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, 9 insertions, 9 deletions

diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 1ca37c72f12f..d1e68b553d3b 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -16,11 +16,11 @@
 #include "proc-macros.S"
 
 ENTRY(cpu_v7m_proc_init)
-        mov     pc, lr
+        ret     lr
 ENDPROC(cpu_v7m_proc_init)
 
 ENTRY(cpu_v7m_proc_fin)
-        mov     pc, lr
+        ret     lr
 ENDPROC(cpu_v7m_proc_fin)
 
 /*
@@ -34,7 +34,7 @@ ENDPROC(cpu_v7m_proc_fin)
  */
         .align  5
 ENTRY(cpu_v7m_reset)
-        mov     pc, r0
+        ret     r0
 ENDPROC(cpu_v7m_reset)
 
 /*
@@ -46,18 +46,18 @@ ENDPROC(cpu_v7m_reset)
  */
 ENTRY(cpu_v7m_do_idle)
         wfi
-        mov     pc, lr
+        ret     lr
 ENDPROC(cpu_v7m_do_idle)
 
 ENTRY(cpu_v7m_dcache_clean_area)
-        mov     pc, lr
+        ret     lr
 ENDPROC(cpu_v7m_dcache_clean_area)
 
 /*
  * There is no MMU, so here is nothing to do.
  */
 ENTRY(cpu_v7m_switch_mm)
-        mov     pc, lr
+        ret     lr
 ENDPROC(cpu_v7m_switch_mm)
 
 .globl  cpu_v7m_suspend_size
@@ -65,11 +65,11 @@ ENDPROC(cpu_v7m_switch_mm)
 
 #ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v7m_do_suspend)
-        mov     pc, lr
+        ret     lr
 ENDPROC(cpu_v7m_do_suspend)
 
 ENTRY(cpu_v7m_do_resume)
-        mov     pc, lr
+        ret     lr
 ENDPROC(cpu_v7m_do_resume)
 #endif
 
@@ -120,7 +120,7 @@ __v7m_setup:
         ldr     r12, [r0, V7M_SCB_CCR]  @ system control register
         orr     r12, #V7M_SCB_CCR_STKALIGN
         str     r12, [r0, V7M_SCB_CCR]
-        mov     pc, lr
+        ret     lr
 ENDPROC(__v7m_setup)
 
         .align 2