arch/powerpc/kernel/entry_64.S

/*
 *  PowerPC version 
 *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
 *  Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
 *    Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
 *  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/errno.h>
#include <asm/unistd.h>
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/thread_info.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/cputable.h>
#include <asm/firmware.h>
#include <asm/bug.h>
#include <asm/ptrace.h>
#include <asm/irqflags.h>
#include <asm/ftrace.h>
#include <asm/hw_irq.h>

/*
 * System calls.
 */
	.section	".toc","aw"
.SYS_CALL_TABLE:
	.tc .sys_call_table[TC],.sys_call_table

/* This value is used to mark exception frames on the stack. */
exception_marker:
	.tc	ID_EXC_MARKER[TC],STACK_FRAME_REGS_MARKER

	.section	".text"
	.align 7

#undef SHOW_SYSCALLS

	.globl system_call_common
system_call_common:
	andi.	r10,r12,MSR_PR
	mr	r10,r1
	addi	r1,r1,-INT_FRAME_SIZE
	beq-	1f
	ld	r1,PACAKSAVE(r13)
1:	std	r10,0(r1)
	std	r11,_NIP(r1)
	std	r12,_MSR(r1)
	std	r0,GPR0(r1)
	std	r10,GPR1(r1)
	ACCOUNT_CPU_USER_ENTRY(r10, r11)
	std	r2,GPR2(r1)
	std	r3,GPR3(r1)
	mfcr	r2
	std	r4,GPR4(r1)
	std	r5,GPR5(r1)
	std	r6,GPR6(r1)
	std	r7,GPR7(r1)
	std	r8,GPR8(r1)
	li	r11,0
	std	r11,GPR9(r1)
	std	r11,GPR10(r1)
	std	r11,GPR11(r1)
	std	r11,GPR12(r1)
	std	r11,_XER(r1)
	std	r11,_CTR(r1)
	std	r9,GPR13(r1)
	mflr	r10
	/*
	 * This clears CR0.SO (bit 28), which is the error indication on
	 * return from this system call.
	 */
	rldimi	r2,r11,28,(63-28)
	li	r11,0xc01
	std	r10,_LINK(r1)
	std	r11,_TRAP(r1)
	std	r3,ORIG_GPR3(r1)
	std	r2,_CCR(r1)
	ld	r2,PACATOC(r13)
	addi	r9,r1,STACK_FRAME_OVERHEAD
	ld	r11,exception_marker@toc(r2)
	std	r11,-16(r9)		/* "regshere" marker */
#if defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR)
BEGIN_FW_FTR_SECTION
	beq	33f
	/* if from user, see if there are any DTL entries to process */
	ld	r10,PACALPPACAPTR(r13)	/* get ptr to VPA */
	ld	r11,PACA_DTL_RIDX(r13)	/* get log read index */
	ld	r10,LPPACA_DTLIDX(r10)	/* get log write index */
	cmpd	cr1,r11,r10
	beq+	cr1,33f
	bl	.accumulate_stolen_time
	REST_GPR(0,r1)
	REST_4GPRS(3,r1)
	REST_2GPRS(7,r1)
	addi	r9,r1,STACK_FRAME_OVERHEAD
33:
END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
#endif /* CONFIG_VIRT_CPU_ACCOUNTING && CONFIG_PPC_SPLPAR */

	/*
	 * A syscall should always be called with interrupts enabled
	 * so we just unconditionally hard-enable here. When some kind
	 * of irq tracing is used, we additionally check that condition
	 * is correct
	 */
#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_BUG)
	lbz	r10,PACASOFTIRQEN(r13)
	xori	r10,r10,1
1:	tdnei	r10,0
	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
#endif

#ifdef CONFIG_PPC_BOOK3E
	wrteei	1
#else
	ld	r11,PACAKMSR(r13)
	ori	r11,r11,MSR_EE
	mtmsrd	r11,1
#endif /* CONFIG_PPC_BOOK3E */

	/* We do need to set SOFTE in the stack frame or the return
	 * from interrupt will be painful
	 */
	li	r10,1
	std	r10,SOFTE(r1)

#ifdef SHOW_SYSCALLS
	bl	.do_show_syscall
	REST_GPR(0,r1)
	REST_4GPRS(3,r1)
	REST_2GPRS(7,r1)
	addi	r9,r1,STACK_FRAME_OVERHEAD
#endif
	CURRENT_THREAD_INFO(r11, r1)
	ld	r10,TI_FLAGS(r11)
	andi.	r11,r10,_TIF_SYSCALL_T_OR_A
	bne-	syscall_dotrace
.Lsyscall_dotrace_cont:
	cmpldi	0,r0,NR_syscalls
	bge-	syscall_enosys

system_call:			/* label this so stack traces look sane */
/*
 * Need to vector to 32 Bit or default sys_call_table here,
 * based on caller's run-mode / personality.
 */
	ld	r11,.SYS_CALL_TABLE@toc(2)
	andi.	r10,r10,_TIF_32BIT
	beq	15f
	addi	r11,r11,8	/* use 32-bit syscall entries */
	clrldi	r3,r3,32
	clrldi	r4,r4,32
	clrldi	r5,r5,32
	clrldi	r6,r6,32
	clrldi	r7,r7,32
	clrldi	r8,r8,32
15:
	slwi	r0,r0,4
	ldx	r10,r11,r0	/* Fetch system call handler [ptr] */
	mtctr   r10
	bctrl			/* Call handler */

syscall_exit:
	std	r3,RESULT(r1)
#ifdef SHOW_SYSCALLS
	bl	.do_show_syscall_exit
	ld	r3,RESULT(r1)
#endif
	CURRENT_THREAD_INFO(r12, r1)

	ld	r8,_MSR(r1)
#ifdef CONFIG_PPC_BOOK3S
	/* No MSR:RI on BookE */
	andi.	r10,r8,MSR_RI
	beq-	unrecov_restore
#endif
	/*
	 * Disable interrupts so current_thread_info()->flags can't change,
	 * and so that we don't get interrupted after loading SRR0/1.
	 */
#ifdef CONFIG_PPC_BOOK3E
	wrteei	0
#else
	ld	r10,PACAKMSR(r13)
	/*
	 * For performance reasons we clear RI the same time that we
	 * clear EE. We only need to clear RI just before we restore r13
	 * below, but batching it with EE saves us one expensive mtmsrd call.
	 * We have to be careful to restore RI if we branch anywhere from
	 * here (eg syscall_exit_work).
	 */
	li	r9,MSR_RI
	andc	r11,r10,r9
	mtmsrd	r11,1
#endif /* CONFIG_PPC_BOOK3E */

	ld	r9,TI_FLAGS(r12)
	li	r11,-_LAST_ERRNO
	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
	bne-	syscall_exit_work
	cmpld	r3,r11
	ld	r5,_CCR(r1)
	bge-	syscall_error
.Lsyscall_error_cont:
	ld	r7,_NIP(r1)
BEGIN_FTR_SECTION
	stdcx.	r0,0,r1			/* to clear the reservation */
END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
	andi.	r6,r8,MSR_PR
	ld	r4,_LINK(r1)

	beq-	1f
	ACCOUNT_CPU_USER_EXIT(r11, r12)
	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
1:	ld	r2,GPR2(r1)
	ld	r1,GPR1(r1)
	mtlr	r4
	mtcr	r5
	mtspr	SPRN_SRR0,r7
	mtspr	SPRN_SRR1,r8
	RFI
	b	.	/* prevent speculative execution */

syscall_error:	
	oris	r5,r5,0x1000	/* Set SO bit in CR */
	neg	r3,r3
	std	r5,_CCR(r1)
	b	.Lsyscall_error_cont
	
/* Traced system call support */
syscall_dotrace:
	bl	.save_nvgprs
	addi	r3,r1,STACK_FRAME_OVERHEAD
	bl	.do_syscall_trace_enter
	/*
	 * Restore argument registers possibly just changed.
	 * We use the return value of do_syscall_trace_enter
	 * for the call number to look up in the table (r0).
	 */
	mr	r0,r3
	ld	r3,GPR3(r1)
	ld	r4,GPR4(r1)
	ld	r5,GPR5(r1)
	ld	r6,GPR6(r1)
	ld	r7,GPR7(r1)
	ld	r8,GPR8(r1)
	addi	r9,r1,STACK_FRAME_OVERHEAD
	CURRENT_THREAD_INFO(r10, r1)
	ld	r10,TI_FLAGS(r10)
	b	.Lsyscall_dotrace_cont

syscall_enosys:
	li	r3,-ENOSYS
	b	syscall_exit
	
syscall_exit_work:
#ifdef CONFIG_PPC_BOOK3S
	mtmsrd	r10,1		/* Restore RI */
#endif
	/* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr.
	 If TIF_NOERROR is set, just save r3 as it is. */

	andi.	r0,r9,_TIF_RESTOREALL
	beq+	0f
	REST_NVGPRS(r1)
	b	2f
0:	cmpld	r3,r11		/* r10 is -LAST_ERRNO */
	blt+	1f
	andi.	r0,r9,_TIF_NOERROR
	bne-	1f
	ld	r5,_CCR(r1)
	neg	r3,r3
	oris	r5,r5,0x1000	/* Set SO bit in CR */
	std	r5,_CCR(r1)
1:	std	r3,GPR3(r1)
2:	andi.	r0,r9,(_TIF_PERSYSCALL_MASK)
	beq	4f

	/* Clear per-syscall TIF flags if any are set.  */

	li	r11,_TIF_PERSYSCALL_MASK
	addi	r12,r12,TI_FLAGS
3:	ldarx	r10,0,r12
	andc	r10,r10,r11
	stdcx.	r10,0,r12
	bne-	3b
	subi	r12,r12,TI_FLAGS

4:	/* Anything else left to do? */
	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
	beq	.ret_from_except_lite

	/* Re-enable interrupts */
#ifdef CONFIG_PPC_BOOK3E
	wrteei	1
#else
	ld	r10,PACAKMSR(r13)
	ori	r10,r10,MSR_EE
	mtmsrd	r10,1
#endif /* CONFIG_PPC_BOOK3E */

	bl	.save_nvgprs
	addi	r3,r1,STACK_FRAME_OVERHEAD
	bl	.do_syscall_trace_leave
	b	.ret_from_except

/* Save non-volatile GPRs, if not already saved. */
_GLOBAL(save_nvgprs)
	ld	r11,_TRAP(r1)
	andi.	r0,r11,1
	beqlr-
	SAVE_NVGPRS(r1)
	clrrdi	r0,r11,1
	std	r0,_TRAP(r1)
	blr

	
/*
 * 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 (r14 - r31) before calling
 * the C code.  Similarly, fork, vfork and clone need the full
 * register state on the stack so that it can be copied to the child.
 */

_GLOBAL(ppc_fork)
	bl	.save_nvgprs
	bl	.sys_fork
	b	syscall_exit

_GLOBAL(ppc_vfork)
	bl	.save_nvgprs
	bl	.sys_vfork
	b	syscall_exit

_GLOBAL(ppc_clone)
	bl	.save_nvgprs
	bl	.sys_clone
	b	syscall_exit

_GLOBAL(ppc32_swapcontext)
	bl	.save_nvgprs
	bl	.compat_sys_swapcontext
	b	syscall_exit

_GLOBAL(ppc64_swapcontext)
	bl	.save_nvgprs
	bl	.sys_swapcontext
	b	syscall_exit

_GLOBAL(ret_from_fork)
	bl	.schedule_tail
	REST_NVGPRS(r1)
	li	r3,0
	b	syscall_exit

_GLOBAL(ret_from_kernel_thread)
	bl	.schedule_tail
	REST_NVGPRS(r1)
	REST_GPR(2,r1)
	mtlr	r14
	mr	r3,r15
	blrl
	li	r3,0
	b	.do_exit	# no return

_GLOBAL(__ret_from_kernel_execve)
	addi	r1,r3,-STACK_FRAME_OVERHEAD
	li	r10,1
	std	r10,SOFTE(r1)
	b	syscall_exit

	.section	".toc","aw"
DSCR_DEFAULT:
	.tc dscr_default[TC],dscr_default

	.section	".text"

/*
 * 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, via ret_from_except.
 * On entry, r3 points to the THREAD for the current task, r4
 * points to the THREAD for the new task.
 *
 * 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/powerpc/kernel/process.c 
 */
	.align	7
_GLOBAL(_switch)
	mflr	r0
	std	r0,16(r1)
	stdu	r1,-SWITCH_FRAME_SIZE(r1)
	/* r3-r13 are caller saved -- Cort */
	SAVE_8GPRS(14, r1)
	SAVE_10GPRS(22, r1)
	mflr	r20		/* Return to switch caller */
	mfmsr	r22
	li	r0, MSR_FP
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
	oris	r0,r0,MSR_VSX@h	/* Disable VSX */
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif /* CONFIG_VSX */
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
	oris	r0,r0,MSR_VEC@h	/* Disable altivec */
	mfspr	r24,SPRN_VRSAVE	/* save vrsave register value */
	std	r24,THREAD_VRSAVE(r3)
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_PPC64
BEGIN_FTR_SECTION
	mfspr	r25,SPRN_DSCR
	std	r25,THREAD_DSCR(r3)
END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
#endif
	and.	r0,r0,r22
	beq+	1f
	andc	r22,r22,r0
	MTMSRD(r22)
	isync
1:	std	r20,_NIP(r1)
	mfcr	r23
	std	r23,_CCR(r1)
	std	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 */

	/*
	 * If we optimise away the clear of the reservation in system
	 * calls because we know the CPU tracks the address of the
	 * reservation, then we need to clear it here to cover the
	 * case that the kernel context switch path has no larx
	 * instructions.
	 */
BEGIN_FTR_SECTION
	ldarx	r6,0,r1
END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS)

	addi	r6,r4,-THREAD	/* Convert THREAD to 'current' */
	std	r6,PACACURRENT(r13)	/* Set new 'current' */

	ld	r8,KSP(r4)	/* new stack pointer */
#ifdef CONFIG_PPC_BOOK3S
BEGIN_FTR_SECTION
  BEGIN_FTR_SECTION_NESTED(95)
	clrrdi	r6,r8,28	/* get its ESID */
	clrrdi	r9,r1,28	/* get current sp ESID */
  FTR_SECTION_ELSE_NESTED(95)
	clrrdi	r6,r8,40	/* get its 1T ESID */
	clrrdi	r9,r1,40	/* get current sp 1T ESID */
  ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(MMU_FTR_1T_SEGMENT, 95)
FTR_SECTION_ELSE
	b	2f
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_SLB)
	clrldi.	r0,r6,2		/* is new ESID c00000000? */
	cmpd	cr1,r6,r9	/* or is new ESID the same as current ESID? */
	cror	eq,4*cr1+eq,eq
	beq	2f		/* if yes, don't slbie it */

	/* Bolt in the new stack SLB entry */
	ld	r7,KSP_VSID(r4)	/* Get new stack's VSID */
	oris	r0,r6,(SLB_ESID_V)@h
	ori	r0,r0,(SLB_NUM_BOLTED-1)@l
BEGIN_FTR_SECTION
	li	r9,MMU_SEGSIZE_1T	/* insert B field */
	oris	r6,r6,(MMU_SEGSIZE_1T << SLBIE_SSIZE_SHIFT)@h
	rldimi	r7,r9,SLB_VSID_SSIZE_SHIFT,0
END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)

	/* Update the last bolted SLB.  No write barriers are needed
	 * here, provided we only update the current CPU's SLB shadow
	 * buffer.
	 */
	ld	r9,PACA_SLBSHADOWPTR(r13)
	li	r12,0
	std	r12,SLBSHADOW_STACKESID(r9) /* Clear ESID */
	std	r7,SLBSHADOW_STACKVSID(r9)  /* Save VSID */
	std	r0,SLBSHADOW_STACKESID(r9)  /* Save ESID */

	/* No need to check for MMU_FTR_NO_SLBIE_B here, since when
	 * we have 1TB segments, the only CPUs known to have the errata
	 * only support less than 1TB of system memory and we'll never
	 * actually hit this code path.
	 */

	slbie	r6
	slbie	r6		/* Workaround POWER5 < DD2.1 issue */
	slbmte	r7,r0
	isync
2:
#endif /* !CONFIG_PPC_BOOK3S */

	CURRENT_THREAD_INFO(r7, r8)  /* base of new stack */
	/* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE
	   because we don't need to leave the 288-byte ABI gap at the
	   top of the kernel stack. */
	addi	r7,r7,THREAD_SIZE-SWITCH_FRAME_SIZE

	mr	r1,r8		/* start using new stack pointer */
	std	r7,PACAKSAVE(r13)

#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
	ld	r0,THREAD_VRSAVE(r4)
	mtspr	SPRN_VRSAVE,r0		/* if G4, restore VRSAVE reg */
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_PPC64
BEGIN_FTR_SECTION
	lwz	r6,THREAD_DSCR_INHERIT(r4)
	ld	r7,DSCR_DEFAULT@toc(2)
	ld	r0,THREAD_DSCR(r4)
	cmpwi	r6,0
	bne	1f
	ld	r0,0(r7)
1:	cmpd	r0,r25
	beq	2f
	mtspr	SPRN_DSCR,r0
2:
END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
#endif

	ld	r6,_CCR(r1)
	mtcrf	0xFF,r6

	/* r3-r13 are destroyed -- Cort */
	REST_8GPRS(14, r1)
	REST_10GPRS(22, r1)

	/* convert old thread to its task_struct for return value */
	addi	r3,r3,-THREAD
	ld	r7,_NIP(r1)	/* Return to _switch caller in new task */
	mtlr	r7
	addi	r1,r1,SWITCH_FRAME_SIZE
	blr

	.align	7
_GLOBAL(ret_from_except)
	ld	r11,_TRAP(r1)
	andi.	r0,r11,1
	bne	.ret_from_except_lite
	REST_NVGPRS(r1)

_GLOBAL(ret_from_except_lite)
	/*
	 * Disable interrupts so that current_thread_info()->flags
	 * can't change between when we test it and when we return
	 * from the interrupt.
	 */
#ifdef CONFIG_PPC_BOOK3E
	wrteei	0
#else
	ld	r10,PACAKMSR(r13) /* Get kernel MSR without EE */
	mtmsrd	r10,1		  /* Update machine state */
#endif /* CONFIG_PPC_BOOK3E */

	CURRENT_THREAD_INFO(r9, r1)
	ld	r3,_MSR(r1)
	ld	r4,TI_FLAGS(r9)
	andi.	r3,r3,MSR_PR
	beq	resume_kernel

	/* Check current_thread_info()->flags */
	andi.	r0,r4,_TIF_USER_WORK_MASK
	beq	restore

	andi.	r0,r4,_TIF_NEED_RESCHED
	beq	1f
	bl	.restore_interrupts
	bl	.schedule
	b	.ret_from_except_lite

1:	bl	.save_nvgprs
	bl	.restore_interrupts
	addi	r3,r1,STACK_FRAME_OVERHEAD
	bl	.do_notify_resume
	b	.ret_from_except

resume_kernel:
	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
	CURRENT_THREAD_INFO(r9, r1)
	ld	r8,TI_FLAGS(r9)
	andis.	r8,r8,_TIF_EMULATE_STACK_STORE@h
	beq+	1f

	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */

	lwz	r3,GPR1(r1)
	subi	r3,r3,INT_FRAME_SIZE	/* dst: Allocate a trampoline exception frame */
	mr	r4,r1			/* src:  current exception frame */
	mr	r1,r3			/* Reroute the trampoline frame to r1 */

	/* Copy from the original to the trampoline. */
	li	r5,INT_FRAME_SIZE/8	/* size: INT_FRAME_SIZE */
	li	r6,0			/* start offset: 0 */
	mtctr	r5
2:	ldx	r0,r6,r4
	stdx	r0,r6,r3
	addi	r6,r6,8
	bdnz	2b

	/* Do real store operation to complete stwu */
	lwz	r5,GPR1(r1)
	std	r8,0(r5)

	/* Clear _TIF_EMULATE_STACK_STORE flag */
	lis	r11,_TIF_EMULATE_STACK_STORE@h
	addi	r5,r9,TI_FLAGS
	ldarx	r4,0,r5
	andc	r4,r4,r11
	stdcx.	r4,0,r5
	bne-	0b
1:

#ifdef CONFIG_PREEMPT
	/* Check if we need to preempt */
	andi.	r0,r4,_TIF_NEED_RESCHED
	beq+	restore
	/* Check that preempt_count() == 0 and interrupts are enabled */
	lwz	r8,TI_PREEMPT(r9)
	cmpwi	cr1,r8,0
	ld	r0,SOFTE(r1)
	cmpdi	r0,0
	crandc	eq,cr1*4+eq,eq
	bne	restore

	/*
	 * Here we are preempting the current task. We want to make
	 * sure we are soft-disabled first
	 */
	SOFT_DISABLE_INTS(r3,r4)
1:	bl	.preempt_schedule_irq

	/* Re-test flags and eventually loop */
	CURRENT_THREAD_INFO(r9, r1)
	ld	r4,TI_FLAGS(r9)
	andi.	r0,r4,_TIF_NEED_RESCHED
	bne	1b
#endif /* CONFIG_PREEMPT */

	.globl	fast_exc_return_irq
fast_exc_return_irq:
restore:
	/*
	 * This is the main kernel exit path. First we check if we
	 * are about to re-enable interrupts
	 */
	ld	r5,SOFTE(r1)
	lbz	r6,PACASOFTIRQEN(r13)
	cmpwi	cr0,r5,0
	beq	restore_irq_off

	/* We are enabling, were we already enabled ? Yes, just return */
	cmpwi	cr0,r6,1
	beq	cr0,do_restore

	/*
	 * We are about to soft-enable interrupts (we are hard disabled
	 * at this point). We check if there's anything that needs to
	 * be replayed first.
	 */
	lbz	r0,PACAIRQHAPPENED(r13)
	cmpwi	cr0,r0,0
	bne-	restore_check_irq_replay

	/*
	 * Get here when nothing happened while soft-disabled, just
	 * soft-enable and move-on. We will hard-enable as a side
	 * effect of rfi
	 */
restore_no_replay:
	TRACE_ENABLE_INTS
	li	r0,1
	stb	r0,PACASOFTIRQEN(r13);

	/*
	 * Final return path. BookE is handled in a different file
	 */
do_restore:
#ifdef CONFIG_PPC_BOOK3E
	b	.exception_return_book3e
#else
	/*
	 * Clear the reservation. If we know the CPU tracks the address of
	 * the reservation then we can potentially save some cycles and use
	 * a larx. On POWER6 and POWER7 this is significantly faster.
	 */
BEGIN_FTR_SECTION
	stdcx.	r0,0,r1		/* to clear the reservation */
FTR_SECTION_ELSE
	ldarx	r4,0,r1
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)

	/*
	 * Some code path such as load_up_fpu or altivec return directly
	 * here. They run entirely hard disabled and do not alter the
	 * interrupt state. They also don't use lwarx/stwcx. and thus
	 * are known not to leave dangling reservations.
	 */
	.globl	fast_exception_return
fast_exception_return:
	ld	r3,_MSR(r1)
	ld	r4,_CTR(r1)
	ld	r0,_LINK(r1)
	mtctr	r4
	mtlr	r0
	ld	r4,_XER(r1)
	mtspr	SPRN_XER,r4

	REST_8GPRS(5, r1)

	andi.	r0,r3,MSR_RI
	beq-	unrecov_restore

	/*
	 * Clear RI before restoring r13.  If we are returning to
	 * userspace and we take an exception after restoring r13,
	 * we end up corrupting the userspace r13 value.
	 */
	ld	r4,PACAKMSR(r13) /* Get kernel MSR without EE */
	andc	r4,r4,r0	 /* r0 contains MSR_RI here */
	mtmsrd	r4,1

	/*
	 * r13 is our per cpu area, only restore it if we are returning to
	 * userspace the value stored in the stack frame may belong to
	 * another CPU.
	 */
	andi.	r0,r3,MSR_PR
	beq	1f
	ACCOUNT_CPU_USER_EXIT(r2, r4)
	REST_GPR(13, r1)
1:
	mtspr	SPRN_SRR1,r3

	ld	r2,_CCR(r1)
	mtcrf	0xFF,r2
	ld	r2,_NIP(r1)
	mtspr	SPRN_SRR0,r2

	ld	r0,GPR0(r1)
	ld	r2,GPR2(r1)
	ld	r3,GPR3(r1)
	ld	r4,GPR4(r1)
	ld	r1,GPR1(r1)

	rfid
	b	.	/* prevent speculative execution */

#endif /* CONFIG_PPC_BOOK3E */

	/*
	 * We are returning to a context with interrupts soft disabled.
	 *
	 * However, we may also about to hard enable, so we need to
	 * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
	 * or that bit can get out of sync and bad things will happen
	 */
restore_irq_off:
	ld	r3,_MSR(r1)
	lbz	r7,PACAIRQHAPPENED(r13)
	andi.	r0,r3,MSR_EE
	beq	1f
	rlwinm	r7,r7,0,~PACA_IRQ_HARD_DIS
	stb	r7,PACAIRQHAPPENED(r13)
1:	li	r0,0
	stb	r0,PACASOFTIRQEN(r13);
	TRACE_DISABLE_INTS
	b	do_restore

	/*
	 * Something did happen, check if a re-emit is needed
	 * (this also clears paca->irq_happened)
	 */
restore_check_irq_replay:
	/* XXX: We could implement a fast path here where we check
	 * for irq_happened being just 0x01, in which case we can
	 * clear it and return. That means that we would potentially
	 * miss a decrementer having wrapped all the way around.
	 *
	 * Still, this might be useful for things like hash_page
	 */
	bl	.__check_irq_replay
	cmpwi	cr0,r3,0
 	beq	restore_no_replay
 
	/*
	 * We need to re-emit an interrupt. We do so by re-using our
	 * existing exception frame. We first change the trap value,
	 * but we need to ensure we preserve the low nibble of it
	 */
	ld	r4,_TRAP(r1)
	clrldi	r4,r4,60
	or	r4,r4,r3
	std	r4,_TRAP(r1)

	/*
	 * Then find the right handler and call it. Interrupts are
	 * still soft-disabled and we keep them that way.
	*/
	cmpwi	cr0,r3,0x500
	bne	1f
	addi	r3,r1,STACK_FRAME_OVERHEAD;
 	bl	.do_IRQ
	b	.ret_from_except
1:	cmpwi	cr0,r3,0x900
	bne	1f
	addi	r3,r1,STACK_FRAME_OVERHEAD;
	bl	.timer_interrupt
	b	.ret_from_except
#ifdef CONFIG_PPC_BOOK3E
1:	cmpwi	cr0,r3,0x280
	bne	1f
	addi	r3,r1,STACK_FRAME_OVERHEAD;
	bl	.doorbell_exception
	b	.ret_from_except
#endif /* CONFIG_PPC_BOOK3E */
1:	b	.ret_from_except /* What else to do here ? */
 
unrecov_restore:
	addi	r3,r1,STACK_FRAME_OVERHEAD
	bl	.unrecoverable_exception
	b	unrecov_restore

#ifdef CONFIG_PPC_RTAS
/*
 * On CHRP, the Run-Time Abstraction Services (RTAS) have to be
 * called with the MMU off.
 *
 * In addition, we need to be in 32b mode, at least for now.
 * 
 * Note: r3 is an input parameter to rtas, so don't trash it...
 */
_GLOBAL(enter_rtas)
	mflr	r0
	std	r0,16(r1)
        stdu	r1,-RTAS_FRAME_SIZE(r1)	/* Save SP and create stack space. */

	/* Because RTAS is running in 32b mode, it clobbers the high order half
	 * of all registers that it saves.  We therefore save those registers
	 * RTAS might touch to the stack.  (r0, r3-r13 are caller saved)
   	 */
	SAVE_GPR(2, r1)			/* Save the TOC */
	SAVE_GPR(13, r1)		/* Save paca */
	SAVE_8GPRS(14, r1)		/* Save the non-volatiles */
	SAVE_10GPRS(22, r1)		/* ditto */

	mfcr	r4
	std	r4,_CCR(r1)
	mfctr	r5
	std	r5,_CTR(r1)
	mfspr	r6,SPRN_XER
	std	r6,_XER(r1)
	mfdar	r7
	std	r7,_DAR(r1)
	mfdsisr	r8
	std	r8,_DSISR(r1)

	/* Temporary workaround to clear CR until RTAS can be modified to
	 * ignore all bits.
	 */
	li	r0,0
	mtcr	r0

#ifdef CONFIG_BUG	
	/* There is no way it is acceptable to get here with interrupts enabled,
	 * check it with the asm equivalent of WARN_ON
	 */
	lbz	r0,PACASOFTIRQEN(r13)
1:	tdnei	r0,0
	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
#endif
	
	/* Hard-disable interrupts */
	mfmsr	r6
	rldicl	r7,r6,48,1
	rotldi	r7,r7,16
	mtmsrd	r7,1

	/* Unfortunately, the stack pointer and the MSR are also clobbered,
	 * so they are saved in the PACA which allows us to restore
	 * our original state after RTAS returns.
         */
	std	r1,PACAR1(r13)
        std	r6,PACASAVEDMSR(r13)

	/* Setup our real return addr */	
	LOAD_REG_ADDR(r4,.rtas_return_loc)
	clrldi	r4,r4,2			/* convert to realmode address */
       	mtlr	r4

	li	r0,0
	ori	r0,r0,MSR_EE|MSR_SE|MSR_BE|MSR_RI
	andc	r0,r6,r0
	
        li      r9,1
        rldicr  r9,r9,MSR_SF_LG,(63-MSR_SF_LG)
	ori	r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI
	andc	r6,r0,r9
	sync				/* disable interrupts so SRR0/1 */
	mtmsrd	r0			/* don't get trashed */

	LOAD_REG_ADDR(r4, rtas)
	ld	r5,RTASENTRY(r4)	/* get the rtas->entry value */
	ld	r4,RTASBASE(r4)		/* get the rtas->base value */
	
	mtspr	SPRN_SRR0,r5
	mtspr	SPRN_SRR1,r6
	rfid
	b	.	/* prevent speculative execution */

_STATIC(rtas_return_loc)
	/* relocation is off at this point */
	GET_PACA(r4)
	clrldi	r4,r4,2			/* convert to realmode address */

	bcl	20,31,$+4
0:	mflr	r3
	ld	r3,(1f-0b)(r3)		/* get &.rtas_restore_regs */

	mfmsr   r6
	li	r0,MSR_RI
	andc	r6,r6,r0
	sync	
	mtmsrd  r6
        
        ld	r1,PACAR1(r4)           /* Restore our SP */
        ld	r4,PACASAVEDMSR(r4)     /* Restore our MSR */

	mtspr	SPRN_SRR0,r3
	mtspr	SPRN_SRR1,r4
	rfid
	b	.	/* prevent speculative execution */

	.align	3
1:	.llong	.rtas_restore_regs

_STATIC(rtas_restore_regs)
	/* relocation is on at this point */
	REST_GPR(2, r1)			/* Restore the TOC */
	REST_GPR(13, r1)		/* Restore paca */
	REST_8GPRS(14, r1)		/* Restore the non-volatiles */
	REST_10GPRS(22, r1)		/* ditto */

	GET_PACA(r13)

	ld	r4,_CCR(r1)
	mtcr	r4
	ld	r5,_CTR(r1)
	mtctr	r5
	ld	r6,_XER(r1)
	mtspr	SPRN_XER,r6
	ld	r7,_DAR(r1)
	mtdar	r7
	ld	r8,_DSISR(r1)
	mtdsisr	r8

        addi	r1,r1,RTAS_FRAME_SIZE	/* Unstack our frame */
	ld	r0,16(r1)		/* get return address */

	mtlr    r0
        blr				/* return to caller */

#endif /* CONFIG_PPC_RTAS */

_GLOBAL(enter_prom)
	mflr	r0
	std	r0,16(r1)
        stdu	r1,-PROM_FRAME_SIZE(r1)	/* Save SP and create stack space */

	/* Because PROM is running in 32b mode, it clobbers the high order half
	 * of all registers that it saves.  We therefore save those registers
	 * PROM might touch to the stack.  (r0, r3-r13 are caller saved)
   	 */
	SAVE_GPR(2, r1)
	SAVE_GPR(13, r1)
	SAVE_8GPRS(14, r1)
	SAVE_10GPRS(22, r1)
	mfcr	r10
	mfmsr	r11
	std	r10,_CCR(r1)
	std	r11,_MSR(r1)

	/* Get the PROM entrypoint */
	mtlr	r4

	/* Switch MSR to 32 bits mode
	 */
#ifdef CONFIG_PPC_BOOK3E
	rlwinm	r11,r11,0,1,31
	mtmsr	r11
#else /* CONFIG_PPC_BOOK3E */
        mfmsr   r11
        li      r12,1
        rldicr  r12,r12,MSR_SF_LG,(63-MSR_SF_LG)
        andc    r11,r11,r12
        li      r12,1
        rldicr  r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG)
        andc    r11,r11,r12
        mtmsrd  r11
#endif /* CONFIG_PPC_BOOK3E */
        isync

	/* Enter PROM here... */
	blrl

	/* Just make sure that r1 top 32 bits didn't get
	 * corrupt by OF
	 */
	rldicl	r1,r1,0,32

	/* Restore the MSR (back to 64 bits) */
	ld	r0,_MSR(r1)
	MTMSRD(r0)
        isync

	/* Restore other registers */
	REST_GPR(2, r1)
	REST_GPR(13, r1)
	REST_8GPRS(14, r1)
	REST_10GPRS(22, r1)
	ld	r4,_CCR(r1)
	mtcr	r4
	
        addi	r1,r1,PROM_FRAME_SIZE
	ld	r0,16(r1)
	mtlr    r0
        blr

#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE
_GLOBAL(mcount)
_GLOBAL(_mcount)
	blr

_GLOBAL(ftrace_caller)
	/* Taken from output of objdump from lib64/glibc */
	mflr	r3
	ld	r11, 0(r1)
	stdu	r1, -112(r1)
	std	r3, 128(r1)
	ld	r4, 16(r11)
	subi	r3, r3, MCOUNT_INSN_SIZE
.globl ftrace_call
ftrace_call:
	bl	ftrace_stub
	nop
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.globl ftrace_graph_call
ftrace_graph_call:
	b	ftrace_graph_stub
_GLOBAL(ftrace_graph_stub)
#endif
	ld	r0, 128(r1)
	mtlr	r0
	addi	r1, r1, 112
_GLOBAL(ftrace_stub)
	blr
#else
_GLOBAL(mcount)
	blr

_GLOBAL(_mcount)
	/* Taken from output of objdump from lib64/glibc */
	mflr	r3
	ld	r11, 0(r1)
	stdu	r1, -112(r1)
	std	r3, 128(r1)
	ld	r4, 16(r11)

	subi	r3, r3, MCOUNT_INSN_SIZE
	LOAD_REG_ADDR(r5,ftrace_trace_function)
	ld	r5,0(r5)
	ld	r5,0(r5)
	mtctr	r5
	bctrl
	nop


#ifdef CONFIG_FUNCTION_GRAPH_TRACER
	b	ftrace_graph_caller
#endif
	ld	r0, 128(r1)
	mtlr	r0
	addi	r1, r1, 112
_GLOBAL(ftrace_stub)
	blr

#endif /* CONFIG_DYNAMIC_FTRACE */

#ifdef CONFIG_FUNCTION_GRAPH_TRACER
_GLOBAL(ftrace_graph_caller)
	/* load r4 with local address */
	ld	r4, 128(r1)
	subi	r4, r4, MCOUNT_INSN_SIZE

	/* get the parent address */
	ld	r11, 112(r1)
	addi	r3, r11, 16

	bl	.prepare_ftrace_return
	nop

	ld	r0, 128(r1)
	mtlr	r0
	addi	r1, r1, 112
	blr

_GLOBAL(return_to_handler)
	/* need to save return values */
	std	r4,  -24(r1)
	std	r3,  -16(r1)
	std	r31, -8(r1)
	mr	r31, r1
	stdu	r1, -112(r1)

	bl	.ftrace_return_to_handler
	nop

	/* return value has real return address */
	mtlr	r3

	ld	r1, 0(r1)
	ld	r4,  -24(r1)
	ld	r3,  -16(r1)
	ld	r31, -8(r1)

	/* Jump back to real return address */
	blr

_GLOBAL(mod_return_to_handler)
	/* need to save return values */
	std	r4,  -32(r1)
	std	r3,  -24(r1)
	/* save TOC */
	std	r2,  -16(r1)
	std	r31, -8(r1)
	mr	r31, r1
	stdu	r1, -112(r1)

	/*
	 * We are in a module using the module's TOC.
	 * Switch to our TOC to run inside the core kernel.
	 */
	ld	r2, PACATOC(r13)

	bl	.ftrace_return_to_handler
	nop

	/* return value has real return address */
	mtlr	r3

	ld	r1, 0(r1)
	ld	r4,  -32(r1)
	ld	r3,  -24(r1)
	ld	r2,  -16(r1)
	ld	r31, -8(r1)

	/* Jump back to real return address */
	blr
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
#endif /* CONFIG_FUNCTION_TRACER */