exc_exit_restart_end
+exc_exit_restart_end:
+	SYNC
+	RFI
+
+#else /* !(CONFIG_4xx || CONFIG_BOOKE) */
+	/*
+	 * This is a bit different on 4xx/Book-E because it doesn't have
+	 * the RI bit in the MSR.
+	 * The TLB miss handler checks if we have interrupted
+	 * the exception exit path and restarts it if so
+	 * (well maybe one day it will... :).
+	 */
+	lwz	r11,_LINK(r1)
+	mtlr	r11
+	lwz	r10,_CCR(r1)
+	mtcrf	0xff,r10
+	REST_2GPRS(9, r1)
+	.globl exc_exit_restart
+exc_exit_restart:
+	lwz	r11,_NIP(r1)
+	lwz	r12,_MSR(r1)
+exc_exit_start:
+	mtspr	SPRN_SRR0,r11
+	mtspr	SPRN_SRR1,r12
+	REST_2GPRS(11, r1)
+	lwz	r1,GPR1(r1)
+	.globl exc_exit_restart_end
+exc_exit_restart_end:
+	PPC405_ERR77_SYNC
+	rfi
+	b	.			/* prevent prefetch past rfi */
+
+/*
+ * Returning from a critical interrupt in user mode doesn't need
+ * to be any different from a normal exception.  For a critical
+ * interrupt in the kernel, we just return (without checking for
+ * preemption) since the interrupt may have happened at some crucial
+ * place (e.g. inside the TLB miss handler), and because we will be
+ * running with r1 pointing into critical_stack, not the current
+ * process's kernel stack (and therefore current_thread_info() will
+ * give the wrong answer).
+ * We have to restore various SPRs that may have been in use at the
+ * time of the critical interrupt.
+ *
+ */
+#ifdef CONFIG_40x
+#define PPC_40x_TURN_OFF_MSR_DR						    \
+	/* avoid any possible TLB misses here by turning off MSR.DR, we	    \
+	 * assume the instructions here are mapped by a pinned TLB entry */ \
+	li	r10,MSR_IR;						    \
+	mtmsr	r10;							    \
+	isync;								    \
+	tophys(r1, r1);
+#else
+#define PPC_40x_TURN_OFF_MSR_DR
+#endif
+
+#define RET_FROM_EXC_LEVEL(exc_lvl_srr0, exc_lvl_srr1, exc_lvl_rfi)	\
+	REST_NVGPRS(r1);						\
+	lwz	r3,_MSR(r1);						\
+	andi.	r3,r3,MSR_PR;						\
+	LOAD_MSR_KERNEL(r10,MSR_KERNEL);				\
+	bne	user_exc_return;					\
+	lwz	r0,GPR0(r1);						\
+	lwz	r2,GPR2(r1);						\
+	REST_4GPRS(3, r1);						\
+	REST_2GPRS(7, r1);						\
+	lwz	r10,_XER(r1);						\
+	lwz	r11,_CTR(r1);						\
+	mtspr	SPRN_XER,r10;						\
+	mtctr	r11;							\
+	PPC405_ERR77(0,r1);						\
+	stwcx.	r0,0,r1;		/* to clear the reservation */	\
+	lwz	r11,_LINK(r1);						\
+	mtlr	r11;							\
+	lwz	r10,_CCR(r1);						\
+	mtcrf	0xff,r10;						\
+	PPC_40x_TURN_OFF_MSR_DR;					\
+	lwz	r9,_DEAR(r1);						\
+	lwz	r10,_ESR(r1);						\
+	mtspr	SPRN_DEAR,r9;						\
+	mtspr	SPRN_ESR,r10;						\
+	lwz	r11,_NIP(r1);						\
+	lwz	r12,_MSR(r1);						\
+	mtspr	exc_lvl_srr0,r11;					\
+	mtspr	exc_lvl_srr1,r12;					\
+	lwz	r9,GPR9(r1);						\
+	lwz	r12,GPR12(r1);						\
+	lwz	r10,GPR10(r1);						\
+	lwz	r11,GPR11(r1);						\
+	lwz	r1,GPR1(r1);						\
+	PPC405_ERR77_SYNC;						\
+	exc_lvl_rfi;							\
+	b	.;		/* prevent prefetch past exc_lvl_rfi */
+
+	.globl	ret_from_crit_exc
+ret_from_crit_exc:
+	RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, RFCI)
+
+#ifdef CONFIG_BOOKE
+	.globl	ret_from_debug_exc
+ret_from_debug_exc:
+	RET_FROM_EXC_LEVEL(SPRN_DSRR0, SPRN_DSRR1, RFDI)
+
+	.globl	ret_from_mcheck_exc
+ret_from_mcheck_exc:
+	RET_FROM_EXC_LEVEL(SPRN_MCSRR0, SPRN_MCSRR1, RFMCI)
+#endif /* CONFIG_BOOKE */
+
+/*
+ * Load the DBCR0 value for a task that is being ptraced,
+ * having first saved away the global DBCR0.  Note that r0
+ * has the dbcr0 value to set upon entry to this.
+ */
+load_dbcr0:
+	mfmsr	r10		/* first disable debug exceptions */
+	rlwinm	r10,r10,0,~MSR_DE
+	mtmsr	r10
+	isync
+	mfspr	r10,SPRN_DBCR0
+	lis	r11,global_dbcr0@ha
+	addi	r11,r11,global_dbcr0@l
+	stw	r10,0(r11)
+	mtspr	SPRN_DBCR0,r0
+	lwz	r10,4(r11)
+	addi	r10,r10,1
+	stw	r10,4(r11)
+	li	r11,-1
+	mtspr	SPRN_DBSR,r11	/* clear all pending debug events */
+	blr
+
+	.comm	global_dbcr0,8
+#endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
+
+do_work:			/* r10 contains MSR_KERNEL here */
+	andi.	r0,r9,_TIF_NEED_RESCHED
+	beq	do_user_signal
+
+do_resched:			/* r10 contains MSR_KERNEL here */
+	ori	r10,r10,MSR_EE
+	SYNC
+	MTMSRD(r10)		/* hard-enable interrupts */
+	bl	schedule
+recheck:
+	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+	SYNC
+	MTMSRD(r10)		/* disable interrupts */
+	rlwinm	r9,r1,0,0,18
+	lwz	r9,TI_FLAGS(r9)
+	andi.	r0,r9,_TIF_NEED_RESCHED
+	bne-	do_resched
+	andi.	r0,r9,_TIF_SIGPENDING
+	beq	restore_user
+do_user_signal:			/* r10 contains MSR_KERNEL here */
+	ori	r10,r10,MSR_EE
+	SYNC
+	MTMSRD(r10)		/* hard-enable interrupts */
+	/* save r13-r31 in the exception frame, if not already done */
+	lwz	r3,TRAP(r1)
+	andi.	r0,r3,1
+	beq	2f
+	SAVE_NVGPRS(r1)
+	rlwinm	r3,r3,0,0,30
+	stw	r3,TRAP(r1)
+2:	li	r3,0
+	addi	r4,r1,STACK_FRAME_OVERHEAD
+	bl	do_signal
+	REST_NVGPRS(r1)
+	b	recheck
+
+/*
+ * We come here when we are at the end of handling an exception
+ * that occurred at a place where taking an exception will lose
+ * state information, such as the contents of SRR0 and SRR1.
+ */
+nonrecoverable:
+	lis	r10,exc_exit_restart_end@ha
+	addi	r10,r10,exc_exit_restart_end@l
+	cmplw	r12,r10
+	bge	3f
+	lis	r11,exc_exit_restart@ha
+	addi	r11,r11,exc_exit_restart@l
+	cmplw	r12,r11
+	blt	3f
+	lis	r10,ee_restarts@ha
+	lwz	r12,ee_restarts@l(r10)
+	addi	r12,r12,1
+	stw	r12,ee_restarts@l(r10)
+	mr	r12,r11		/* restart at exc_exit_restart */
+	blr
+3:	/* OK, we can't recover, kill this process */
+	/* but the 601 doesn't implement the RI bit, so assume it's OK */
+BEGIN_FTR_SECTION
+	blr
+END_FTR_SECTION_IFSET(CPU_FTR_601)
+	lwz	r3,TRAP(r1)
+	andi.	r0,r3,1
+	beq	4f
+	SAVE_NVGPRS(r1)
+	rlwinm	r3,r3,0,0,30
+	stw	r3,TRAP(r1)
+4:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	nonrecoverable_exception
+	/* shouldn't return */
+	b	4b
+
+	.comm	ee_restarts,4
+
+/*
+ * PROM code for specific machines follows.  Put it
+ * here so it's easy to add arch-specific sections later.
+ * -- Cort
+ */
+#ifdef CONFIG_PPC_OF
+/*
+ * On CHRP, the Run-Time Abstraction Services (RTAS) have to be
+ * called with the MMU off.
+ */
+_GLOBAL(enter_rtas)
+	stwu	r1,-INT_FRAME_SIZE(r1)
+	mflr	r0
+	stw	r0,INT_FRAME_SIZE+4(r1)
+	lis	r4,rtas_data@ha
+	lwz	r4,rtas_data@l(r4)
+	lis	r6,1f@ha	/* physical return address for rtas */
+	addi	r6,r6,1f@l
+	tophys(r6,r6)
+	tophys(r7,r1)
+	lis	r8,rtas_entry@ha
+	lwz	r8,rtas_entry@l(r8)
+	mfmsr	r9
+	stw	r9,8(r1)
+	LOAD_MSR_KERNEL(r0,MSR_KERNEL)
+	SYNC			/* disable interrupts so SRR0/1 */
+	MTMSRD(r0)		/* don't get trashed */
+	li	r9,MSR_KERNEL & ~(MSR_IR|MSR_DR)
+	mtlr	r6
+	CLR_TOP32(r7)
+	mtspr	SPRN_SPRG2,r7
+	mtspr	SPRN_SRR0,r8
+	mtspr	SPRN_SRR1,r9
+	RFI
+1:	tophys(r9,r1)
+	lwz	r8,INT_FRAME_SIZE+4(r9)	/* get return address */
+	lwz	r9,8(r9)	/* original msr value */
+	FIX_SRR1(r9,r0)
+	addi	r1,r1,INT_FRAME_SIZE
+	li	r0,0
+	mtspr	SPRN_SPRG2,r0
+	mtspr	SPRN_SRR0,r8
+	mtspr	SPRN_SRR1,r9
+	RFI			/* return to caller */
+
+	.globl	machine_check_in_rtas
+machine_check_in_rtas:
+	twi	31,0,0
+	/* XXX load up BATs and panic */
+
+#endif /* CONFIG_PPC_OF */