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-arm1022.S b/arch/arm/mm/proc-arm1022.S
index 6f01a0ae3b30..a126b7a59928 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -62,7 +62,7 @@
  * cpu_arm1022_proc_init()
  */
 ENTRY(cpu_arm1022_proc_init)
-        mov     pc, lr
+        ret     lr
 
 /*
  * cpu_arm1022_proc_fin()
@@ -72,7 +72,7 @@ ENTRY(cpu_arm1022_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_arm1022_reset(loc)
@@ -96,7 +96,7 @@ ENTRY(cpu_arm1022_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_arm1022_reset)
         .popsection
 
@@ -106,7 +106,7 @@ ENDPROC(cpu_arm1022_reset)
         .align  5
 ENTRY(cpu_arm1022_do_idle)
         mcr     p15, 0, r0, c7, c0, 4           @ Wait for interrupt
-        mov     pc, lr
+        ret     lr
 
 /* ================================= CACHE ================================ */
 
@@ -122,7 +122,7 @@ ENTRY(arm1022_flush_icache_all)
         mov     r0, #0
         mcr     p15, 0, r0, c7, c5, 0           @ invalidate I cache
 #endif
-        mov     pc, lr
+        ret     lr
 ENDPROC(arm1022_flush_icache_all)
 
 /*
@@ -156,7 +156,7 @@ __flush_whole_cache:
         mcrne   p15, 0, ip, c7, c5, 0           @ invalidate I cache
 #endif
         mcrne   p15, 0, ip, c7, c10, 4          @ drain WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      flush_user_cache_range(start, end, flags)
@@ -185,7 +185,7 @@ ENTRY(arm1022_flush_user_cache_range)
         mcrne   p15, 0, ip, c7, c5, 0           @ invalidate I cache
 #endif
         mcrne   p15, 0, ip, c7, c10, 4          @ drain WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      coherent_kern_range(start, end)
@@ -225,7 +225,7 @@ ENTRY(arm1022_coherent_user_range)
         blo     1b
         mcr     p15, 0, ip, c7, c10, 4          @ drain WB
         mov     r0, #0
-        mov     pc, lr
+        ret     lr
 
 /*
  *      flush_kern_dcache_area(void *addr, size_t size)
@@ -246,7 +246,7 @@ ENTRY(arm1022_flush_kern_dcache_area)
         blo     1b
 #endif
         mcr     p15, 0, ip, c7, c10, 4          @ drain WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      dma_inv_range(start, end)
@@ -275,7 +275,7 @@ arm1022_dma_inv_range:
         blo     1b
 #endif
         mcr     p15, 0, ip, c7, c10, 4          @ drain WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      dma_clean_range(start, end)
@@ -297,7 +297,7 @@ arm1022_dma_clean_range:
         blo     1b
 #endif
         mcr     p15, 0, ip, c7, c10, 4          @ drain WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      dma_flush_range(start, end)
@@ -317,7 +317,7 @@ ENTRY(arm1022_dma_flush_range)
         blo     1b
 #endif
         mcr     p15, 0, ip, c7, c10, 4          @ drain WB
-        mov     pc, lr
+        ret     lr
 
 /*
  *      dma_map_area(start, size, dir)
@@ -340,7 +340,7 @@ ENDPROC(arm1022_dma_map_area)
  *      - dir   - DMA direction
  */
 ENTRY(arm1022_dma_unmap_area)
-        mov     pc, lr
+        ret     lr
 ENDPROC(arm1022_dma_unmap_area)
 
         .globl  arm1022_flush_kern_cache_louis
@@ -358,7 +358,7 @@ ENTRY(cpu_arm1022_dcache_clean_area)
         subs    r1, r1, #CACHE_DLINESIZE
         bhi     1b
 #endif
-        mov     pc, lr
+        ret     lr
 
 /* =============================== PageTable ============================== */
 
@@ -389,7 +389,7 @@ ENTRY(cpu_arm1022_switch_mm)
         mcr     p15, 0, r0, c2, c0, 0           @ load page table pointer
         mcr     p15, 0, r1, c8, c7, 0           @ invalidate I & D TLBs
 #endif
-        mov     pc, lr
+        ret     lr
         
 /*
  * cpu_arm1022_set_pte_ext(ptep, pte, ext)
@@ -405,7 +405,7 @@ ENTRY(cpu_arm1022_set_pte_ext)
         mcr     p15, 0, r0, c7, c10, 1          @ clean D entry
 #endif
 #endif /* CONFIG_MMU */
-        mov     pc, lr
+        ret     lr
 
         .type   __arm1022_setup, #function
 __arm1022_setup:
@@ -423,7 +423,7 @@ __arm1022_setup:
 #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN
         orr     r0, r0, #0x4000                 @ .R..............
 #endif
-        mov     pc, lr
+        ret     lr
         .size   __arm1022_setup, . - __arm1022_setup
 
         /*