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>
diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S
index 11e5e58..a0982ce 100644
--- a/arch/arm/mm/cache-v4wt.S
+++ b/arch/arm/mm/cache-v4wt.S
@@ -13,6 +13,7 @@
*/
#include <linux/linkage.h>
#include <linux/init.h>
+#include <asm/assembler.h>
#include <asm/page.h>
#include "proc-macros.S"
@@ -48,7 +49,7 @@
ENTRY(v4wt_flush_icache_all)
mov r0, #0
mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache
- mov pc, lr
+ ret lr
ENDPROC(v4wt_flush_icache_all)
/*
@@ -71,7 +72,7 @@
tst r2, #VM_EXEC
mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache
mcr p15, 0, ip, c7, c6, 0 @ invalidate D cache
- mov pc, lr
+ ret lr
/*
* flush_user_cache_range(start, end, flags)
@@ -94,7 +95,7 @@
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
- mov pc, lr
+ ret lr
/*
* coherent_kern_range(start, end)
@@ -126,7 +127,7 @@
cmp r0, r1
blo 1b
mov r0, #0
- mov pc, lr
+ ret lr
/*
* flush_kern_dcache_area(void *addr, size_t size)
@@ -160,7 +161,7 @@
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
- mov pc, lr
+ ret lr
/*
* dma_flush_range(start, end)
@@ -192,7 +193,7 @@
* - dir - DMA direction
*/
ENTRY(v4wt_dma_map_area)
- mov pc, lr
+ ret lr
ENDPROC(v4wt_dma_unmap_area)
ENDPROC(v4wt_dma_map_area)
