summaryrefslogtreecommitdiff
path: root/arch/arm/mm/cache-fa.S
diff options
context:
space:
mode:
authorRussell King <rmk+kernel@arm.linux.org.uk>2014-06-30 19:29:12 +0400
committerRussell King <rmk+kernel@arm.linux.org.uk>2014-07-18 15:29:04 +0400
commit6ebbf2ce437b33022d30badd49dc94d33ecfa498 (patch)
treebc015e35b456a28bb0e501803a454dc0c0d3291a /arch/arm/mm/cache-fa.S
parentaf040ffc9ba1e079ee4c0748aff64fa3d4716fa5 (diff)
downloadlinux-6ebbf2ce437b33022d30badd49dc94d33ecfa498.tar.xz
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>
Diffstat (limited to 'arch/arm/mm/cache-fa.S')
-rw-r--r--arch/arm/mm/cache-fa.S19
1 files changed, 10 insertions, 9 deletions
diff --git a/arch/arm/mm/cache-fa.S b/arch/arm/mm/cache-fa.S
index e505befe51b5..2f0c58836ae7 100644
--- a/arch/arm/mm/cache-fa.S
+++ b/arch/arm/mm/cache-fa.S
@@ -15,6 +15,7 @@
*/
#include <linux/linkage.h>
#include <linux/init.h>
+#include <asm/assembler.h>
#include <asm/memory.h>
#include <asm/page.h>
@@ -45,7 +46,7 @@
ENTRY(fa_flush_icache_all)
mov r0, #0
mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache
- mov pc, lr
+ ret lr
ENDPROC(fa_flush_icache_all)
/*
@@ -71,7 +72,7 @@ __flush_whole_cache:
mcrne p15, 0, ip, c7, c5, 6 @ invalidate BTB
mcrne p15, 0, ip, c7, c10, 4 @ drain write buffer
mcrne p15, 0, ip, c7, c5, 4 @ prefetch flush
- mov pc, lr
+ ret lr
/*
* flush_user_cache_range(start, end, flags)
@@ -99,7 +100,7 @@ ENTRY(fa_flush_user_cache_range)
mcrne p15, 0, ip, c7, c5, 6 @ invalidate BTB
mcrne p15, 0, ip, c7, c10, 4 @ data write barrier
mcrne p15, 0, ip, c7, c5, 4 @ prefetch flush
- mov pc, lr
+ ret lr
/*
* coherent_kern_range(start, end)
@@ -135,7 +136,7 @@ ENTRY(fa_coherent_user_range)
mcr p15, 0, r0, c7, c5, 6 @ invalidate BTB
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
mcr p15, 0, r0, c7, c5, 4 @ prefetch flush
- mov pc, lr
+ ret lr
/*
* flush_kern_dcache_area(void *addr, size_t size)
@@ -155,7 +156,7 @@ ENTRY(fa_flush_kern_dcache_area)
mov r0, #0
mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
- mov pc, lr
+ ret lr
/*
* dma_inv_range(start, end)
@@ -181,7 +182,7 @@ fa_dma_inv_range:
blo 1b
mov r0, #0
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
- mov pc, lr
+ ret lr
/*
* dma_clean_range(start, end)
@@ -199,7 +200,7 @@ fa_dma_clean_range:
blo 1b
mov r0, #0
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
- mov pc, lr
+ ret lr
/*
* dma_flush_range(start,end)
@@ -214,7 +215,7 @@ ENTRY(fa_dma_flush_range)
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)
@@ -237,7 +238,7 @@ ENDPROC(fa_dma_map_area)
* - dir - DMA direction
*/
ENTRY(fa_dma_unmap_area)
- mov pc, lr
+ ret lr
ENDPROC(fa_dma_unmap_area)
.globl fa_flush_kern_cache_louis