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>

1 files changed, 17 insertions, 17 deletions

diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index d19b1cfcad91..23259f104c66 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -118,7 +118,7 @@ ENTRY(cpu_xscale_proc_init)
 	mrc	p15, 0, r1, c1, c0, 1
 	bic	r1, r1, #1
 	mcr	p15, 0, r1, c1, c0, 1
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_xscale_proc_fin()
@@ -128,7 +128,7 @@ ENTRY(cpu_xscale_proc_fin)
 	bic	r0, r0, #0x1800			@ ...IZ...........
 	bic	r0, r0, #0x0006			@ .............CA.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_xscale_reset(loc)
@@ -160,7 +160,7 @@ ENTRY(cpu_xscale_reset)
 	@ CAUTION: MMU turned off from this point. We count on the pipeline
 	@ already containing those two last instructions to survive.
 	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I & D TLBs
-	mov	pc, r0
+	ret	r0
 ENDPROC(cpu_xscale_reset)
 	.popsection
 
@@ -179,7 +179,7 @@ ENDPROC(cpu_xscale_reset)
 ENTRY(cpu_xscale_do_idle)
 	mov	r0, #1
 	mcr	p14, 0, r0, c7, c0, 0		@ Go to IDLE
-	mov	pc, lr
+	ret	lr
 
 /* ================================= CACHE ================================ */
 
@@ -191,7 +191,7 @@ ENTRY(cpu_xscale_do_idle)
 ENTRY(xscale_flush_icache_all)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
-	mov	pc, lr
+	ret	lr
 ENDPROC(xscale_flush_icache_all)
 
 /*
@@ -216,7 +216,7 @@ __flush_whole_cache:
 	tst	r2, #VM_EXEC
 	mcrne	p15, 0, ip, c7, c5, 0		@ Invalidate I cache & BTB
 	mcrne	p15, 0, ip, c7, c10, 4		@ Drain Write (& Fill) Buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_user_cache_range(start, end, vm_flags)
@@ -245,7 +245,7 @@ ENTRY(xscale_flush_user_cache_range)
 	tst	r2, #VM_EXEC
 	mcrne	p15, 0, ip, c7, c5, 6		@ Invalidate BTB
 	mcrne	p15, 0, ip, c7, c10, 4		@ Drain Write (& Fill) Buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	coherent_kern_range(start, end)
@@ -269,7 +269,7 @@ ENTRY(xscale_coherent_kern_range)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ Invalidate I cache & BTB
 	mcr	p15, 0, r0, c7, c10, 4		@ Drain Write (& Fill) Buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	coherent_user_range(start, end)
@@ -291,7 +291,7 @@ ENTRY(xscale_coherent_user_range)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 6		@ Invalidate BTB
 	mcr	p15, 0, r0, c7, c10, 4		@ Drain Write (& Fill) Buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_kern_dcache_area(void *addr, size_t size)
@@ -312,7 +312,7 @@ ENTRY(xscale_flush_kern_dcache_area)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ Invalidate I cache & BTB
 	mcr	p15, 0, r0, c7, c10, 4		@ Drain Write (& Fill) Buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_inv_range(start, end)
@@ -336,7 +336,7 @@ xscale_dma_inv_range:
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ Drain Write (& Fill) Buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_clean_range(start, end)
@@ -353,7 +353,7 @@ xscale_dma_clean_range:
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ Drain Write (& Fill) Buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_flush_range(start, end)
@@ -371,7 +371,7 @@ ENTRY(xscale_dma_flush_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ Drain Write (& Fill) Buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_map_area(start, size, dir)
@@ -407,7 +407,7 @@ ENDPROC(xscale_80200_A0_A1_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(xscale_dma_unmap_area)
-	mov	pc, lr
+	ret	lr
 ENDPROC(xscale_dma_unmap_area)
 
 	.globl	xscale_flush_kern_cache_louis
@@ -458,7 +458,7 @@ ENTRY(cpu_xscale_dcache_clean_area)
 	add	r0, r0, #CACHELINESIZE
 	subs	r1, r1, #CACHELINESIZE
 	bhi	1b
-	mov	pc, lr
+	ret	lr
 
 /* =============================== PageTable ============================== */
 
@@ -521,7 +521,7 @@ ENTRY(cpu_xscale_set_pte_ext)
 	orr	r2, r2, ip
 
 	xscale_set_pte_ext_epilogue
-	mov	pc, lr
+	ret	lr
 
 	.ltorg
 	.align
@@ -572,7 +572,7 @@ __xscale_setup:
 	mrc	p15, 0, r0, c1, c0, 0		@ get control register
 	bic	r0, r0, r5
 	orr	r0, r0, r6
-	mov	pc, lr
+	ret	lr
 	.size	__xscale_setup, . - __xscale_setup
 
 	/*