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, 22 insertions, 22 deletions

diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index db79b62..03a1b75 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -69,7 +69,7 @@ ENTRY(cpu_feroceon_proc_init)
 	movne	r2, r2, lsr #2			@ turned into # of sets
 	sub	r2, r2, #(1 << 5)
 	stmia	r1, {r2, r3}
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_feroceon_proc_fin()
@@ -86,7 +86,7 @@ ENTRY(cpu_feroceon_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_feroceon_reset(loc)
@@ -110,7 +110,7 @@ ENTRY(cpu_feroceon_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_feroceon_reset)
 	.popsection
 
@@ -124,7 +124,7 @@ ENTRY(cpu_feroceon_do_idle)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c10, 4		@ Drain write buffer
 	mcr	p15, 0, r0, c7, c0, 4		@ Wait for interrupt
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_icache_all()
@@ -134,7 +134,7 @@ ENTRY(cpu_feroceon_do_idle)
 ENTRY(feroceon_flush_icache_all)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
-	mov	pc, lr
+	ret	lr
 ENDPROC(feroceon_flush_icache_all)
 
 /*
@@ -169,7 +169,7 @@ __flush_whole_cache:
 	mov	ip, #0
 	mcrne	p15, 0, ip, c7, c5, 0		@ invalidate I cache
 	mcrne	p15, 0, ip, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_user_cache_range(start, end, flags)
@@ -198,7 +198,7 @@ ENTRY(feroceon_flush_user_cache_range)
 	tst	r2, #VM_EXEC
 	mov	ip, #0
 	mcrne	p15, 0, ip, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	coherent_kern_range(start, end)
@@ -233,7 +233,7 @@ ENTRY(feroceon_coherent_user_range)
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_kern_dcache_area(void *addr, size_t size)
@@ -254,7 +254,7 @@ ENTRY(feroceon_flush_kern_dcache_area)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 	.align	5
 ENTRY(feroceon_range_flush_kern_dcache_area)
@@ -268,7 +268,7 @@ ENTRY(feroceon_range_flush_kern_dcache_area)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_inv_range(start, end)
@@ -295,7 +295,7 @@ feroceon_dma_inv_range:
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 	.align	5
 feroceon_range_dma_inv_range:
@@ -311,7 +311,7 @@ feroceon_range_dma_inv_range:
 	mcr	p15, 5, r0, c15, c14, 0		@ D inv range start
 	mcr	p15, 5, r1, c15, c14, 1		@ D inv range top
 	msr	cpsr_c, r2			@ restore interrupts
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_clean_range(start, end)
@@ -331,7 +331,7 @@ feroceon_dma_clean_range:
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 	.align	5
 feroceon_range_dma_clean_range:
@@ -344,7 +344,7 @@ feroceon_range_dma_clean_range:
 	mcr	p15, 5, r1, c15, c13, 1		@ D clean range top
 	msr	cpsr_c, r2			@ restore interrupts
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_flush_range(start, end)
@@ -362,7 +362,7 @@ ENTRY(feroceon_dma_flush_range)
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 	.align	5
 ENTRY(feroceon_range_dma_flush_range)
@@ -375,7 +375,7 @@ ENTRY(feroceon_range_dma_flush_range)
 	mcr	p15, 5, r1, c15, c15, 1		@ D clean/inv range top
 	msr	cpsr_c, r2			@ restore interrupts
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_map_area(start, size, dir)
@@ -412,7 +412,7 @@ ENDPROC(feroceon_range_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(feroceon_dma_unmap_area)
-	mov	pc, lr
+	ret	lr
 ENDPROC(feroceon_dma_unmap_area)
 
 	.globl	feroceon_flush_kern_cache_louis
@@ -461,7 +461,7 @@ ENTRY(cpu_feroceon_dcache_clean_area)
 	bhi	1b
 #endif
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /* =============================== PageTable ============================== */
 
@@ -490,9 +490,9 @@ ENTRY(cpu_feroceon_switch_mm)
 
 	mcr	p15, 0, r0, c2, c0, 0		@ load page table pointer
 	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I & D TLBs
-	mov	pc, r2
+	ret	r2
 #else
-	mov	pc, lr
+	ret	lr
 #endif
 
 /*
@@ -512,7 +512,7 @@ ENTRY(cpu_feroceon_set_pte_ext)
 #endif
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 #endif
-	mov	pc, lr
+	ret	lr
 
 /* Suspend/resume support: taken from arch/arm/mm/proc-arm926.S */
 .globl	cpu_feroceon_suspend_size
@@ -554,7 +554,7 @@ __feroceon_setup:
 	mrc	p15, 0, r0, c1, c0		@ get control register v4
 	bic	r0, r0, r5
 	orr	r0, r0, r6
-	mov	pc, lr
+	ret	lr
 	.size	__feroceon_setup, . - __feroceon_setup
 
 	/*