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-v6.S b/arch/arm/mm/cache-v6.S
index d8fd4d4..2465995 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -51,7 +51,7 @@
#else
mcr p15, 0, r0, c7, c5, 0 @ invalidate I-cache
#endif
- mov pc, lr
+ ret lr
ENDPROC(v6_flush_icache_all)
/*
@@ -73,7 +73,7 @@
#else
mcr p15, 0, r0, c7, c15, 0 @ Cache clean+invalidate
#endif
- mov pc, lr
+ ret lr
/*
* v6_flush_cache_all()
@@ -98,7 +98,7 @@
* - we have a VIPT cache.
*/
ENTRY(v6_flush_user_cache_range)
- mov pc, lr
+ ret lr
/*
* v6_coherent_kern_range(start,end)
@@ -150,7 +150,7 @@
#else
mcr p15, 0, r0, c7, c5, 6 @ invalidate BTB
#endif
- mov pc, lr
+ ret lr
/*
* Fault handling for the cache operation above. If the virtual address in r0
@@ -158,7 +158,7 @@
*/
9001:
mov r0, #-EFAULT
- mov pc, lr
+ ret lr
UNWIND(.fnend )
ENDPROC(v6_coherent_user_range)
ENDPROC(v6_coherent_kern_range)
@@ -188,7 +188,7 @@
mov r0, #0
mcr p15, 0, r0, c7, c10, 4
#endif
- mov pc, lr
+ ret lr
/*
@@ -239,7 +239,7 @@
blo 1b
mov r0, #0
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
- mov pc, lr
+ ret lr
/*
* v6_dma_clean_range(start,end)
@@ -262,7 +262,7 @@
blo 1b
mov r0, #0
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
- mov pc, lr
+ ret lr
/*
* v6_dma_flush_range(start,end)
@@ -290,7 +290,7 @@
blo 1b
mov r0, #0
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
- mov pc, lr
+ ret lr
/*
* dma_map_area(start, size, dir)
@@ -323,7 +323,7 @@
teq r2, #DMA_TO_DEVICE
bne v6_dma_inv_range
#endif
- mov pc, lr
+ ret lr
ENDPROC(v6_dma_unmap_area)
.globl v6_flush_kern_cache_louis