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>

1 files changed, 17 insertions, 17 deletions

diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 549557df6d57..22bf8dde4f84 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -63,7 +63,7 @@
  * cpu_arm920_proc_init()
  */
 ENTRY(cpu_arm920_proc_init)
-        mov     pc, lr
+        ret     lr
 
 /*
  * cpu_arm920_proc_fin()
@@ -73,7 +73,7 @@ ENTRY(cpu_arm920_proc_fin)
         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_arm920_reset(loc)
@@ -97,7 +97,7 @@ ENTRY(cpu_arm920_reset)
         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_arm920_reset)
         .popsection
 
@@ -107,7 +107,7 @@ ENDPROC(cpu_arm920_reset)
         .align  5
 ENTRY(cpu_arm920_do_idle)
         mcr     p15, 0, r0, c7, c0, 4           @ Wait for interrupt
-        mov     pc, lr
+        ret     lr
 
 
 #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
@@ -120,7 +120,7 @@ ENTRY(cpu_arm920_do_idle)
 ENTRY(arm920_flush_icache_all)
         mov     r0, #0
         mcr     p15, 0, r0, c7, c5, 0           @ invalidate I cache
-        mov     pc, lr
+        ret     lr
 ENDPROC(arm920_flush_icache_all)
 
 /*
@@ -151,7 +151,7 @@ __flush_whole_cache:
         tst     r2, #VM_EXEC
         mcrne   p15, 0, ip, c7, c5, 0           @ invalidate I cache
         mcrne   p15, 0, ip, c7, c10, 4          @ drain WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      flush_user_cache_range(start, end, flags)
@@ -177,7 +177,7 @@ ENTRY(arm920_flush_user_cache_range)
         blo     1b
         tst     r2, #VM_EXEC
         mcrne   p15, 0, ip, c7, c10, 4          @ drain WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      coherent_kern_range(start, end)
@@ -211,7 +211,7 @@ ENTRY(arm920_coherent_user_range)
         blo     1b
         mcr     p15, 0, r0, c7, c10, 4          @ drain WB
         mov     r0, #0
-        mov     pc, lr
+        ret     lr
 
 /*
  *      flush_kern_dcache_area(void *addr, size_t size)
@@ -231,7 +231,7 @@ ENTRY(arm920_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 WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      dma_inv_range(start, end)
@@ -257,7 +257,7 @@ arm920_dma_inv_range:
         cmp     r0, r1
         blo     1b
         mcr     p15, 0, r0, c7, c10, 4          @ drain WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      dma_clean_range(start, end)
@@ -276,7 +276,7 @@ arm920_dma_clean_range:
         cmp     r0, r1
         blo     1b
         mcr     p15, 0, r0, c7, c10, 4          @ drain WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      dma_flush_range(start, end)
@@ -293,7 +293,7 @@ ENTRY(arm920_dma_flush_range)
         cmp     r0, r1
         blo     1b
         mcr     p15, 0, r0, c7, c10, 4          @ drain WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      dma_map_area(start, size, dir)
@@ -316,7 +316,7 @@ ENDPROC(arm920_dma_map_area)
  *      - dir   - DMA direction
  */
 ENTRY(arm920_dma_unmap_area)
-        mov     pc, lr
+        ret     lr
 ENDPROC(arm920_dma_unmap_area)
 
         .globl  arm920_flush_kern_cache_louis
@@ -332,7 +332,7 @@ ENTRY(cpu_arm920_dcache_clean_area)
         add     r0, r0, #CACHE_DLINESIZE
         subs    r1, r1, #CACHE_DLINESIZE
         bhi     1b
-        mov     pc, lr
+        ret     lr
 
 /* =============================== PageTable ============================== */
 
@@ -367,7 +367,7 @@ ENTRY(cpu_arm920_switch_mm)
         mcr     p15, 0, r0, c2, c0, 0           @ load page table pointer
         mcr     p15, 0, ip, c8, c7, 0           @ invalidate I & D TLBs
 #endif
-        mov     pc, lr
+        ret     lr
 
 /*
  * cpu_arm920_set_pte(ptep, pte, ext)
@@ -382,7 +382,7 @@ ENTRY(cpu_arm920_set_pte_ext)
         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
 
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl  cpu_arm920_suspend_size
@@ -423,7 +423,7 @@ __arm920_setup:
         mrc     p15, 0, r0, c1, c0              @ get control register v4
         bic     r0, r0, r5
         orr     r0, r0, r6
-        mov     pc, lr
+        ret     lr
         .size   __arm920_setup, . - __arm920_setup
 
         /*