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>

2 files changed, 7 insertions, 6 deletions

diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S
index 510c29e079ca..f5d881b5d0f7 100644
--- a/arch/arm/mach-mvebu/coherency_ll.S
+++ b/arch/arm/mach-mvebu/coherency_ll.S
@@ -46,7 +46,7 @@ ENTRY(ll_get_coherency_base)
         ldr     r1, =coherency_base
         ldr     r1, [r1]
 2:
-        mov     pc, lr
+        ret     lr
 ENDPROC(ll_get_coherency_base)
 
 /*
@@ -63,7 +63,7 @@ ENTRY(ll_get_coherency_cpumask)
         mov     r2, #(1 << 24)
         lsl     r3, r2, r3
 ARM_BE8(rev     r3, r3)
-        mov     pc, lr
+        ret     lr
 ENDPROC(ll_get_coherency_cpumask)
 
 /*
@@ -94,7 +94,7 @@ ENTRY(ll_add_cpu_to_smp_group)
         strex   r1, r2, [r0]
         cmp     r1, #0
         bne     1b
-        mov     pc, lr
+        ret     lr
 ENDPROC(ll_add_cpu_to_smp_group)
 
 ENTRY(ll_enable_coherency)
@@ -118,7 +118,7 @@ ENTRY(ll_enable_coherency)
         bne     1b
         dsb
         mov     r0, #0
-        mov     pc, lr
+        ret     lr
 ENDPROC(ll_enable_coherency)
 
 ENTRY(ll_disable_coherency)
@@ -141,7 +141,7 @@ ENTRY(ll_disable_coherency)
         cmp     r1, #0
         bne     1b
         dsb
-        mov     pc, lr
+        ret     lr
 ENDPROC(ll_disable_coherency)
 
         .align 2
diff --git a/arch/arm/mach-mvebu/headsmp-a9.S b/arch/arm/mach-mvebu/headsmp-a9.S
index 5925366bc03c..7c91ddb6f1f7 100644
--- a/arch/arm/mach-mvebu/headsmp-a9.S
+++ b/arch/arm/mach-mvebu/headsmp-a9.S
@@ -14,6 +14,7 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <asm/assembler.h>
 
         __CPUINIT
 #define CPU_RESUME_ADDR_REG 0xf10182d4
@@ -24,7 +25,7 @@
 armada_375_smp_cpu1_enable_code_start:
         ldr     r0, [pc, #4]
         ldr     r1, [r0]
-        mov     pc, r1
+        ret     r1
         .word   CPU_RESUME_ADDR_REG
 armada_375_smp_cpu1_enable_code_end: