entry-armv.s

linux-2.6.15.6

	.align	5
__pabt_usr:
	usr_entry

	enable_irq				@ Enable interrupts
	mov	r0, r2				@ address (pc)
	mov	r1, sp				@ regs
	bl	do_PrefetchAbort		@ call abort handler
	/* fall through */
/*
 * This is the return code to user mode for abort handlers
 */
ENTRY(ret_from_exception)
	get_thread_info tsk
	mov	why, #0
	b	ret_to_user

/*
 * Register switch for ARMv3 and ARMv4 processors
 * r0 = previous task_struct, r1 = previous thread_info, r2 = next thread_info
 * previous and next are guaranteed not to be the same.
 */
ENTRY(__switch_to)
	add	ip, r1, #TI_CPU_SAVE
	ldr	r3, [r2, #TI_TP_VALUE]
	stmia	ip!, {r4 - sl, fp, sp, lr}	@ Store most regs on stack
	ldr	r6, [r2, #TI_CPU_DOMAIN]!
#if __LINUX_ARM_ARCH__ >= 6
#ifdef CONFIG_CPU_MPCORE
	clrex
#else
	strex	r5, r4, [ip]			@ Clear exclusive monitor
#endif
#endif
#if defined(CONFIG_CPU_XSCALE) && !defined(CONFIG_IWMMXT)
	mra	r4, r5, acc0
	stmia   ip, {r4, r5}
#endif
#if defined(CONFIG_HAS_TLS_REG)
	mcr	p15, 0, r3, c13, c0, 3		@ set TLS register
#elif !defined(CONFIG_TLS_REG_EMUL)
	mov	r4, #0xffff0fff
	str	r3, [r4, #-15]			@ TLS val at 0xffff0ff0
#endif
	mcr	p15, 0, r6, c3, c0, 0		@ Set domain register
#ifdef CONFIG_VFP
	@ Always disable VFP so we can lazily save/restore the old
	@ state. This occurs in the context of the previous thread.
	VFPFMRX	r4, FPEXC
	bic	r4, r4, #FPEXC_ENABLE
	VFPFMXR	FPEXC, r4
#endif
#if defined(CONFIG_IWMMXT)
	bl	iwmmxt_task_switch
#elif defined(CONFIG_CPU_XSCALE)
	add	r4, r2, #40			@ cpu_context_save->extra
	ldmib	r4, {r4, r5}
	mar	acc0, r4, r5
#endif
	ldmib	r2, {r4 - sl, fp, sp, pc}	@ Load all regs saved previously

	__INIT

/*
 * User helpers.
 *
 * These are segment of kernel provided user code reachable from user space
 * at a fixed address in kernel memory.  This is used to provide user space
 * with some operations which require kernel help because of unimplemented
 * native feature and/or instructions in many ARM CPUs. The idea is for
 * this code to be executed directly in user mode for best efficiency but
 * which is too intimate with the kernel counter part to be left to user
 * libraries.  In fact this code might even differ from one CPU to another
 * depending on the available  instruction set and restrictions like on
 * SMP systems.  In other words, the kernel reserves the right to change
 * this code as needed without warning. Only the entry points and their
 * results are guaranteed to be stable.
 *
 * Each segment is 32-byte aligned and will be moved to the top of the high
 * vector page.  New segments (if ever needed) must be added in front of
 * existing ones.  This mechanism should be used only for things that are
 * really small and justified, and not be abused freely.
 *
 * User space is expected to implement those things inline when optimizing
 * for a processor that has the necessary native support, but only if such
 * resulting binaries are already to be incompatible with earlier ARM
 * processors due to the use of unsupported instructions other than what
 * is provided here.  In other words don't make binaries unable to run on
 * earlier processors just for the sake of not using these kernel helpers
 * if your compiled code is not going to use the new instructions for other
 * purpose.
 */

	.align	5
	.globl	__kuser_helper_start
__kuser_helper_start:

/*
 * Reference prototype:
 *
 *	void __kernel_memory_barrier(void)
 *
 * Input:
 *
 *	lr = return address
 *
 * Output:
 *
 *	none
 *
 * Clobbered:
 *
 *	the Z flag might be lost
 *
 * Definition and user space usage example:
 *
 *	typedef void (__kernel_dmb_t)(void);
 *	#define __kernel_dmb (*(__kernel_dmb_t *)0xffff0fa0)
 *
 * Apply any needed memory barrier to preserve consistency with data modified
 * manually and __kuser_cmpxchg usage.
 *
 * This could be used as follows:
 *
 * #define __kernel_dmb() \
 *         asm volatile ( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #95" \
 *	        : : : "lr","cc" )
 */

__kuser_memory_barrier:				@ 0xffff0fa0

#if __LINUX_ARM_ARCH__ >= 6 && defined(CONFIG_SMP)
	mcr	p15, 0, r0, c7, c10, 5	@ dmb
#endif
	mov	pc, lr

	.align	5

/*
 * Reference prototype:
 *
 *	int __kernel_cmpxchg(int oldval, int newval, int *ptr)
 *
 * Input:
 *
 *	r0 = oldval
 *	r1 = newval
 *	r2 = ptr
 *	lr = return address
 *
 * Output:
 *
 *	r0 = returned value (zero or non-zero)
 *	C flag = set if r0 == 0, clear if r0 != 0
 *
 * Clobbered:
 *
 *	r3, ip, flags
 *
 * Definition and user space usage example:
 *
 *	typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr);
 *	#define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0)
 *
 * Atomically store newval in *ptr if *ptr is equal to oldval for user space.
 * Return zero if *ptr was changed or non-zero if no exchange happened.
 * The C flag is also set if *ptr was changed to allow for assembly
 * optimization in the calling code.
 *
 * Note: this routine already includes memory barriers as needed.
 *
 * For example, a user space atomic_add implementation could look like this:
 *
 * #define atomic_add(ptr, val) \
 *	({ register unsigned int *__ptr asm("r2") = (ptr); \
 *	   register unsigned int __result asm("r1"); \
 *	   asm volatile ( \
 *	       "1: @ atomic_add\n\t" \
 *	       "ldr	r0, [r2]\n\t" \
 *	       "mov	r3, #0xffff0fff\n\t" \
 *	       "add	lr, pc, #4\n\t" \
 *	       "add	r1, r0, %2\n\t" \
 *	       "add	pc, r3, #(0xffff0fc0 - 0xffff0fff)\n\t" \
 *	       "bcc	1b" \
 *	       : "=&r" (__result) \
 *	       : "r" (__ptr), "rIL" (val) \
 *	       : "r0","r3","ip","lr","cc","memory" ); \
 *	   __result; })
 */

__kuser_cmpxchg:				@ 0xffff0fc0

#if defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)

	/*
	 * Poor you.  No fast solution possible...
	 * The kernel itself must perform the operation.
	 * A special ghost syscall is used for that (see traps.c).
	 */
	swi	#0x9ffff0
	mov	pc, lr

#elif __LINUX_ARM_ARCH__ < 6

	/*
	 * Theory of operation:
	 *
	 * We set the Z flag before loading oldval. If ever an exception
	 * occurs we can not be sure the loaded value will still be the same
	 * when the exception returns, therefore the user exception handler
	 * will clear the Z flag whenever the interrupted user code was
	 * actually from the kernel address space (see the usr_entry macro).
	 *
	 * The post-increment on the str is used to prevent a race with an
	 * exception happening just after the str instruction which would
	 * clear the Z flag although the exchange was done.
	 */
	teq	ip, ip			@ set Z flag
	ldr	ip, [r2]		@ load current val
	add	r3, r2, #1		@ prepare store ptr
	teqeq	ip, r0			@ compare with oldval if still allowed
	streq	r1, [r3, #-1]!		@ store newval if still allowed
	subs	r0, r2, r3		@ if r2 == r3 the str occured
	mov	pc, lr

#else

#ifdef CONFIG_SMP
	mcr	p15, 0, r0, c7, c10, 5	@ dmb
#endif
	ldrex	r3, [r2]
	subs	r3, r3, r0
	strexeq	r3, r1, [r2]
	rsbs	r0, r3, #0
#ifdef CONFIG_SMP
	mcr	p15, 0, r0, c7, c10, 5	@ dmb
#endif
	mov	pc, lr

#endif

	.align	5

/*
 * Reference prototype:
 *
 *	int __kernel_get_tls(void)
 *
 * Input:
 *
 *	lr = return address
 *
 * Output:
 *
 *	r0 = TLS value
 *
 * Clobbered:
 *
 *	the Z flag might be lost
 *
 * Definition and user space usage example:
 *
 *	typedef int (__kernel_get_tls_t)(void);
 *	#define __kernel_get_tls (*(__kernel_get_tls_t *)0xffff0fe0)
 *
 * Get the TLS value as previously set via the __ARM_NR_set_tls syscall.
 *
 * This could be used as follows:
 *
 * #define __kernel_get_tls() \
 *	({ register unsigned int __val asm("r0"); \
 *         asm( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #31" \
 *	        : "=r" (__val) : : "lr","cc" ); \
 *	   __val; })
 */

__kuser_get_tls:				@ 0xffff0fe0

#if !defined(CONFIG_HAS_TLS_REG) && !defined(CONFIG_TLS_REG_EMUL)

	ldr	r0, [pc, #(16 - 8)]		@ TLS stored at 0xffff0ff0
	mov	pc, lr

#else

	mrc	p15, 0, r0, c13, c0, 3		@ read TLS register
	mov	pc, lr

#endif

	.rep	5
	.word	0			@ pad up to __kuser_helper_version
	.endr

/*
 * Reference declaration:
 *
 *	extern unsigned int __kernel_helper_version;
 *
 * Definition and user space usage example:
 *
 *	#define __kernel_helper_version (*(unsigned int *)0xffff0ffc)
 *
 * User space may read this to determine the curent number of helpers
 * available.
 */

__kuser_helper_version:				@ 0xffff0ffc
	.word	((__kuser_helper_end - __kuser_helper_start) >> 5)

	.globl	__kuser_helper_end
__kuser_helper_end:


/*
 * Vector stubs.
 *
 * This code is copied to 0xffff0200 so we can use branches in the
 * vectors, rather than ldr's.  Note that this code must not
 * exceed 0x300 bytes.
 *
 * Common stub entry macro:
 *   Enter in IRQ mode, spsr = SVC/USR CPSR, lr = SVC/USR PC
 *
 * SP points to a minimal amount of processor-private memory, the address
 * of which is copied into r0 for the mode specific abort handler.
 */
	.macro	vector_stub, name, mode, correction=0
	.align	5

vector_\name:
	.if \correction
	sub	lr, lr, #\correction
	.endif

	@
	@ Save r0, lr_<exception> (parent PC) and spsr_<exception>
	@ (parent CPSR)
	@
	stmia	sp, {r0, lr}		@ save r0, lr
	mrs	lr, spsr
	str	lr, [sp, #8]		@ save spsr

	@
	@ Prepare for SVC32 mode.  IRQs remain disabled.
	@
	mrs	r0, cpsr
	eor	r0, r0, #(\mode ^ SVC_MODE)
	msr	spsr_cxsf, r0

	@
	@ the branch table must immediately follow this code
	@
	and	lr, lr, #0x0f
	mov	r0, sp
	ldr	lr, [pc, lr, lsl #2]
	movs	pc, lr			@ branch to handler in SVC mode
	.endm

	.globl	__stubs_start
__stubs_start:
/*
 * Interrupt dispatcher
 */
	vector_stub	irq, IRQ_MODE, 4

	.long	__irq_usr			@  0  (USR_26 / USR_32)
	.long	__irq_invalid			@  1  (FIQ_26 / FIQ_32)
	.long	__irq_invalid			@  2  (IRQ_26 / IRQ_32)
	.long	__irq_svc			@  3  (SVC_26 / SVC_32)
	.long	__irq_invalid			@  4
	.long	__irq_invalid			@  5
	.long	__irq_invalid			@  6
	.long	__irq_invalid			@  7
	.long	__irq_invalid			@  8
	.long	__irq_invalid			@  9
	.long	__irq_invalid			@  a
	.long	__irq_invalid			@  b
	.long	__irq_invalid			@  c
	.long	__irq_invalid			@  d
	.long	__irq_invalid			@  e
	.long	__irq_invalid			@  f

/*
 * Data abort dispatcher
 * Enter in ABT mode, spsr = USR CPSR, lr = USR PC
 */
	vector_stub	dabt, ABT_MODE, 8

	.long	__dabt_usr			@  0  (USR_26 / USR_32)
	.long	__dabt_invalid			@  1  (FIQ_26 / FIQ_32)
	.long	__dabt_invalid			@  2  (IRQ_26 / IRQ_32)
	.long	__dabt_svc			@  3  (SVC_26 / SVC_32)
	.long	__dabt_invalid			@  4
	.long	__dabt_invalid			@  5
	.long	__dabt_invalid			@  6
	.long	__dabt_invalid			@  7
	.long	__dabt_invalid			@  8
	.long	__dabt_invalid			@  9
	.long	__dabt_invalid			@  a
	.long	__dabt_invalid			@  b
	.long	__dabt_invalid			@  c
	.long	__dabt_invalid			@  d
	.long	__dabt_invalid			@  e
	.long	__dabt_invalid			@  f

/*
 * Prefetch abort dispatcher
 * Enter in ABT mode, spsr = USR CPSR, lr = USR PC
 */
	vector_stub	pabt, ABT_MODE, 4

	.long	__pabt_usr			@  0 (USR_26 / USR_32)
	.long	__pabt_invalid			@  1 (FIQ_26 / FIQ_32)
	.long	__pabt_invalid			@  2 (IRQ_26 / IRQ_32)
	.long	__pabt_svc			@  3 (SVC_26 / SVC_32)
	.long	__pabt_invalid			@  4
	.long	__pabt_invalid			@  5
	.long	__pabt_invalid			@  6
	.long	__pabt_invalid			@  7
	.long	__pabt_invalid			@  8
	.long	__pabt_invalid			@  9
	.long	__pabt_invalid			@  a
	.long	__pabt_invalid			@  b
	.long	__pabt_invalid			@  c
	.long	__pabt_invalid			@  d
	.long	__pabt_invalid			@  e
	.long	__pabt_invalid			@  f

/*
 * Undef instr entry dispatcher
 * Enter in UND mode, spsr = SVC/USR CPSR, lr = SVC/USR PC
 */
	vector_stub	und, UND_MODE

	.long	__und_usr			@  0 (USR_26 / USR_32)
	.long	__und_invalid			@  1 (FIQ_26 / FIQ_32)
	.long	__und_invalid			@  2 (IRQ_26 / IRQ_32)
	.long	__und_svc			@  3 (SVC_26 / SVC_32)
	.long	__und_invalid			@  4
	.long	__und_invalid			@  5
	.long	__und_invalid			@  6
	.long	__und_invalid			@  7
	.long	__und_invalid			@  8
	.long	__und_invalid			@  9
	.long	__und_invalid			@  a
	.long	__und_invalid			@  b
	.long	__und_invalid			@  c
	.long	__und_invalid			@  d
	.long	__und_invalid			@  e
	.long	__und_invalid			@  f

	.align	5

/*=============================================================================
 * Undefined FIQs
 *-----------------------------------------------------------------------------
 * Enter in FIQ mode, spsr = ANY CPSR, lr = ANY PC
 * MUST PRESERVE SVC SPSR, but need to switch to SVC mode to show our msg.
 * Basically to switch modes, we *HAVE* to clobber one register...  brain
 * damage alert!  I don't think that we can execute any code in here in any
 * other mode than FIQ...  Ok you can switch to another mode, but you can't
 * get out of that mode without clobbering one register.
 */
vector_fiq:
	disable_fiq
	subs	pc, lr, #4

/*=============================================================================
 * Address exception handler
 *-----------------------------------------------------------------------------
 * These aren't too critical.
 * (they're not supposed to happen, and won't happen in 32-bit data mode).
 */

vector_addrexcptn:
	b	vector_addrexcptn

/*
 * We group all the following data together to optimise
 * for CPUs with separate I & D caches.
 */
	.align	5

.LCvswi:
	.word	vector_swi

	.globl	__stubs_end
__stubs_end:

	.equ	stubs_offset, __vectors_start + 0x200 - __stubs_start

	.globl	__vectors_start
__vectors_start:
	swi	SYS_ERROR0
	b	vector_und + stubs_offset
	ldr	pc, .LCvswi + stubs_offset
	b	vector_pabt + stubs_offset
	b	vector_dabt + stubs_offset
	b	vector_addrexcptn + stubs_offset
	b	vector_irq + stubs_offset
	b	vector_fiq + stubs_offset

	.globl	__vectors_end
__vectors_end:

	.data

	.globl	cr_alignment
	.globl	cr_no_alignment
cr_alignment:
	.space	4
cr_no_alignment:
	.space	4