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-arm1020.S b/arch/arm/mm/proc-arm1020.S
index d1a2d05971e0..86ee5d47ce3c 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -73,7 +73,7 @@
  * cpu_arm1020_proc_init()
  */
 ENTRY(cpu_arm1020_proc_init)
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_arm1020_proc_fin()
@@ -83,7 +83,7 @@ ENTRY(cpu_arm1020_proc_fin)
 	bic	r0, r0, #0x1000 		@ ...i............
 	bic	r0, r0, #0x000e 		@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_arm1020_reset(loc)
@@ -107,7 +107,7 @@ ENTRY(cpu_arm1020_reset)
 	bic	ip, ip, #0x000f 		@ ............wcam
 	bic	ip, ip, #0x1100 		@ ...i...s........
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
-	mov	pc, r0
+	ret	r0
 ENDPROC(cpu_arm1020_reset)
 	.popsection
 
@@ -117,7 +117,7 @@ ENDPROC(cpu_arm1020_reset)
 	.align	5
 ENTRY(cpu_arm1020_do_idle)
 	mcr	p15, 0, r0, c7, c0, 4		@ Wait for interrupt
-	mov	pc, lr
+	ret	lr
 
 /* ================================= CACHE ================================ */
 
@@ -133,7 +133,7 @@ ENTRY(arm1020_flush_icache_all)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 #endif
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm1020_flush_icache_all)
 
 /*
@@ -169,7 +169,7 @@ __flush_whole_cache:
 	mcrne	p15, 0, ip, c7, c5, 0		@ invalidate I cache
 #endif
 	mcrne	p15, 0, ip, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_user_cache_range(start, end, flags)
@@ -200,7 +200,7 @@ ENTRY(arm1020_flush_user_cache_range)
 	mcrne	p15, 0, ip, c7, c5, 0		@ invalidate I cache
 #endif
 	mcrne	p15, 0, ip, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	coherent_kern_range(start, end)
@@ -242,7 +242,7 @@ ENTRY(arm1020_coherent_user_range)
 	blo	1b
 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_kern_dcache_area(void *addr, size_t size)
@@ -264,7 +264,7 @@ ENTRY(arm1020_flush_kern_dcache_area)
 	blo	1b
 #endif
 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_inv_range(start, end)
@@ -297,7 +297,7 @@ arm1020_dma_inv_range:
 	blo	1b
 #endif
 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_clean_range(start, end)
@@ -320,7 +320,7 @@ arm1020_dma_clean_range:
 	blo	1b
 #endif
 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_flush_range(start, end)
@@ -342,7 +342,7 @@ ENTRY(arm1020_dma_flush_range)
 	blo	1b
 #endif
 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_map_area(start, size, dir)
@@ -365,7 +365,7 @@ ENDPROC(arm1020_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(arm1020_dma_unmap_area)
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm1020_dma_unmap_area)
 
 	.globl	arm1020_flush_kern_cache_louis
@@ -384,7 +384,7 @@ ENTRY(cpu_arm1020_dcache_clean_area)
 	subs	r1, r1, #CACHE_DLINESIZE
 	bhi	1b
 #endif
-	mov	pc, lr
+	ret	lr
 
 /* =============================== PageTable ============================== */
 
@@ -423,7 +423,7 @@ ENTRY(cpu_arm1020_switch_mm)
 	mcr	p15, 0, r0, c2, c0, 0		@ load page table pointer
 	mcr	p15, 0, r1, c8, c7, 0		@ invalidate I & D TLBs
 #endif /* CONFIG_MMU */
-	mov	pc, lr
+	ret	lr
         
 /*
  * cpu_arm1020_set_pte(ptep, pte)
@@ -441,7 +441,7 @@ ENTRY(cpu_arm1020_set_pte_ext)
 #endif
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 #endif /* CONFIG_MMU */
-	mov	pc, lr
+	ret	lr
 
 	.type	__arm1020_setup, #function
 __arm1020_setup:
@@ -460,7 +460,7 @@ __arm1020_setup:
 #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN
 	orr	r0, r0, #0x4000 		@ .R.. .... .... ....
 #endif
-	mov	pc, lr
+	ret	lr
 	.size	__arm1020_setup, . - __arm1020_setup
 
 	/*