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/lib/div64.S b/arch/arm/lib/div64.S
index e55c484..a9eafe4 100644
--- a/arch/arm/lib/div64.S
+++ b/arch/arm/lib/div64.S
@@ -13,6 +13,7 @@
*/
#include <linux/linkage.h>
+#include <asm/assembler.h>
#include <asm/unwind.h>
#ifdef __ARMEB__
@@ -97,7 +98,7 @@
mov yl, #0
cmpeq xl, r4
movlo xh, xl
- movlo pc, lr
+ retlo lr
@ The division loop for lower bit positions.
@ Here we shift remainer bits leftwards rather than moving the
@@ -111,14 +112,14 @@
subcs xh, xh, r4
movs ip, ip, lsr #1
bne 4b
- mov pc, lr
+ ret lr
@ The top part of remainder became zero. If carry is set
@ (the 33th bit) this is a false positive so resume the loop.
@ Otherwise, if lower part is also null then we are done.
6: bcs 5b
cmp xl, #0
- moveq pc, lr
+ reteq lr
@ We still have remainer bits in the low part. Bring them up.
@@ -144,7 +145,7 @@
movs ip, ip, lsr #1
mov xh, #1
bne 4b
- mov pc, lr
+ ret lr
8: @ Division by a power of 2: determine what that divisor order is
@ then simply shift values around
@@ -184,13 +185,13 @@
THUMB( orr yl, yl, xh )
mov xh, xl, lsl ip
mov xh, xh, lsr ip
- mov pc, lr
+ ret lr
@ eq -> division by 1: obvious enough...
9: moveq yl, xl
moveq yh, xh
moveq xh, #0
- moveq pc, lr
+ reteq lr
UNWIND(.fnend)
UNWIND(.fnstart)
