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/proc-sa110.S b/arch/arm/mm/proc-sa110.S
index c45319c..8008a04 100644
--- a/arch/arm/mm/proc-sa110.S
+++ b/arch/arm/mm/proc-sa110.S
@@ -38,7 +38,7 @@
ENTRY(cpu_sa110_proc_init)
mov r0, #0
mcr p15, 0, r0, c15, c1, 2 @ Enable clock switching
- mov pc, lr
+ ret lr
/*
* cpu_sa110_proc_fin()
@@ -50,7 +50,7 @@
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_sa110_reset(loc)
@@ -74,7 +74,7 @@
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_sa110_reset)
.popsection
@@ -103,7 +103,7 @@
mov r0, r0 @ safety
mov r0, r0 @ safety
mcr p15, 0, r0, c15, c1, 2 @ enable clock switching
- mov pc, lr
+ ret lr
/* ================================= CACHE ================================ */
@@ -121,7 +121,7 @@
add r0, r0, #DCACHELINESIZE
subs r1, r1, #DCACHELINESIZE
bhi 1b
- mov pc, lr
+ ret lr
/* =============================== PageTable ============================== */
@@ -141,7 +141,7 @@
mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs
ldr pc, [sp], #4
#else
- mov pc, lr
+ ret lr
#endif
/*
@@ -157,7 +157,7 @@
mcr p15, 0, r0, c7, c10, 1 @ clean D entry
mcr p15, 0, r0, c7, c10, 4 @ drain WB
#endif
- mov pc, lr
+ ret lr
.type __sa110_setup, #function
__sa110_setup:
@@ -173,7 +173,7 @@
mrc p15, 0, r0, c1, c0 @ get control register v4
bic r0, r0, r5
orr r0, r0, r6
- mov pc, lr
+ ret lr
.size __sa110_setup, . - __sa110_setup
/*