ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+

ARMv6 and greater introduced a new instruction ("bx") which can be used
to return from function calls.  Recent CPUs perform better when the
"bx lr" instruction is used rather than the "mov pc, lr" instruction,
and this sequence is strongly recommended to be used by the ARM
architecture manual (section A.4.1.1).

We provide a new macro "ret" with all its variants for the condition
code which will resolve to the appropriate instruction.

Rather than doing this piecemeal, and miss some instances, change all
the "mov pc" instances to use the new macro, with the exception of
the "movs" instruction and the kprobes code.  This allows us to detect
the "mov pc, lr" case and fix it up - and also gives us the possibility
of deploying this for other registers depending on the CPU selection.

Reported-by: Will Deacon <will.deacon@arm.com>
Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1
Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S
Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood
Tested-by: Shawn Guo <shawn.guo@freescale.com>
Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs
Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385
Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci
Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp
Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen
Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M
Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

12 files changed, 63 insertions, 74 deletions

diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index 14f7c3b14632..78c91b5f97d4 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -90,7 +90,7 @@ ENTRY(printascii)
 		ldrneb	r1, [r0], #1
 		teqne	r1, #0
 		bne	1b
-		mov	pc, lr
+		ret	lr
 ENDPROC(printascii)
 
 ENTRY(printch)
@@ -105,7 +105,7 @@ ENTRY(debug_ll_addr)
 		addruart r2, r3, ip
 		str	r2, [r0]
 		str	r3, [r1]
-		mov	pc, lr
+		ret	lr
 ENDPROC(debug_ll_addr)
 #endif
 
@@ -116,7 +116,7 @@ ENTRY(printascii)
 		mov	r0, #0x04		@ SYS_WRITE0
 	ARM(	svc	#0x123456	)
 	THUMB(	svc	#0xab		)
-		mov	pc, lr
+		ret	lr
 ENDPROC(printascii)
 
 ENTRY(printch)
@@ -125,14 +125,14 @@ ENTRY(printch)
 		mov	r0, #0x03		@ SYS_WRITEC
 	ARM(	svc	#0x123456	)
 	THUMB(	svc	#0xab		)
-		mov	pc, lr
+		ret	lr
 ENDPROC(printch)
 
 ENTRY(debug_ll_addr)
 		mov	r2, #0
 		str	r2, [r0]
 		str	r2, [r1]
-		mov	pc, lr
+		ret	lr
 ENDPROC(debug_ll_addr)
 
 #endif
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 52a949a8077d..36276cdccfbc 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -224,7 +224,7 @@ svc_preempt:
 1:	bl	preempt_schedule_irq		@ irq en/disable is done inside
 	ldr	r0, [tsk, #TI_FLAGS]		@ get new tasks TI_FLAGS
 	tst	r0, #_TIF_NEED_RESCHED
-	moveq	pc, r8				@ go again
+	reteq	r8				@ go again
 	b	1b
 #endif
 
@@ -490,7 +490,7 @@ ENDPROC(__und_usr)
 	.pushsection .fixup, "ax"
 	.align	2
 4:	str     r4, [sp, #S_PC]			@ retry current instruction
-	mov	pc, r9
+	ret	r9
 	.popsection
 	.pushsection __ex_table,"a"
 	.long	1b, 4b
@@ -552,7 +552,7 @@ call_fpe:
 #endif
 	tst	r0, #0x08000000			@ only CDP/CPRT/LDC/STC have bit 27
 	tstne	r0, #0x04000000			@ bit 26 set on both ARM and Thumb-2
-	moveq	pc, lr
+	reteq	lr
 	and	r8, r0, #0x00000f00		@ mask out CP number
  THUMB(	lsr	r8, r8, #8		)
 	mov	r7, #1
@@ -571,33 +571,33 @@ call_fpe:
  THUMB(	add	pc, r8			)
 	nop
 
-	movw_pc	lr				@ CP#0
+	ret.w	lr				@ CP#0
 	W(b)	do_fpe				@ CP#1 (FPE)
 	W(b)	do_fpe				@ CP#2 (FPE)
-	movw_pc	lr				@ CP#3
+	ret.w	lr				@ CP#3
 #ifdef CONFIG_CRUNCH
 	b	crunch_task_enable		@ CP#4 (MaverickCrunch)
 	b	crunch_task_enable		@ CP#5 (MaverickCrunch)
 	b	crunch_task_enable		@ CP#6 (MaverickCrunch)
 #else
-	movw_pc	lr				@ CP#4
-	movw_pc	lr				@ CP#5
-	movw_pc	lr				@ CP#6
+	ret.w	lr				@ CP#4
+	ret.w	lr				@ CP#5
+	ret.w	lr				@ CP#6
 #endif
-	movw_pc	lr				@ CP#7
-	movw_pc	lr				@ CP#8
-	movw_pc	lr				@ CP#9
+	ret.w	lr				@ CP#7
+	ret.w	lr				@ CP#8
+	ret.w	lr				@ CP#9
 #ifdef CONFIG_VFP
 	W(b)	do_vfp				@ CP#10 (VFP)
 	W(b)	do_vfp				@ CP#11 (VFP)
 #else
-	movw_pc	lr				@ CP#10 (VFP)
-	movw_pc	lr				@ CP#11 (VFP)
+	ret.w	lr				@ CP#10 (VFP)
+	ret.w	lr				@ CP#11 (VFP)
 #endif
-	movw_pc	lr				@ CP#12
-	movw_pc	lr				@ CP#13
-	movw_pc	lr				@ CP#14 (Debug)
-	movw_pc	lr				@ CP#15 (Control)
+	ret.w	lr				@ CP#12
+	ret.w	lr				@ CP#13
+	ret.w	lr				@ CP#14 (Debug)
+	ret.w	lr				@ CP#15 (Control)
 
 #ifdef NEED_CPU_ARCHITECTURE
 	.align	2
@@ -649,7 +649,7 @@ ENTRY(fp_enter)
 	.popsection
 
 ENTRY(no_fp)
-	mov	pc, lr
+	ret	lr
 ENDPROC(no_fp)
 
 __und_usr_fault_32:
@@ -745,7 +745,7 @@ ENDPROC(__switch_to)
 #ifdef CONFIG_ARM_THUMB
 	bx	\reg
 #else
-	mov	pc, \reg
+	ret	\reg
 #endif
 	.endm
 
@@ -837,7 +837,7 @@ kuser_cmpxchg64_fixup:
 #if __LINUX_ARM_ARCH__ < 6
 	bcc	kuser_cmpxchg32_fixup
 #endif
-	mov	pc, lr
+	ret	lr
 	.previous
 
 #else
@@ -905,7 +905,7 @@ kuser_cmpxchg32_fixup:
 	subs	r8, r4, r7
 	rsbcss	r8, r8, #(2b - 1b)
 	strcs	r7, [sp, #S_PC]
-	mov	pc, lr
+	ret	lr
 	.previous
 
 #else
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 7139d4a7dea7..e52fe5a2d843 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -8,6 +8,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <asm/assembler.h>
 #include <asm/unistd.h>
 #include <asm/ftrace.h>
 #include <asm/unwind.h>
@@ -88,7 +89,7 @@ ENTRY(ret_from_fork)
 	cmp	r5, #0
 	movne	r0, r4
 	adrne	lr, BSYM(1f)
-	movne	pc, r5
+	retne	r5
 1:	get_thread_info tsk
 	b	ret_slow_syscall
 ENDPROC(ret_from_fork)
@@ -290,7 +291,7 @@ ENDPROC(ftrace_graph_caller_old)
 
 .macro mcount_exit
 	ldmia	sp!, {r0-r3, ip, lr}
-	mov	pc, ip
+	ret	ip
 .endm
 
 ENTRY(__gnu_mcount_nc)
@@ -298,7 +299,7 @@ UNWIND(.fnstart)
 #ifdef CONFIG_DYNAMIC_FTRACE
 	mov	ip, lr
 	ldmia	sp!, {lr}
-	mov	pc, ip
+	ret	ip
 #else
 	__mcount
 #endif
@@ -333,12 +334,12 @@ return_to_handler:
 	bl	ftrace_return_to_handler
 	mov	lr, r0			@ r0 has real ret addr
 	ldmia	sp!, {r0-r3}
-	mov	pc, lr
+	ret	lr
 #endif
 
 ENTRY(ftrace_stub)
 .Lftrace_stub:
-	mov	pc, lr
+	ret	lr
 ENDPROC(ftrace_stub)
 
 #endif /* CONFIG_FUNCTION_TRACER */
@@ -561,7 +562,7 @@ sys_mmap2:
 		streq	r5, [sp, #4]
 		beq	sys_mmap_pgoff
 		mov	r0, #-EINVAL
-		mov	pc, lr
+		ret	lr
 #else
 		str	r5, [sp, #4]
 		b	sys_mmap_pgoff
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 5d702f8900b1..8db307d0954b 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -240,12 +240,6 @@
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 	.endm
 
-	@
-	@ 32-bit wide "mov pc, reg"
-	@
-	.macro	movw_pc, reg
-	mov	pc, \reg
-	.endm
 #else	/* CONFIG_THUMB2_KERNEL */
 	.macro	svc_exit, rpsr, irq = 0
 	.if	\irq != 0
@@ -304,14 +298,6 @@
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 	.endm
 #endif	/* ifdef CONFIG_CPU_V7M / else */
-
-	@
-	@ 32-bit wide "mov pc, reg"
-	@
-	.macro	movw_pc, reg
-	mov	pc, \reg
-	nop
-	.endm
 #endif	/* !CONFIG_THUMB2_KERNEL */
 
 /*
diff --git a/arch/arm/kernel/fiqasm.S b/arch/arm/kernel/fiqasm.S
index 207f9d652010..8dd26e1a9bd6 100644
--- a/arch/arm/kernel/fiqasm.S
+++ b/arch/arm/kernel/fiqasm.S
@@ -32,7 +32,7 @@ ENTRY(__set_fiq_regs)
 	ldr	lr, [r0]
 	msr	cpsr_c, r1	@ return to SVC mode
 	mov	r0, r0		@ avoid hazard prior to ARMv4
-	mov	pc, lr
+	ret	lr
 ENDPROC(__set_fiq_regs)
 
 ENTRY(__get_fiq_regs)
@@ -45,5 +45,5 @@ ENTRY(__get_fiq_regs)
 	str	lr, [r0]
 	msr	cpsr_c, r1	@ return to SVC mode
 	mov	r0, r0		@ avoid hazard prior to ARMv4
-	mov	pc, lr
+	ret	lr
 ENDPROC(__get_fiq_regs)
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 572a38335c96..8733012d231f 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -10,6 +10,7 @@
  * published by the Free Software Foundation.
  *
  */
+#include <asm/assembler.h>
 
 #define ATAG_CORE 0x54410001
 #define ATAG_CORE_SIZE ((2*4 + 3*4) >> 2)
@@ -61,10 +62,10 @@ __vet_atags:
 	cmp	r5, r6
 	bne	1f
 
-2:	mov	pc, lr				@ atag/dtb pointer is ok
+2:	ret	lr				@ atag/dtb pointer is ok
 
 1:	mov	r2, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(__vet_atags)
 
 /*
@@ -162,7 +163,7 @@ __lookup_processor_type:
 	cmp	r5, r6
 	blo	1b
 	mov	r5, #0				@ unknown processor
-2:	mov	pc, lr
+2:	ret	lr
 ENDPROC(__lookup_processor_type)
 
 /*
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 716249cc2ee1..cc176b67c134 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -82,7 +82,7 @@ ENTRY(stext)
 	adr	lr, BSYM(1f)			@ return (PIC) address
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
- THUMB(	mov	pc, r12				)
+ THUMB(	ret	r12				)
  1:	b	__after_proc_init
 ENDPROC(stext)
 
@@ -119,7 +119,7 @@ ENTRY(secondary_startup)
 	mov	r13, r12			@ __secondary_switched address
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
- THUMB(	mov	pc, r12				)
+ THUMB(	ret	r12				)
 ENDPROC(secondary_startup)
 
 ENTRY(__secondary_switched)
@@ -164,7 +164,7 @@ __after_proc_init:
 #endif
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
 #endif /* CONFIG_CPU_CP15 */
-	mov	pc, r13
+	ret	r13
 ENDPROC(__after_proc_init)
 	.ltorg
 
@@ -254,7 +254,7 @@ ENTRY(__setup_mpu)
 	orr	r0, r0, #CR_M			@ Set SCTRL.M (MPU on)
 	mcr	p15, 0, r0, c1, c0, 0		@ Enable MPU
 	isb
-	mov pc,lr
+	ret	lr
 ENDPROC(__setup_mpu)
 #endif
 #include "head-common.S"
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 2c35f0ff2fdc..664eee8c4a26 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -140,7 +140,7 @@ ENTRY(stext)
 	mov	r8, r4				@ set TTBR1 to swapper_pg_dir
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
- THUMB(	mov	pc, r12				)
+ THUMB(	ret	r12				)
 1:	b	__enable_mmu
 ENDPROC(stext)
 	.ltorg
@@ -335,7 +335,7 @@ __create_page_tables:
 	sub	r4, r4, #0x1000		@ point to the PGD table
 	mov	r4, r4, lsr #ARCH_PGD_SHIFT
 #endif
-	mov	pc, lr
+	ret	lr
 ENDPROC(__create_page_tables)
 	.ltorg
 	.align
@@ -383,7 +383,7 @@ ENTRY(secondary_startup)
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	) @ initialise processor
 						  @ (return control reg)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
- THUMB(	mov	pc, r12				)
+ THUMB(	ret	r12				)
 ENDPROC(secondary_startup)
 
 	/*
@@ -468,7 +468,7 @@ ENTRY(__turn_mmu_on)
 	instr_sync
 	mov	r3, r3
 	mov	r3, r13
-	mov	pc, r3
+	ret	r3
 __turn_mmu_on_end:
 ENDPROC(__turn_mmu_on)
 	.popsection
@@ -487,7 +487,7 @@ __fixup_smp:
 	orr	r4, r4, #0x0000b000
 	orr	r4, r4, #0x00000020	@ val 0x4100b020
 	teq	r3, r4			@ ARM 11MPCore?
-	moveq	pc, lr			@ yes, assume SMP
+	reteq	lr			@ yes, assume SMP
 
 	mrc	p15, 0, r0, c0, c0, 5	@ read MPIDR
 	and	r0, r0, #0xc0000000	@ multiprocessing extensions and
@@ -500,7 +500,7 @@ __fixup_smp:
 	orr	r4, r4, #0x0000c000
 	orr	r4, r4, #0x00000090
 	teq	r3, r4			@ Check for ARM Cortex-A9
-	movne	pc, lr			@ Not ARM Cortex-A9,
+	retne	lr			@ Not ARM Cortex-A9,
 
 	@ If a future SoC *does* use 0x0 as the PERIPH_BASE, then the
 	@ below address check will need to be #ifdef'd or equivalent
@@ -512,7 +512,7 @@ __fixup_smp:
 ARM_BE8(rev	r0, r0)			@ byteswap if big endian
 	and	r0, r0, #0x3		@ number of CPUs
 	teq	r0, #0x0		@ is 1?
-	movne	pc, lr
+	retne	lr
 
 __fixup_smp_on_up:
 	adr	r0, 1f
@@ -539,7 +539,7 @@ smp_on_up:
 	.text
 __do_fixup_smp_on_up:
 	cmp	r4, r5
-	movhs	pc, lr
+	reths	lr
 	ldmia	r4!, {r0, r6}
  ARM(	str	r6, [r0, r3]	)
  THUMB(	add	r0, r0, r3	)
@@ -672,7 +672,7 @@ ARM_BE8(rev16	ip, ip)
 2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
 	bcc	1b
-	mov	pc, lr
+	ret	lr
 #endif
 ENDPROC(__fixup_a_pv_table)
 
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 797b1a6a4906..56ce6290c831 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -99,7 +99,7 @@ ENTRY(__hyp_stub_install_secondary)
 	 * immediately.
 	 */
 	compare_cpu_mode_with_primary	r4, r5, r6, r7
-	movne	pc, lr
+	retne	lr
 
 	/*
 	 * Once we have given up on one CPU, we do not try to install the
@@ -111,7 +111,7 @@ ENTRY(__hyp_stub_install_secondary)
 	 */
 
 	cmp	r4, #HYP_MODE
-	movne	pc, lr			@ give up if the CPU is not in HYP mode
+	retne	lr			@ give up if the CPU is not in HYP mode
 
 /*
  * Configure HSCTLR to set correct exception endianness/instruction set
@@ -201,7 +201,7 @@ ENDPROC(__hyp_get_vectors)
 	@ fall through
 ENTRY(__hyp_set_vectors)
 	__HVC(0)
-	mov	pc, lr
+	ret	lr
 ENDPROC(__hyp_set_vectors)
 
 #ifndef ZIMAGE
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index a5599cfc43cb..0960be7953f0 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -179,7 +179,7 @@ concan_load:
 	get_thread_info r10
 #endif
 4:	dec_preempt_count r10, r3
-	mov	pc, lr
+	ret	lr
 
 /*
  * Back up Concan regs to save area and disable access to them
@@ -265,7 +265,7 @@ ENTRY(iwmmxt_task_copy)
 	mov	r3, lr				@ preserve return address
 	bl	concan_dump
 	msr	cpsr_c, ip			@ restore interrupt mode
-	mov	pc, r3
+	ret	r3
 
 /*
  * Restore Concan state from given memory address
@@ -301,7 +301,7 @@ ENTRY(iwmmxt_task_restore)
 	mov	r3, lr				@ preserve return address
 	bl	concan_load
 	msr	cpsr_c, ip			@ restore interrupt mode
-	mov	pc, r3
+	ret	r3
 
 /*
  * Concan handling on task switch
@@ -323,7 +323,7 @@ ENTRY(iwmmxt_task_switch)
 	add	r3, r0, #TI_IWMMXT_STATE	@ get next task Concan save area
 	ldr	r2, [r2]			@ get current Concan owner
 	teq	r2, r3				@ next task owns it?
-	movne	pc, lr				@ no: leave Concan disabled
+	retne	lr				@ no: leave Concan disabled
 
 1:	@ flip Concan access
 	XSC(eor	r1, r1, #0x3)
@@ -350,7 +350,7 @@ ENTRY(iwmmxt_task_release)
 	eors	r0, r0, r1			@ if equal...
 	streq	r0, [r3]			@ then clear ownership
 	msr	cpsr_c, r2			@ restore interrupts
-	mov	pc, lr
+	ret	lr
 
 	.data
 concan_owner:
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index 95858966d84e..35e72585ec1d 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -3,6 +3,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/kexec.h>
 
 	.align	3	/* not needed for this code, but keeps fncpy() happy */
@@ -59,7 +60,7 @@ ENTRY(relocate_new_kernel)
 	mov r0,#0
 	ldr r1,kexec_mach_type
 	ldr r2,kexec_boot_atags
- ARM(	mov pc, lr	)
+ ARM(	ret lr	)
  THUMB(	bx lr		)
 
 	.align
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 1b880db2a033..e1e60e5a7a27 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -107,7 +107,7 @@ ENTRY(cpu_resume_mmu)
 	instr_sync
 	mov	r0, r0
 	mov	r0, r0
-	mov	pc, r3			@ jump to virtual address
+	ret	r3			@ jump to virtual address
 ENDPROC(cpu_resume_mmu)
 	.popsection
 cpu_resume_after_mmu: