diff mbox

ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+ (part1)

Message ID E1X20mL-00083I-Sv@rmk-PC.arm.linux.org.uk (mailing list archive)
State New, archived
Headers show

Commit Message

Russell King July 1, 2014, 4:19 p.m. UTC 
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.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
(Resent without the long Cc list)
(Resent with the patch cut in half - sorry, you're going to have to
join the two halves together to test it.)

 arch/arm/crypto/aes-armv4.S              |  3 ++-
 arch/arm/include/asm/assembler.h         | 21 +++++++++++++++
 arch/arm/include/asm/entry-macro-multi.S |  2 +-
 arch/arm/kernel/debug.S                  | 10 ++++----
 arch/arm/kernel/entry-armv.S             | 42 +++++++++++++++---------------
 arch/arm/kernel/entry-common.S           | 13 +++++-----
 arch/arm/kernel/entry-header.S           | 14 ----------
 arch/arm/kernel/fiqasm.S                 |  4 +--
 arch/arm/kernel/head-common.S            |  7 ++---
 arch/arm/kernel/head-nommu.S             |  8 +++---
 arch/arm/kernel/head.S                   | 18 ++++++-------
 arch/arm/kernel/hyp-stub.S               |  6 ++---
 arch/arm/kernel/iwmmxt.S                 | 10 ++++----
 arch/arm/kernel/relocate_kernel.S        |  3 ++-
 arch/arm/kernel/sleep.S                  |  2 +-
 arch/arm/kvm/init.S                      |  3 ++-
 arch/arm/lib/ashldi3.S                   |  3 ++-
 arch/arm/lib/ashrdi3.S                   |  3 ++-
 arch/arm/lib/backtrace.S                 |  2 +-
 arch/arm/lib/bitops.h                    |  5 ++--
 arch/arm/lib/bswapsdi2.S                 |  5 ++--
 arch/arm/lib/call_with_stack.S           |  4 +--
 arch/arm/lib/csumpartial.S               |  2 +-
 arch/arm/lib/csumpartialcopygeneric.S    |  5 ++--
 arch/arm/lib/delay-loop.S                | 18 ++++++-------
 arch/arm/lib/div64.S                     | 13 +++++-----
 arch/arm/lib/findbit.S                   | 10 ++++----
 arch/arm/lib/getuser.S                   |  8 +++---
 arch/arm/lib/io-readsb.S                 |  2 +-
 arch/arm/lib/io-readsl.S                 |  6 ++---
 arch/arm/lib/io-readsw-armv3.S           |  4 +--
 arch/arm/lib/io-readsw-armv4.S           |  2 +-
 arch/arm/lib/io-writesb.S                |  2 +-
 arch/arm/lib/io-writesl.S                | 10 ++++----
 arch/arm/lib/io-writesw-armv3.S          |  4 +--
 arch/arm/lib/io-writesw-armv4.S          |  4 +--
 arch/arm/lib/lib1funcs.S                 | 26 +++++++++----------
 arch/arm/lib/lshrdi3.S                   |  3 ++-
 arch/arm/lib/memchr.S                    |  2 +-
 arch/arm/lib/memset.S                    |  2 +-
 arch/arm/lib/memzero.S                   |  2 +-
 arch/arm/lib/muldi3.S                    |  3 ++-
 arch/arm/lib/putuser.S                   | 10 ++++----
 arch/arm/lib/strchr.S                    |  2 +-
 arch/arm/lib/strrchr.S                   |  2 +-
 arch/arm/lib/ucmpdi2.S                   |  5 ++--
 arch/arm/mach-davinci/sleep.S            |  2 +-
 arch/arm/mach-ep93xx/crunch-bits.S       |  6 ++---
 arch/arm/mach-imx/suspend-imx6.S         |  5 ++--
 arch/arm/mach-mvebu/coherency_ll.S       | 10 ++++----
 arch/arm/mach-mvebu/headsmp-a9.S         |  3 ++-
 arch/arm/mach-omap2/sleep44xx.S          |  3 ++-
 arch/arm/mach-omap2/sram242x.S           |  6 ++---
 arch/arm/mach-omap2/sram243x.S           |  6 ++---
 arch/arm/mach-pxa/mioa701_bootresume.S   |  2 +-
 arch/arm/mach-pxa/standby.S              |  4 +--
 arch/arm/mach-s3c24xx/sleep-s3c2410.S    |  2 +-
 arch/arm/mach-s3c24xx/sleep-s3c2412.S    |  2 +-
 arch/arm/mach-shmobile/headsmp.S         |  3 ++-
 arch/arm/mach-tegra/sleep-tegra20.S      | 24 ++++++++---------
 arch/arm/mach-tegra/sleep-tegra30.S      | 14 +++++-----
 arch/arm/mach-tegra/sleep.S              |  8 +++---
 arch/arm/mm/cache-fa.S                   | 19 +++++++-------
 arch/arm/mm/cache-nop.S                  |  5 ++--
 arch/arm/mm/cache-v4.S                   | 13 +++++-----
 arch/arm/mm/cache-v4wb.S                 | 15 ++++++-----
 arch/arm/mm/cache-v4wt.S                 | 13 +++++-----
 arch/arm/mm/cache-v6.S                   | 20 +++++++--------
 arch/arm/mm/cache-v7.S                   | 30 +++++++++++-----------
 arch/arm/mm/l2c-l2x0-resume.S            |  7 ++---
 arch/arm/mm/proc-arm1020.S               | 34 ++++++++++++------------
 arch/arm/mm/proc-arm1020e.S              | 34 ++++++++++++------------
 arch/arm/mm/proc-arm1022.S               | 34 ++++++++++++------------
 arch/arm/mm/proc-arm1026.S               | 34 ++++++++++++------------
 arch/arm/mm/proc-arm720.S                | 16 ++++++------
 arch/arm/mm/proc-arm740.S                |  8 +++---
 arch/arm/mm/proc-arm7tdmi.S              |  8 +++---
 arch/arm/mm/proc-arm920.S                | 34 ++++++++++++------------
 arch/arm/mm/proc-arm922.S                | 34 ++++++++++++------------
 arch/arm/mm/proc-arm925.S                | 34 ++++++++++++------------
 arch/arm/mm/proc-arm926.S                | 34 ++++++++++++------------
 arch/arm/mm/proc-arm940.S                | 24 ++++++++---------
 arch/arm/mm/proc-arm946.S                | 30 +++++++++++-----------
 arch/arm/mm/proc-arm9tdmi.S              |  8 +++---
 arch/arm/mm/proc-fa526.S                 | 16 ++++++------
 arch/arm/mm/proc-feroceon.S              | 44 ++++++++++++++++----------------
 arch/arm/mm/proc-mohawk.S                | 34 ++++++++++++------------
 arch/arm/mm/proc-sa110.S                 | 16 ++++++------
 arch/arm/mm/proc-sa1100.S                | 16 ++++++------
 arch/arm/mm/proc-v6.S                    | 16 ++++++------
 arch/arm/mm/proc-v7-2level.S             |  4 +--
 arch/arm/mm/proc-v7-3level.S             |  5 ++--
 arch/arm/mm/proc-v7.S                    | 14 +++++-----
 arch/arm/mm/proc-v7m.S                   | 18 ++++++-------
 arch/arm/mm/proc-xsc3.S                  | 32 +++++++++++------------
 arch/arm/mm/proc-xscale.S                | 34 ++++++++++++------------
 arch/arm/mm/tlb-fa.S                     |  7 ++---
 arch/arm/mm/tlb-v4.S                     |  5 ++--
 arch/arm/mm/tlb-v4wb.S                   |  7 ++---
 arch/arm/mm/tlb-v4wbi.S                  |  7 ++---
 arch/arm/mm/tlb-v6.S                     |  5 ++--
 arch/arm/mm/tlb-v7.S                     |  4 +--
 arch/arm/nwfpe/entry.S                   |  8 +++---
 arch/arm/vfp/entry.S                     |  4 +--
 arch/arm/vfp/vfphw.S                     | 26 +++++++++----------
 arch/arm/xen/hypercall.S                 |  6 ++---
 106 files changed, 644 insertions(+), 607 deletions(-)

diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index 0f098f407c9f..252b2503038d 100644
--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Måns Rullgård July 1, 2014, 4:42 p.m. UTC | #1 
Russell King <rmk+kernel@arm.linux.org.uk> writes:

> 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.

When the source register is not "lr" the name "ret" is a misnomer since
only the "bx lr" instruction is predicted as a function return.  The
"bx" instruction with other source registers uses the normal prediction
mechanisms, leaving the return stack alone, and should not be used for
function returns.  Any code currently using another register to return
from a function should probably be modified to use lr instead, unless
there are special reasons for doing otherwise.  If code jumping to an
address in a non-lr register is not a return, using the "ret" name will
make for some rather confusing reading.

I would suggest either using a more neutral name than "ret" or adding an
alias to be used for non-return jumps so as to make the intent clearer.
Russell King - ARM Linux July 1, 2014, 5:13 p.m. UTC | #2 
On Tue, Jul 01, 2014 at 05:42:42PM +0100, Måns Rullgård wrote:
> Russell King <rmk+kernel@arm.linux.org.uk> writes:
> 
> > 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.
> 
> When the source register is not "lr" the name "ret" is a misnomer since
> only the "bx lr" instruction is predicted as a function return.  The
> "bx" instruction with other source registers uses the normal prediction
> mechanisms, leaving the return stack alone, and should not be used for
> function returns.  Any code currently using another register to return
> from a function should probably be modified to use lr instead, unless
> there are special reasons for doing otherwise.  If code jumping to an
> address in a non-lr register is not a return, using the "ret" name will
> make for some rather confusing reading.
> 
> I would suggest either using a more neutral name than "ret" or adding an
> alias to be used for non-return jumps so as to make the intent clearer.

If you read the patch, the branches which are changed are those which
do indeed return in some way.  There are those which do this having
moved lr to a different register.

As you point out, "bx lr" /may/ be treated specially (I've actually been
discussing this with Will Deacon over the last couple of days, who has
also been talking to the hardware people in ARM, and Will is happy with
this patch as in its current form.)  This is why I've changed all
"mov pc, reg" instructions which return in some way to use this macro,
and left others (those which are used to call some function and return
back to the same point) alone.

I have thought about introducing a "call" macro for those other sites,
but as there are soo few of them, I've left them as-is for the time
being (this patch is already large enough.)

If there are any in the patch which you have specific concerns about,
please specifically point them out those which give you a concern.

Thanks.
Måns Rullgård July 1, 2014, 5:24 p.m. UTC | #3 
Russell King - ARM Linux <linux@arm.linux.org.uk> writes:

> On Tue, Jul 01, 2014 at 05:42:42PM +0100, Måns Rullgård wrote:
>> Russell King <rmk+kernel@arm.linux.org.uk> writes:
>> 
>> > 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.
>> 
>> When the source register is not "lr" the name "ret" is a misnomer since
>> only the "bx lr" instruction is predicted as a function return.  The
>> "bx" instruction with other source registers uses the normal prediction
>> mechanisms, leaving the return stack alone, and should not be used for
>> function returns.  Any code currently using another register to return
>> from a function should probably be modified to use lr instead, unless
>> there are special reasons for doing otherwise.  If code jumping to an
>> address in a non-lr register is not a return, using the "ret" name will
>> make for some rather confusing reading.
>> 
>> I would suggest either using a more neutral name than "ret" or adding an
>> alias to be used for non-return jumps so as to make the intent clearer.
>
> If you read the patch, the branches which are changed are those which
> do indeed return in some way.  There are those which do this having
> moved lr to a different register.

The patch is huge, and it wasn't obvious (to me) from the diff context
what the non-lr jumps were doing.

> As you point out, "bx lr" /may/ be treated specially (I've actually been

Most, if not all, Cortex-A cores do this according the public TRMs.
They also do the same thing for "mov pc, lr" so there will probably be
no performance gain from this change.  It's still a good idea though,
since we don't know what future cores will do.

> discussing this with Will Deacon over the last couple of days, who has
> also been talking to the hardware people in ARM, and Will is happy with
> this patch as in its current form.)  This is why I've changed all
> "mov pc, reg" instructions which return in some way to use this macro,
> and left others (those which are used to call some function and return
> back to the same point) alone.

In that case the patch should be fine.  Your patch description didn't
make it clear that only actual returns were being changed.
Will Deacon July 1, 2014, 5:35 p.m. UTC | #4 
Hi Mans,

On Tue, Jul 01, 2014 at 06:24:43PM +0100, Måns Rullgård wrote:
> Russell King - ARM Linux <linux@arm.linux.org.uk> writes:
> > As you point out, "bx lr" /may/ be treated specially (I've actually been
> 
> Most, if not all, Cortex-A cores do this according the public TRMs.
> They also do the same thing for "mov pc, lr" so there will probably be
> no performance gain from this change.  It's still a good idea though,
> since we don't know what future cores will do.

Funnily enough, that's not actually true (and is more or less what prompted
this patch after discussion with Russell). There are cores out there that
don't predict mov pc, lr at all (let alone do anything with the return
stack).

> > discussing this with Will Deacon over the last couple of days, who has
> > also been talking to the hardware people in ARM, and Will is happy with
> > this patch as in its current form.)  This is why I've changed all
> > "mov pc, reg" instructions which return in some way to use this macro,
> > and left others (those which are used to call some function and return
> > back to the same point) alone.
> 
> In that case the patch should be fine.  Your patch description didn't
> make it clear that only actual returns were being changed.

I'm led to believe that some predictors require lr in order to update the
return stack, whilst others don't. That part is all horribly
micro-architectural, so the current patch is doing the right thing by
sticking to the ARM ARM but enabling us to hook into other registers later
on if we choose.

Cheers,

Will
--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Stephen Warren July 1, 2014, 7:26 p.m. UTC | #5 
On 07/01/2014 10:19 AM, Russell King wrote:
> 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.

Tested-by: Stephen Warren <swarren@nvidia.com>

(On an NVIDIA Tegra Jetson TK1 board, both CPU hotplug and system sleep
were tested, which are the use-cases that actually use the edited
assembly files)
--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Måns Rullgård July 1, 2014, 8:04 p.m. UTC | #6 
Will Deacon <will.deacon@arm.com> writes:

> Hi Mans,
>
> On Tue, Jul 01, 2014 at 06:24:43PM +0100, Måns Rullgård wrote:
>> Russell King - ARM Linux <linux@arm.linux.org.uk> writes:
>> > As you point out, "bx lr" /may/ be treated specially (I've actually been
>> 
>> Most, if not all, Cortex-A cores do this according the public TRMs.
>> They also do the same thing for "mov pc, lr" so there will probably be
>> no performance gain from this change.  It's still a good idea though,
>> since we don't know what future cores will do.
>
> Funnily enough, that's not actually true (and is more or less what prompted
> this patch after discussion with Russell). There are cores out there that
> don't predict mov pc, lr at all (let alone do anything with the return
> stack).

Even ones where the TRM says they do?  I suppose the only way to know
for sure is to measure it.

>> > discussing this with Will Deacon over the last couple of days, who has
>> > also been talking to the hardware people in ARM, and Will is happy with
>> > this patch as in its current form.)  This is why I've changed all
>> > "mov pc, reg" instructions which return in some way to use this macro,
>> > and left others (those which are used to call some function and return
>> > back to the same point) alone.
>> 
>> In that case the patch should be fine.  Your patch description didn't
>> make it clear that only actual returns were being changed.
>
> I'm led to believe that some predictors require lr in order to update the
> return stack, whilst others don't. That part is all horribly
> micro-architectural, so the current patch is doing the right thing by
> sticking to the ARM ARM but enabling us to hook into other registers later
> on if we choose.

Agreed.
Robert Jarzmik July 1, 2014, 10:42 p.m. UTC | #7 
Russell King <rmk+kernel@arm.linux.org.uk> writes:

> 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).

For ARMv5 - XScale, and more specificaly the mioa701_bootresume.S path (suspend
to RAM) :
Tested-by: Robert Jarzmik <robert.jarzmik@free.fr>

Cheers.

--
Robert
--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Nicolas Pitre July 2, 2014, 3:17 a.m. UTC | #8 
On Tue, 1 Jul 2014, Will Deacon wrote:

> Hi Mans,
> 
> On Tue, Jul 01, 2014 at 06:24:43PM +0100, Måns Rullgård wrote:
> > Russell King - ARM Linux <linux@arm.linux.org.uk> writes:
> > > As you point out, "bx lr" /may/ be treated specially (I've actually been
> > 
> > Most, if not all, Cortex-A cores do this according the public TRMs.
> > They also do the same thing for "mov pc, lr" so there will probably be
> > no performance gain from this change.  It's still a good idea though,
> > since we don't know what future cores will do.
> 
> Funnily enough, that's not actually true (and is more or less what prompted
> this patch after discussion with Russell). There are cores out there that
> don't predict mov pc, lr at all (let alone do anything with the return
> stack).
> 
> > > discussing this with Will Deacon over the last couple of days, who has
> > > also been talking to the hardware people in ARM, and Will is happy with
> > > this patch as in its current form.)  This is why I've changed all
> > > "mov pc, reg" instructions which return in some way to use this macro,
> > > and left others (those which are used to call some function and return
> > > back to the same point) alone.
> > 
> > In that case the patch should be fine.  Your patch description didn't
> > make it clear that only actual returns were being changed.
> 
> I'm led to believe that some predictors require lr in order to update the
> return stack, whilst others don't. That part is all horribly
> micro-architectural, so the current patch is doing the right thing by
> sticking to the ARM ARM but enabling us to hook into other registers later
> on if we choose.

May I suggest to have a patch with only the macro definition in it and 
all this discussion in the commit log please?  The usage sites should be 
done in a separate patch to make it clearer.


Nicolas
Tomasz Figa July 5, 2014, 1:06 a.m. UTC | #9 
Hi Russell,

On 01.07.2014 18:19, Russell King wrote:
> 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.
> 
> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

Build- and boot-tested on mach-s3c64xx.

Tested-by: Tomasz Figa <tomasz.figa@gmail.com>

Best regards,
Tomasz
--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/arch/arm/crypto/aes-armv4.S b/arch/arm/crypto/aes-armv4.S
index 3a14ea8fe97e..ebb9761fb572 100644
--- a/arch/arm/crypto/aes-armv4.S
+++ b/arch/arm/crypto/aes-armv4.S
@@ -35,6 +35,7 @@ 
 @ that is being targetted.
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 .text
 
@@ -648,7 +649,7 @@  _armv4_AES_set_encrypt_key:
 
 .Ldone:	mov	r0,#0
 	ldmia   sp!,{r4-r12,lr}
-.Labrt:	mov	pc,lr
+.Labrt:	ret	lr
 ENDPROC(private_AES_set_encrypt_key)
 
 .align	5
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 906703a5b564..f67fd3afebdf 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -427,4 +427,25 @@  THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
+	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
+	.macro	ret\c, reg
+#if __LINUX_ARM_ARCH__ < 6
+	mov\c	pc, \reg
+#else
+	.ifeqs	"\reg", "lr"
+	bx\c	\reg
+	.else
+	mov\c	pc, \reg
+	.endif
+#endif
+	.endm
+	.endr
+
+	.macro	ret.w, reg
+	ret	\reg
+#ifdef CONFIG_THUMB2_KERNEL
+	nop
+#endif
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S
index 88d61815f0c0..469a2b30fa27 100644
--- a/arch/arm/include/asm/entry-macro-multi.S
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -35,5 +35,5 @@ 
 \symbol_name:
 	mov	r8, lr
 	arch_irq_handler_default
-	mov     pc, r8
+	ret	r8
 	.endm
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index 14f7c3b14632..78c91b5f97d4 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -90,7 +90,7 @@  ENTRY(printascii)
 		ldrneb	r1, [r0], #1
 		teqne	r1, #0
 		bne	1b
-		mov	pc, lr
+		ret	lr
 ENDPROC(printascii)
 
 ENTRY(printch)
@@ -105,7 +105,7 @@  ENTRY(debug_ll_addr)
 		addruart r2, r3, ip
 		str	r2, [r0]
 		str	r3, [r1]
-		mov	pc, lr
+		ret	lr
 ENDPROC(debug_ll_addr)
 #endif
 
@@ -116,7 +116,7 @@  ENTRY(printascii)
 		mov	r0, #0x04		@ SYS_WRITE0
 	ARM(	svc	#0x123456	)
 	THUMB(	svc	#0xab		)
-		mov	pc, lr
+		ret	lr
 ENDPROC(printascii)
 
 ENTRY(printch)
@@ -125,14 +125,14 @@  ENTRY(printch)
 		mov	r0, #0x03		@ SYS_WRITEC
 	ARM(	svc	#0x123456	)
 	THUMB(	svc	#0xab		)
-		mov	pc, lr
+		ret	lr
 ENDPROC(printch)
 
 ENTRY(debug_ll_addr)
 		mov	r2, #0
 		str	r2, [r0]
 		str	r2, [r1]
-		mov	pc, lr
+		ret	lr
 ENDPROC(debug_ll_addr)
 
 #endif
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 52a949a8077d..36276cdccfbc 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -224,7 +224,7 @@  svc_preempt:
 1:	bl	preempt_schedule_irq		@ irq en/disable is done inside
 	ldr	r0, [tsk, #TI_FLAGS]		@ get new tasks TI_FLAGS
 	tst	r0, #_TIF_NEED_RESCHED
-	moveq	pc, r8				@ go again
+	reteq	r8				@ go again
 	b	1b
 #endif
 
@@ -490,7 +490,7 @@  ENDPROC(__und_usr)
 	.pushsection .fixup, "ax"
 	.align	2
 4:	str     r4, [sp, #S_PC]			@ retry current instruction
-	mov	pc, r9
+	ret	r9
 	.popsection
 	.pushsection __ex_table,"a"
 	.long	1b, 4b
@@ -552,7 +552,7 @@  call_fpe:
 #endif
 	tst	r0, #0x08000000			@ only CDP/CPRT/LDC/STC have bit 27
 	tstne	r0, #0x04000000			@ bit 26 set on both ARM and Thumb-2
-	moveq	pc, lr
+	reteq	lr
 	and	r8, r0, #0x00000f00		@ mask out CP number
  THUMB(	lsr	r8, r8, #8		)
 	mov	r7, #1
@@ -571,33 +571,33 @@  call_fpe:
  THUMB(	add	pc, r8			)
 	nop
 
-	movw_pc	lr				@ CP#0
+	ret.w	lr				@ CP#0
 	W(b)	do_fpe				@ CP#1 (FPE)
 	W(b)	do_fpe				@ CP#2 (FPE)
-	movw_pc	lr				@ CP#3
+	ret.w	lr				@ CP#3
 #ifdef CONFIG_CRUNCH
 	b	crunch_task_enable		@ CP#4 (MaverickCrunch)
 	b	crunch_task_enable		@ CP#5 (MaverickCrunch)
 	b	crunch_task_enable		@ CP#6 (MaverickCrunch)
 #else
-	movw_pc	lr				@ CP#4
-	movw_pc	lr				@ CP#5
-	movw_pc	lr				@ CP#6
+	ret.w	lr				@ CP#4
+	ret.w	lr				@ CP#5
+	ret.w	lr				@ CP#6
 #endif
-	movw_pc	lr				@ CP#7
-	movw_pc	lr				@ CP#8
-	movw_pc	lr				@ CP#9
+	ret.w	lr				@ CP#7
+	ret.w	lr				@ CP#8
+	ret.w	lr				@ CP#9
 #ifdef CONFIG_VFP
 	W(b)	do_vfp				@ CP#10 (VFP)
 	W(b)	do_vfp				@ CP#11 (VFP)
 #else
-	movw_pc	lr				@ CP#10 (VFP)
-	movw_pc	lr				@ CP#11 (VFP)
+	ret.w	lr				@ CP#10 (VFP)
+	ret.w	lr				@ CP#11 (VFP)
 #endif
-	movw_pc	lr				@ CP#12
-	movw_pc	lr				@ CP#13
-	movw_pc	lr				@ CP#14 (Debug)
-	movw_pc	lr				@ CP#15 (Control)
+	ret.w	lr				@ CP#12
+	ret.w	lr				@ CP#13
+	ret.w	lr				@ CP#14 (Debug)
+	ret.w	lr				@ CP#15 (Control)
 
 #ifdef NEED_CPU_ARCHITECTURE
 	.align	2
@@ -649,7 +649,7 @@  ENTRY(fp_enter)
 	.popsection
 
 ENTRY(no_fp)
-	mov	pc, lr
+	ret	lr
 ENDPROC(no_fp)
 
 __und_usr_fault_32:
@@ -745,7 +745,7 @@  ENDPROC(__switch_to)
 #ifdef CONFIG_ARM_THUMB
 	bx	\reg
 #else
-	mov	pc, \reg
+	ret	\reg
 #endif
 	.endm
 
@@ -837,7 +837,7 @@  kuser_cmpxchg64_fixup:
 #if __LINUX_ARM_ARCH__ < 6
 	bcc	kuser_cmpxchg32_fixup
 #endif
-	mov	pc, lr
+	ret	lr
 	.previous
 
 #else
@@ -905,7 +905,7 @@  kuser_cmpxchg32_fixup:
 	subs	r8, r4, r7
 	rsbcss	r8, r8, #(2b - 1b)
 	strcs	r7, [sp, #S_PC]
-	mov	pc, lr
+	ret	lr
 	.previous
 
 #else
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 7139d4a7dea7..e52fe5a2d843 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -8,6 +8,7 @@ 
  * published by the Free Software Foundation.
  */
 
+#include <asm/assembler.h>
 #include <asm/unistd.h>
 #include <asm/ftrace.h>
 #include <asm/unwind.h>
@@ -88,7 +89,7 @@  ENTRY(ret_from_fork)
 	cmp	r5, #0
 	movne	r0, r4
 	adrne	lr, BSYM(1f)
-	movne	pc, r5
+	retne	r5
 1:	get_thread_info tsk
 	b	ret_slow_syscall
 ENDPROC(ret_from_fork)
@@ -290,7 +291,7 @@  ENDPROC(ftrace_graph_caller_old)
 
 .macro mcount_exit
 	ldmia	sp!, {r0-r3, ip, lr}
-	mov	pc, ip
+	ret	ip
 .endm
 
 ENTRY(__gnu_mcount_nc)
@@ -298,7 +299,7 @@  UNWIND(.fnstart)
 #ifdef CONFIG_DYNAMIC_FTRACE
 	mov	ip, lr
 	ldmia	sp!, {lr}
-	mov	pc, ip
+	ret	ip
 #else
 	__mcount
 #endif
@@ -333,12 +334,12 @@  return_to_handler:
 	bl	ftrace_return_to_handler
 	mov	lr, r0			@ r0 has real ret addr
 	ldmia	sp!, {r0-r3}
-	mov	pc, lr
+	ret	lr
 #endif
 
 ENTRY(ftrace_stub)
 .Lftrace_stub:
-	mov	pc, lr
+	ret	lr
 ENDPROC(ftrace_stub)
 
 #endif /* CONFIG_FUNCTION_TRACER */
@@ -561,7 +562,7 @@  sys_mmap2:
 		streq	r5, [sp, #4]
 		beq	sys_mmap_pgoff
 		mov	r0, #-EINVAL
-		mov	pc, lr
+		ret	lr
 #else
 		str	r5, [sp, #4]
 		b	sys_mmap_pgoff
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 5d702f8900b1..8db307d0954b 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -240,12 +240,6 @@ 
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 	.endm
 
-	@
-	@ 32-bit wide "mov pc, reg"
-	@
-	.macro	movw_pc, reg
-	mov	pc, \reg
-	.endm
 #else	/* CONFIG_THUMB2_KERNEL */
 	.macro	svc_exit, rpsr, irq = 0
 	.if	\irq != 0
@@ -304,14 +298,6 @@ 
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 	.endm
 #endif	/* ifdef CONFIG_CPU_V7M / else */
-
-	@
-	@ 32-bit wide "mov pc, reg"
-	@
-	.macro	movw_pc, reg
-	mov	pc, \reg
-	nop
-	.endm
 #endif	/* !CONFIG_THUMB2_KERNEL */
 
 /*
diff --git a/arch/arm/kernel/fiqasm.S b/arch/arm/kernel/fiqasm.S
index 207f9d652010..8dd26e1a9bd6 100644
--- a/arch/arm/kernel/fiqasm.S
+++ b/arch/arm/kernel/fiqasm.S
@@ -32,7 +32,7 @@  ENTRY(__set_fiq_regs)
 	ldr	lr, [r0]
 	msr	cpsr_c, r1	@ return to SVC mode
 	mov	r0, r0		@ avoid hazard prior to ARMv4
-	mov	pc, lr
+	ret	lr
 ENDPROC(__set_fiq_regs)
 
 ENTRY(__get_fiq_regs)
@@ -45,5 +45,5 @@  ENTRY(__get_fiq_regs)
 	str	lr, [r0]
 	msr	cpsr_c, r1	@ return to SVC mode
 	mov	r0, r0		@ avoid hazard prior to ARMv4
-	mov	pc, lr
+	ret	lr
 ENDPROC(__get_fiq_regs)
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 572a38335c96..8733012d231f 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -10,6 +10,7 @@ 
  * published by the Free Software Foundation.
  *
  */
+#include <asm/assembler.h>
 
 #define ATAG_CORE 0x54410001
 #define ATAG_CORE_SIZE ((2*4 + 3*4) >> 2)
@@ -61,10 +62,10 @@  __vet_atags:
 	cmp	r5, r6
 	bne	1f
 
-2:	mov	pc, lr				@ atag/dtb pointer is ok
+2:	ret	lr				@ atag/dtb pointer is ok
 
 1:	mov	r2, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(__vet_atags)
 
 /*
@@ -162,7 +163,7 @@  __lookup_processor_type:
 	cmp	r5, r6
 	blo	1b
 	mov	r5, #0				@ unknown processor
-2:	mov	pc, lr
+2:	ret	lr
 ENDPROC(__lookup_processor_type)
 
 /*
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 716249cc2ee1..cc176b67c134 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -82,7 +82,7 @@  ENTRY(stext)
 	adr	lr, BSYM(1f)			@ return (PIC) address
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
- THUMB(	mov	pc, r12				)
+ THUMB(	ret	r12				)
  1:	b	__after_proc_init
 ENDPROC(stext)
 
@@ -119,7 +119,7 @@  ENTRY(secondary_startup)
 	mov	r13, r12			@ __secondary_switched address
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
- THUMB(	mov	pc, r12				)
+ THUMB(	ret	r12				)
 ENDPROC(secondary_startup)
 
 ENTRY(__secondary_switched)
@@ -164,7 +164,7 @@  __after_proc_init:
 #endif
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
 #endif /* CONFIG_CPU_CP15 */
-	mov	pc, r13
+	ret	r13
 ENDPROC(__after_proc_init)
 	.ltorg
 
@@ -254,7 +254,7 @@  ENTRY(__setup_mpu)
 	orr	r0, r0, #CR_M			@ Set SCTRL.M (MPU on)
 	mcr	p15, 0, r0, c1, c0, 0		@ Enable MPU
 	isb
-	mov pc,lr
+	ret	lr
 ENDPROC(__setup_mpu)
 #endif
 #include "head-common.S"
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 2c35f0ff2fdc..664eee8c4a26 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -140,7 +140,7 @@  ENTRY(stext)
 	mov	r8, r4				@ set TTBR1 to swapper_pg_dir
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
- THUMB(	mov	pc, r12				)
+ THUMB(	ret	r12				)
 1:	b	__enable_mmu
 ENDPROC(stext)
 	.ltorg
@@ -335,7 +335,7 @@  __create_page_tables:
 	sub	r4, r4, #0x1000		@ point to the PGD table
 	mov	r4, r4, lsr #ARCH_PGD_SHIFT
 #endif
-	mov	pc, lr
+	ret	lr
 ENDPROC(__create_page_tables)
 	.ltorg
 	.align
@@ -383,7 +383,7 @@  ENTRY(secondary_startup)
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	) @ initialise processor
 						  @ (return control reg)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
- THUMB(	mov	pc, r12				)
+ THUMB(	ret	r12				)
 ENDPROC(secondary_startup)
 
 	/*
@@ -468,7 +468,7 @@  ENTRY(__turn_mmu_on)
 	instr_sync
 	mov	r3, r3
 	mov	r3, r13
-	mov	pc, r3
+	ret	r3
 __turn_mmu_on_end:
 ENDPROC(__turn_mmu_on)
 	.popsection
@@ -487,7 +487,7 @@  __fixup_smp:
 	orr	r4, r4, #0x0000b000
 	orr	r4, r4, #0x00000020	@ val 0x4100b020
 	teq	r3, r4			@ ARM 11MPCore?
-	moveq	pc, lr			@ yes, assume SMP
+	reteq	lr			@ yes, assume SMP
 
 	mrc	p15, 0, r0, c0, c0, 5	@ read MPIDR
 	and	r0, r0, #0xc0000000	@ multiprocessing extensions and
@@ -500,7 +500,7 @@  __fixup_smp:
 	orr	r4, r4, #0x0000c000
 	orr	r4, r4, #0x00000090
 	teq	r3, r4			@ Check for ARM Cortex-A9
-	movne	pc, lr			@ Not ARM Cortex-A9,
+	retne	lr			@ Not ARM Cortex-A9,
 
 	@ If a future SoC *does* use 0x0 as the PERIPH_BASE, then the
 	@ below address check will need to be #ifdef'd or equivalent
@@ -512,7 +512,7 @@  __fixup_smp:
 ARM_BE8(rev	r0, r0)			@ byteswap if big endian
 	and	r0, r0, #0x3		@ number of CPUs
 	teq	r0, #0x0		@ is 1?
-	movne	pc, lr
+	retne	lr
 
 __fixup_smp_on_up:
 	adr	r0, 1f
@@ -539,7 +539,7 @@  smp_on_up:
 	.text
 __do_fixup_smp_on_up:
 	cmp	r4, r5
-	movhs	pc, lr
+	reths	lr
 	ldmia	r4!, {r0, r6}
  ARM(	str	r6, [r0, r3]	)
  THUMB(	add	r0, r0, r3	)
@@ -672,7 +672,7 @@  ARM_BE8(rev16	ip, ip)
 2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
 	bcc	1b
-	mov	pc, lr
+	ret	lr
 #endif
 ENDPROC(__fixup_a_pv_table)
 
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 797b1a6a4906..56ce6290c831 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -99,7 +99,7 @@  ENTRY(__hyp_stub_install_secondary)
 	 * immediately.
 	 */
 	compare_cpu_mode_with_primary	r4, r5, r6, r7
-	movne	pc, lr
+	retne	lr
 
 	/*
 	 * Once we have given up on one CPU, we do not try to install the
@@ -111,7 +111,7 @@  ENTRY(__hyp_stub_install_secondary)
 	 */
 
 	cmp	r4, #HYP_MODE
-	movne	pc, lr			@ give up if the CPU is not in HYP mode
+	retne	lr			@ give up if the CPU is not in HYP mode
 
 /*
  * Configure HSCTLR to set correct exception endianness/instruction set
@@ -201,7 +201,7 @@  ENDPROC(__hyp_get_vectors)
 	@ fall through
 ENTRY(__hyp_set_vectors)
 	__HVC(0)
-	mov	pc, lr
+	ret	lr
 ENDPROC(__hyp_set_vectors)
 
 #ifndef ZIMAGE
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index a5599cfc43cb..0960be7953f0 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -179,7 +179,7 @@  concan_load:
 	get_thread_info r10
 #endif
 4:	dec_preempt_count r10, r3
-	mov	pc, lr
+	ret	lr
 
 /*
  * Back up Concan regs to save area and disable access to them
@@ -265,7 +265,7 @@  ENTRY(iwmmxt_task_copy)
 	mov	r3, lr				@ preserve return address
 	bl	concan_dump
 	msr	cpsr_c, ip			@ restore interrupt mode
-	mov	pc, r3
+	ret	r3
 
 /*
  * Restore Concan state from given memory address
@@ -301,7 +301,7 @@  ENTRY(iwmmxt_task_restore)
 	mov	r3, lr				@ preserve return address
 	bl	concan_load
 	msr	cpsr_c, ip			@ restore interrupt mode
-	mov	pc, r3
+	ret	r3
 
 /*
  * Concan handling on task switch
@@ -323,7 +323,7 @@  ENTRY(iwmmxt_task_switch)
 	add	r3, r0, #TI_IWMMXT_STATE	@ get next task Concan save area
 	ldr	r2, [r2]			@ get current Concan owner
 	teq	r2, r3				@ next task owns it?
-	movne	pc, lr				@ no: leave Concan disabled
+	retne	lr				@ no: leave Concan disabled
 
 1:	@ flip Concan access
 	XSC(eor	r1, r1, #0x3)
@@ -350,7 +350,7 @@  ENTRY(iwmmxt_task_release)
 	eors	r0, r0, r1			@ if equal...
 	streq	r0, [r3]			@ then clear ownership
 	msr	cpsr_c, r2			@ restore interrupts
-	mov	pc, lr
+	ret	lr
 
 	.data
 concan_owner:
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index 95858966d84e..35e72585ec1d 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -3,6 +3,7 @@ 
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/kexec.h>
 
 	.align	3	/* not needed for this code, but keeps fncpy() happy */
@@ -59,7 +60,7 @@  ENTRY(relocate_new_kernel)
 	mov r0,#0
 	ldr r1,kexec_mach_type
 	ldr r2,kexec_boot_atags
- ARM(	mov pc, lr	)
+ ARM(	ret lr	)
  THUMB(	bx lr		)
 
 	.align
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 1b880db2a033..e1e60e5a7a27 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -107,7 +107,7 @@  ENTRY(cpu_resume_mmu)
 	instr_sync
 	mov	r0, r0
 	mov	r0, r0
-	mov	pc, r3			@ jump to virtual address
+	ret	r3			@ jump to virtual address
 ENDPROC(cpu_resume_mmu)
 	.popsection
 cpu_resume_after_mmu:
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 1b9844d369cc..b2d229f09c07 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -17,6 +17,7 @@ 
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/unified.h>
 #include <asm/asm-offsets.h>
 #include <asm/kvm_asm.h>
@@ -134,7 +135,7 @@  phase2:
 	ldr	r0, =TRAMPOLINE_VA
 	adr	r1, target
 	bfi	r0, r1, #0, #PAGE_SHIFT
-	mov	pc, r0
+	ret	r0
 
 target:	@ We're now in the trampoline code, switch page tables
 	mcrr	p15, 4, r2, r3, c2
diff --git a/arch/arm/lib/ashldi3.S b/arch/arm/lib/ashldi3.S
index 638deb13da1c..b05e95840651 100644
--- a/arch/arm/lib/ashldi3.S
+++ b/arch/arm/lib/ashldi3.S
@@ -27,6 +27,7 @@  Boston, MA 02110-1301, USA.  */
 
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #ifdef __ARMEB__
 #define al r1
@@ -47,7 +48,7 @@  ENTRY(__aeabi_llsl)
  THUMB(	lsrmi	r3, al, ip		)
  THUMB(	orrmi	ah, ah, r3		)
 	mov	al, al, lsl r2
-	mov	pc, lr
+	ret	lr
 
 ENDPROC(__ashldi3)
 ENDPROC(__aeabi_llsl)
diff --git a/arch/arm/lib/ashrdi3.S b/arch/arm/lib/ashrdi3.S
index 015e8aa5a1d1..275d7d2341a4 100644
--- a/arch/arm/lib/ashrdi3.S
+++ b/arch/arm/lib/ashrdi3.S
@@ -27,6 +27,7 @@  Boston, MA 02110-1301, USA.  */
 
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #ifdef __ARMEB__
 #define al r1
@@ -47,7 +48,7 @@  ENTRY(__aeabi_lasr)
  THUMB(	lslmi	r3, ah, ip		)
  THUMB(	orrmi	al, al, r3		)
 	mov	ah, ah, asr r2
-	mov	pc, lr
+	ret	lr
 
 ENDPROC(__ashrdi3)
 ENDPROC(__aeabi_lasr)
diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S
index 4102be617fce..fab5a50503ae 100644
--- a/arch/arm/lib/backtrace.S
+++ b/arch/arm/lib/backtrace.S
@@ -25,7 +25,7 @@ 
 ENTRY(c_backtrace)
 
 #if !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK)
-		mov	pc, lr
+		ret	lr
 ENDPROC(c_backtrace)
 #else
 		stmfd	sp!, {r4 - r8, lr}	@ Save an extra register so we have a location...
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index 9f12ed1eea86..7d807cfd8ef5 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -1,3 +1,4 @@ 
+#include <asm/assembler.h>
 #include <asm/unwind.h>
 
 #if __LINUX_ARM_ARCH__ >= 6
@@ -70,7 +71,7 @@  UNWIND(	.fnstart	)
 	\instr	r2, r2, r3
 	str	r2, [r1, r0, lsl #2]
 	restore_irqs ip
-	mov	pc, lr
+	ret	lr
 UNWIND(	.fnend		)
 ENDPROC(\name		)
 	.endm
@@ -98,7 +99,7 @@  UNWIND(	.fnstart	)
 	\store	r2, [r1]
 	moveq	r0, #0
 	restore_irqs ip
-	mov	pc, lr
+	ret	lr
 UNWIND(	.fnend		)
 ENDPROC(\name		)
 	.endm
diff --git a/arch/arm/lib/bswapsdi2.S b/arch/arm/lib/bswapsdi2.S
index 9fcdd154eff9..07cda737bb11 100644
--- a/arch/arm/lib/bswapsdi2.S
+++ b/arch/arm/lib/bswapsdi2.S
@@ -1,4 +1,5 @@ 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #if __LINUX_ARM_ARCH__ >= 6
 ENTRY(__bswapsi2)
@@ -18,7 +19,7 @@  ENTRY(__bswapsi2)
 	mov r3, r3, lsr #8
 	bic r3, r3, #0xff00
 	eor r0, r3, r0, ror #8
-	mov pc, lr
+	ret lr
 ENDPROC(__bswapsi2)
 
 ENTRY(__bswapdi2)
@@ -31,6 +32,6 @@  ENTRY(__bswapdi2)
 	bic r1, r1, #0xff00
 	eor r1, r1, r0, ror #8
 	eor r0, r3, ip, ror #8
-	mov pc, lr
+	ret lr
 ENDPROC(__bswapdi2)
 #endif
diff --git a/arch/arm/lib/call_with_stack.S b/arch/arm/lib/call_with_stack.S
index 916c80f13ae7..ed1a421813cb 100644
--- a/arch/arm/lib/call_with_stack.S
+++ b/arch/arm/lib/call_with_stack.S
@@ -36,9 +36,9 @@  ENTRY(call_with_stack)
 	mov	r0, r1
 
 	adr	lr, BSYM(1f)
-	mov	pc, r2
+	ret	r2
 
 1:	ldr	lr, [sp]
 	ldr	sp, [sp, #4]
-	mov	pc, lr
+	ret	lr
 ENDPROC(call_with_stack)
diff --git a/arch/arm/lib/csumpartial.S b/arch/arm/lib/csumpartial.S
index 31d3cb34740d..984e0f29d548 100644
--- a/arch/arm/lib/csumpartial.S
+++ b/arch/arm/lib/csumpartial.S
@@ -97,7 +97,7 @@  td3	.req	lr
 #endif
 #endif
 		adcnes	sum, sum, td0		@ update checksum
-		mov	pc, lr
+		ret	lr
 
 ENTRY(csum_partial)
 		stmfd	sp!, {buf, lr}
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index d6e742d24007..10b45909610c 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -7,6 +7,7 @@ 
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <asm/assembler.h>
 
 /*
  * unsigned int
@@ -40,7 +41,7 @@  sum	.req	r3
 		adcs	sum, sum, ip, put_byte_1	@ update checksum
 		strb	ip, [dst], #1
 		tst	dst, #2
-		moveq	pc, lr			@ dst is now 32bit aligned
+		reteq	lr			@ dst is now 32bit aligned
 
 .Ldst_16bit:	load2b	r8, ip
 		sub	len, len, #2
@@ -48,7 +49,7 @@  sum	.req	r3
 		strb	r8, [dst], #1
 		adcs	sum, sum, ip, put_byte_1
 		strb	ip, [dst], #1
-		mov	pc, lr			@ dst is now 32bit aligned
+		ret	lr			@ dst is now 32bit aligned
 
 		/*
 		 * Handle 0 to 7 bytes, with any alignment of source and
diff --git a/arch/arm/lib/delay-loop.S b/arch/arm/lib/delay-loop.S
index bc1033b897b4..518bf6e93f78 100644
--- a/arch/arm/lib/delay-loop.S
+++ b/arch/arm/lib/delay-loop.S
@@ -35,7 +35,7 @@  ENTRY(__loop_const_udelay)			@ 0 <= r0 <= 0x7fffff06
 		mul	r0, r2, r0		@ max = 2^32-1
 		add	r0, r0, r1, lsr #32-6
 		movs	r0, r0, lsr #6
-		moveq	pc, lr
+		reteq	lr
 
 /*
  * loops = r0 * HZ * loops_per_jiffy / 1000000
@@ -46,23 +46,23 @@  ENTRY(__loop_const_udelay)			@ 0 <= r0 <= 0x7fffff06
 ENTRY(__loop_delay)
 		subs	r0, r0, #1
 #if 0
-		movls	pc, lr
+		retls	lr
 		subs	r0, r0, #1
-		movls	pc, lr
+		retls	lr
 		subs	r0, r0, #1
-		movls	pc, lr
+		retls	lr
 		subs	r0, r0, #1
-		movls	pc, lr
+		retls	lr
 		subs	r0, r0, #1
-		movls	pc, lr
+		retls	lr
 		subs	r0, r0, #1
-		movls	pc, lr
+		retls	lr
 		subs	r0, r0, #1
-		movls	pc, lr
+		retls	lr
 		subs	r0, r0, #1
 #endif
 		bhi	__loop_delay
-		mov	pc, lr
+		ret	lr
 ENDPROC(__loop_udelay)
 ENDPROC(__loop_const_udelay)
 ENDPROC(__loop_delay)
diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S
index e55c4842c290..a9eafe4981eb 100644
--- a/arch/arm/lib/div64.S
+++ b/arch/arm/lib/div64.S
@@ -13,6 +13,7 @@ 
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/unwind.h>
 
 #ifdef __ARMEB__
@@ -97,7 +98,7 @@  UNWIND(.fnstart)
 	mov	yl, #0
 	cmpeq	xl, r4
 	movlo	xh, xl
-	movlo	pc, lr
+	retlo	lr
 
 	@ The division loop for lower bit positions.
 	@ Here we shift remainer bits leftwards rather than moving the
@@ -111,14 +112,14 @@  UNWIND(.fnstart)
 	subcs	xh, xh, r4
 	movs	ip, ip, lsr #1
 	bne	4b
-	mov	pc, lr
+	ret	lr
 
 	@ The top part of remainder became zero.  If carry is set
 	@ (the 33th bit) this is a false positive so resume the loop.
 	@ Otherwise, if lower part is also null then we are done.
 6:	bcs	5b
 	cmp	xl, #0
-	moveq	pc, lr
+	reteq	lr
 
 	@ We still have remainer bits in the low part.  Bring them up.
 
@@ -144,7 +145,7 @@  UNWIND(.fnstart)
 	movs	ip, ip, lsr #1
 	mov	xh, #1
 	bne	4b
-	mov	pc, lr
+	ret	lr
 
 8:	@ Division by a power of 2: determine what that divisor order is
 	@ then simply shift values around
@@ -184,13 +185,13 @@  UNWIND(.fnstart)
  THUMB(	orr	yl, yl, xh		)
 	mov	xh, xl, lsl ip
 	mov	xh, xh, lsr ip
-	mov	pc, lr
+	ret	lr
 
 	@ eq -> division by 1: obvious enough...
 9:	moveq	yl, xl
 	moveq	yh, xh
 	moveq	xh, #0
-	moveq	pc, lr
+	reteq	lr
 UNWIND(.fnend)
 
 UNWIND(.fnstart)
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
index 64f6bc1a9132..7848780e8834 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib/findbit.S
@@ -35,7 +35,7 @@  ENTRY(_find_first_zero_bit_le)
 2:		cmp	r2, r1			@ any more?
 		blo	1b
 3:		mov	r0, r1			@ no free bits
-		mov	pc, lr
+		ret	lr
 ENDPROC(_find_first_zero_bit_le)
 
 /*
@@ -76,7 +76,7 @@  ENTRY(_find_first_bit_le)
 2:		cmp	r2, r1			@ any more?
 		blo	1b
 3:		mov	r0, r1			@ no free bits
-		mov	pc, lr
+		ret	lr
 ENDPROC(_find_first_bit_le)
 
 /*
@@ -114,7 +114,7 @@  ENTRY(_find_first_zero_bit_be)
 2:		cmp	r2, r1			@ any more?
 		blo	1b
 3:		mov	r0, r1			@ no free bits
-		mov	pc, lr
+		ret	lr
 ENDPROC(_find_first_zero_bit_be)
 
 ENTRY(_find_next_zero_bit_be)
@@ -148,7 +148,7 @@  ENTRY(_find_first_bit_be)
 2:		cmp	r2, r1			@ any more?
 		blo	1b
 3:		mov	r0, r1			@ no free bits
-		mov	pc, lr
+		ret	lr
 ENDPROC(_find_first_bit_be)
 
 ENTRY(_find_next_bit_be)
@@ -192,5 +192,5 @@  ENDPROC(_find_next_bit_be)
 #endif
 		cmp	r1, r0			@ Clamp to maxbit
 		movlo	r0, r1
-		mov	pc, lr
+		ret	lr
 
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 9b06bb41fca6..0f958e3d8180 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -36,7 +36,7 @@  ENTRY(__get_user_1)
 	check_uaccess r0, 1, r1, r2, __get_user_bad
 1: TUSER(ldrb)	r2, [r0]
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
@@ -56,20 +56,20 @@  rb	.req	r0
 	orr	r2, rb, r2, lsl #8
 #endif
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
 	check_uaccess r0, 4, r1, r2, __get_user_bad
 4: TUSER(ldr)	r2, [r0]
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(__get_user_4)
 
 __get_user_bad:
 	mov	r2, #0
 	mov	r0, #-EFAULT
-	mov	pc, lr
+	ret	lr
 ENDPROC(__get_user_bad)
 
 .pushsection __ex_table, "a"
diff --git a/arch/arm/lib/io-readsb.S b/arch/arm/lib/io-readsb.S
index 9f4238987fe9..c31b2f3153f1 100644
--- a/arch/arm/lib/io-readsb.S
+++ b/arch/arm/lib/io-readsb.S
@@ -25,7 +25,7 @@ 
 
 ENTRY(__raw_readsb)
 		teq	r2, #0		@ do we have to check for the zero len?
-		moveq	pc, lr
+		reteq	lr
 		ands	ip, r1, #3
 		bne	.Linsb_align
 
diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S
index 7a7430950c79..2ed86fa5465f 100644
--- a/arch/arm/lib/io-readsl.S
+++ b/arch/arm/lib/io-readsl.S
@@ -12,7 +12,7 @@ 
 
 ENTRY(__raw_readsl)
 		teq	r2, #0		@ do we have to check for the zero len?
-		moveq	pc, lr
+		reteq	lr
 		ands	ip, r1, #3
 		bne	3f
 
@@ -33,7 +33,7 @@  ENTRY(__raw_readsl)
 		stmcsia	r1!, {r3, ip}
 		ldrne	r3, [r0, #0]
 		strne	r3, [r1, #0]
-		mov	pc, lr
+		ret	lr
 
 3:		ldr	r3, [r0]
 		cmp	ip, #2
@@ -75,5 +75,5 @@  ENTRY(__raw_readsl)
 		strb	r3, [r1, #1]
 8:		mov	r3, ip, get_byte_0
 		strb	r3, [r1, #0]
-		mov	pc, lr
+		ret	lr
 ENDPROC(__raw_readsl)
diff --git a/arch/arm/lib/io-readsw-armv3.S b/arch/arm/lib/io-readsw-armv3.S
index 88487c8c4f23..413da9914529 100644
--- a/arch/arm/lib/io-readsw-armv3.S
+++ b/arch/arm/lib/io-readsw-armv3.S
@@ -27,11 +27,11 @@ 
 		strb	r3, [r1], #1
 
 		subs	r2, r2, #1
-		moveq	pc, lr
+		reteq	lr
 
 ENTRY(__raw_readsw)
 		teq	r2, #0		@ do we have to check for the zero len?
-		moveq	pc, lr
+		reteq	lr
 		tst	r1, #3
 		bne	.Linsw_align
 
diff --git a/arch/arm/lib/io-readsw-armv4.S b/arch/arm/lib/io-readsw-armv4.S
index 1f393d42593d..d9a45e9692ae 100644
--- a/arch/arm/lib/io-readsw-armv4.S
+++ b/arch/arm/lib/io-readsw-armv4.S
@@ -26,7 +26,7 @@ 
 
 ENTRY(__raw_readsw)
 		teq	r2, #0
-		moveq	pc, lr
+		reteq	lr
 		tst	r1, #3
 		bne	.Linsw_align
 
diff --git a/arch/arm/lib/io-writesb.S b/arch/arm/lib/io-writesb.S
index 68b92f4acaeb..a46bbc9b168b 100644
--- a/arch/arm/lib/io-writesb.S
+++ b/arch/arm/lib/io-writesb.S
@@ -45,7 +45,7 @@ 
 
 ENTRY(__raw_writesb)
 		teq	r2, #0		@ do we have to check for the zero len?
-		moveq	pc, lr
+		reteq	lr
 		ands	ip, r1, #3
 		bne	.Loutsb_align
 
diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S
index d0d104a0dd11..4ea2435988c1 100644
--- a/arch/arm/lib/io-writesl.S
+++ b/arch/arm/lib/io-writesl.S
@@ -12,7 +12,7 @@ 
 
 ENTRY(__raw_writesl)
 		teq	r2, #0		@ do we have to check for the zero len?
-		moveq	pc, lr
+		reteq	lr
 		ands	ip, r1, #3
 		bne	3f
 
@@ -33,7 +33,7 @@  ENTRY(__raw_writesl)
 		ldrne	r3, [r1, #0]
 		strcs	ip, [r0, #0]
 		strne	r3, [r0, #0]
-		mov	pc, lr
+		ret	lr
 
 3:		bic	r1, r1, #3
 		ldr	r3, [r1], #4
@@ -47,7 +47,7 @@  ENTRY(__raw_writesl)
 		orr	ip, ip, r3, lspush #16
 		str	ip, [r0]
 		bne	4b
-		mov	pc, lr
+		ret	lr
 
 5:		mov	ip, r3, lspull #8
 		ldr	r3, [r1], #4
@@ -55,7 +55,7 @@  ENTRY(__raw_writesl)
 		orr	ip, ip, r3, lspush #24
 		str	ip, [r0]
 		bne	5b
-		mov	pc, lr
+		ret	lr
 
 6:		mov	ip, r3, lspull #24
 		ldr	r3, [r1], #4
@@ -63,5 +63,5 @@  ENTRY(__raw_writesl)
 		orr	ip, ip, r3, lspush #8
 		str	ip, [r0]
 		bne	6b
-		mov	pc, lr
+		ret	lr
 ENDPROC(__raw_writesl)
diff --git a/arch/arm/lib/io-writesw-armv3.S b/arch/arm/lib/io-writesw-armv3.S
index 49b800419e32..121789eb6802 100644
--- a/arch/arm/lib/io-writesw-armv3.S
+++ b/arch/arm/lib/io-writesw-armv3.S
@@ -28,11 +28,11 @@ 
 		orr	r3, r3, r3, lsl #16
 		str	r3, [r0]
 		subs	r2, r2, #1
-		moveq	pc, lr
+		reteq	lr
 
 ENTRY(__raw_writesw)
 		teq	r2, #0		@ do we have to check for the zero len?
-		moveq	pc, lr
+		reteq	lr
 		tst	r1, #3
 		bne	.Loutsw_align
 
diff --git a/arch/arm/lib/io-writesw-armv4.S b/arch/arm/lib/io-writesw-armv4.S
index ff4f71b579ee..269f90c51ad2 100644
--- a/arch/arm/lib/io-writesw-armv4.S
+++ b/arch/arm/lib/io-writesw-armv4.S
@@ -31,7 +31,7 @@ 
 
 ENTRY(__raw_writesw)
 		teq	r2, #0
-		moveq	pc, lr
+		reteq	lr
 		ands	r3, r1, #3
 		bne	.Loutsw_align
 
@@ -96,5 +96,5 @@  ENTRY(__raw_writesw)
 		tst	r2, #1
 3:		movne	ip, r3, lsr #8
 		strneh	ip, [r0]
-		mov	pc, lr
+		ret	lr
 ENDPROC(__raw_writesw)
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index c562f649734c..947567ff67f9 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -210,7 +210,7 @@  ENTRY(__aeabi_uidiv)
 UNWIND(.fnstart)
 
 	subs	r2, r1, #1
-	moveq	pc, lr
+	reteq	lr
 	bcc	Ldiv0
 	cmp	r0, r1
 	bls	11f
@@ -220,16 +220,16 @@  UNWIND(.fnstart)
 	ARM_DIV_BODY r0, r1, r2, r3
 
 	mov	r0, r2
-	mov	pc, lr
+	ret	lr
 
 11:	moveq	r0, #1
 	movne	r0, #0
-	mov	pc, lr
+	ret	lr
 
 12:	ARM_DIV2_ORDER r1, r2
 
 	mov	r0, r0, lsr r2
-	mov	pc, lr
+	ret	lr
 
 UNWIND(.fnend)
 ENDPROC(__udivsi3)
@@ -244,11 +244,11 @@  UNWIND(.fnstart)
 	moveq   r0, #0
 	tsthi	r1, r2				@ see if divisor is power of 2
 	andeq	r0, r0, r2
-	movls	pc, lr
+	retls	lr
 
 	ARM_MOD_BODY r0, r1, r2, r3
 
-	mov	pc, lr
+	ret	lr
 
 UNWIND(.fnend)
 ENDPROC(__umodsi3)
@@ -274,23 +274,23 @@  UNWIND(.fnstart)
 
 	cmp	ip, #0
 	rsbmi	r0, r0, #0
-	mov	pc, lr
+	ret	lr
 
 10:	teq	ip, r0				@ same sign ?
 	rsbmi	r0, r0, #0
-	mov	pc, lr
+	ret	lr
 
 11:	movlo	r0, #0
 	moveq	r0, ip, asr #31
 	orreq	r0, r0, #1
-	mov	pc, lr
+	ret	lr
 
 12:	ARM_DIV2_ORDER r1, r2
 
 	cmp	ip, #0
 	mov	r0, r3, lsr r2
 	rsbmi	r0, r0, #0
-	mov	pc, lr
+	ret	lr
 
 UNWIND(.fnend)
 ENDPROC(__divsi3)
@@ -315,7 +315,7 @@  UNWIND(.fnstart)
 
 10:	cmp	ip, #0
 	rsbmi	r0, r0, #0
-	mov	pc, lr
+	ret	lr
 
 UNWIND(.fnend)
 ENDPROC(__modsi3)
@@ -331,7 +331,7 @@  UNWIND(.save {r0, r1, ip, lr}	)
 	ldmfd	sp!, {r1, r2, ip, lr}
 	mul	r3, r0, r2
 	sub	r1, r1, r3
-	mov	pc, lr
+	ret	lr
 
 UNWIND(.fnend)
 ENDPROC(__aeabi_uidivmod)
@@ -344,7 +344,7 @@  UNWIND(.save {r0, r1, ip, lr}	)
 	ldmfd	sp!, {r1, r2, ip, lr}
 	mul	r3, r0, r2
 	sub	r1, r1, r3
-	mov	pc, lr
+	ret	lr
 
 UNWIND(.fnend)
 ENDPROC(__aeabi_idivmod)
diff --git a/arch/arm/lib/lshrdi3.S b/arch/arm/lib/lshrdi3.S
index f83d449141f7..922dcd88b02b 100644
--- a/arch/arm/lib/lshrdi3.S
+++ b/arch/arm/lib/lshrdi3.S
@@ -27,6 +27,7 @@  Boston, MA 02110-1301, USA.  */
 
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #ifdef __ARMEB__
 #define al r1
@@ -47,7 +48,7 @@  ENTRY(__aeabi_llsr)
  THUMB(	lslmi	r3, ah, ip		)
  THUMB(	orrmi	al, al, r3		)
 	mov	ah, ah, lsr r2
-	mov	pc, lr
+	ret	lr
 
 ENDPROC(__lshrdi3)
 ENDPROC(__aeabi_llsr)
diff --git a/arch/arm/lib/memchr.S b/arch/arm/lib/memchr.S
index 1da86991d700..74a5bed6d999 100644
--- a/arch/arm/lib/memchr.S
+++ b/arch/arm/lib/memchr.S
@@ -22,5 +22,5 @@  ENTRY(memchr)
 	bne	1b
 	sub	r0, r0, #1
 2:	movne	r0, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(memchr)
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index 94b0650ea98f..671455c854fa 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -110,7 +110,7 @@  ENTRY(memset)
 	strneb	r1, [ip], #1
 	tst	r2, #1
 	strneb	r1, [ip], #1
-	mov	pc, lr
+	ret	lr
 
 6:	subs	r2, r2, #4		@ 1 do we have enough
 	blt	5b			@ 1 bytes to align with?
diff --git a/arch/arm/lib/memzero.S b/arch/arm/lib/memzero.S
index 3fbdef5f802a..385ccb306fa2 100644
--- a/arch/arm/lib/memzero.S
+++ b/arch/arm/lib/memzero.S
@@ -121,5 +121,5 @@  ENTRY(__memzero)
 	strneb	r2, [r0], #1		@ 1
 	tst	r1, #1			@ 1 a byte left over
 	strneb	r2, [r0], #1		@ 1
-	mov	pc, lr			@ 1
+	ret	lr			@ 1
 ENDPROC(__memzero)
diff --git a/arch/arm/lib/muldi3.S b/arch/arm/lib/muldi3.S
index 36c91b4957e2..204305956925 100644
--- a/arch/arm/lib/muldi3.S
+++ b/arch/arm/lib/muldi3.S
@@ -11,6 +11,7 @@ 
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #ifdef __ARMEB__
 #define xh r0
@@ -41,7 +42,7 @@  ENTRY(__aeabi_lmul)
 	adc	xh, xh, yh, lsr #16
 	adds	xl, xl, ip, lsl #16
 	adc	xh, xh, ip, lsr #16
-	mov	pc, lr
+	ret	lr
 
 ENDPROC(__muldi3)
 ENDPROC(__aeabi_lmul)
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 3d73dcb959b0..38d660d3705f 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -36,7 +36,7 @@  ENTRY(__put_user_1)
 	check_uaccess r0, 1, r1, ip, __put_user_bad
 1: TUSER(strb)	r2, [r0]
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(__put_user_1)
 
 ENTRY(__put_user_2)
@@ -60,14 +60,14 @@  ENTRY(__put_user_2)
 #endif
 #endif	/* CONFIG_THUMB2_KERNEL */
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(__put_user_2)
 
 ENTRY(__put_user_4)
 	check_uaccess r0, 4, r1, ip, __put_user_bad
 4: TUSER(str)	r2, [r0]
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
@@ -80,12 +80,12 @@  ENTRY(__put_user_8)
 6: TUSER(str)	r3, [r0]
 #endif
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(__put_user_8)
 
 __put_user_bad:
 	mov	r0, #-EFAULT
-	mov	pc, lr
+	ret	lr
 ENDPROC(__put_user_bad)
 
 .pushsection __ex_table, "a"
diff --git a/arch/arm/lib/strchr.S b/arch/arm/lib/strchr.S
index d8f2a1c1aea4..013d64c71e8d 100644
--- a/arch/arm/lib/strchr.S
+++ b/arch/arm/lib/strchr.S
@@ -23,5 +23,5 @@  ENTRY(strchr)
 		teq	r2, r1
 		movne	r0, #0
 		subeq	r0, r0, #1
-		mov	pc, lr
+		ret	lr
 ENDPROC(strchr)
diff --git a/arch/arm/lib/strrchr.S b/arch/arm/lib/strrchr.S
index 302f20cd2423..3cec1c7482c4 100644
--- a/arch/arm/lib/strrchr.S
+++ b/arch/arm/lib/strrchr.S
@@ -22,5 +22,5 @@  ENTRY(strrchr)
 		teq	r2, #0
 		bne	1b
 		mov	r0, r3
-		mov	pc, lr
+		ret	lr
 ENDPROC(strrchr)
diff --git a/arch/arm/lib/ucmpdi2.S b/arch/arm/lib/ucmpdi2.S
index f0df6a91db04..ad4a6309141a 100644
--- a/arch/arm/lib/ucmpdi2.S
+++ b/arch/arm/lib/ucmpdi2.S
@@ -11,6 +11,7 @@ 
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #ifdef __ARMEB__
 #define xh r0
@@ -31,7 +32,7 @@  ENTRY(__ucmpdi2)
 	movlo	r0, #0
 	moveq	r0, #1
 	movhi	r0, #2
-	mov	pc, lr
+	ret	lr
 
 ENDPROC(__ucmpdi2)
 
@@ -44,7 +45,7 @@  ENTRY(__aeabi_ulcmp)
 	movlo	r0, #-1
 	moveq	r0, #0
 	movhi	r0, #1
-	mov	pc, lr
+	ret	lr
 
 ENDPROC(__aeabi_ulcmp)
 
diff --git a/arch/arm/mach-davinci/sleep.S b/arch/arm/mach-davinci/sleep.S
index d4e9316ecacb..a5336a5e2739 100644
--- a/arch/arm/mach-davinci/sleep.S
+++ b/arch/arm/mach-davinci/sleep.S
@@ -213,7 +213,7 @@  ddr2clk_stop_done:
 	cmp	ip, r0
 	bne	ddr2clk_stop_done
 
-	mov	pc, lr
+	ret	lr
 ENDPROC(davinci_ddr_psc_config)
 
 CACHE_FLUSH:
diff --git a/arch/arm/mach-ep93xx/crunch-bits.S b/arch/arm/mach-ep93xx/crunch-bits.S
index e96923a3017b..ee0be2af5c61 100644
--- a/arch/arm/mach-ep93xx/crunch-bits.S
+++ b/arch/arm/mach-ep93xx/crunch-bits.S
@@ -198,7 +198,7 @@  crunch_load:
 	get_thread_info r10
 #endif
 2:	dec_preempt_count r10, r3
-	mov	pc, lr
+	ret	lr
 
 /*
  * Back up crunch regs to save area and disable access to them
@@ -277,7 +277,7 @@  ENTRY(crunch_task_copy)
 	mov	r3, lr				@ preserve return address
 	bl	crunch_save
 	msr	cpsr_c, ip			@ restore interrupt mode
-	mov	pc, r3
+	ret	r3
 
 /*
  * Restore crunch state from given memory address
@@ -310,4 +310,4 @@  ENTRY(crunch_task_restore)
 	mov	r3, lr				@ preserve return address
 	bl	crunch_load
 	msr	cpsr_c, ip			@ restore interrupt mode
-	mov	pc, r3
+	ret	r3
diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S
index fe123b079c05..74b50f1982db 100644
--- a/arch/arm/mach-imx/suspend-imx6.S
+++ b/arch/arm/mach-imx/suspend-imx6.S
@@ -10,6 +10,7 @@ 
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hardware/cache-l2x0.h>
 #include "hardware.h"
@@ -301,7 +302,7 @@  rbc_loop:
 	resume_mmdc
 
 	/* return to suspend finish */
-	mov	pc, lr
+	ret	lr
 
 resume:
 	/* invalidate L1 I-cache first */
@@ -325,7 +326,7 @@  resume:
 	mov	r5, #0x1
 	resume_mmdc
 
-	mov	pc, lr
+	ret	lr
 ENDPROC(imx6_suspend)
 
 /*
diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S
index 510c29e079ca..f5d881b5d0f7 100644
--- a/arch/arm/mach-mvebu/coherency_ll.S
+++ b/arch/arm/mach-mvebu/coherency_ll.S
@@ -46,7 +46,7 @@  ENTRY(ll_get_coherency_base)
 	ldr	r1, =coherency_base
 	ldr	r1, [r1]
 2:
-	mov	pc, lr
+	ret	lr
 ENDPROC(ll_get_coherency_base)
 
 /*
@@ -63,7 +63,7 @@  ENTRY(ll_get_coherency_cpumask)
 	mov	r2, #(1 << 24)
 	lsl	r3, r2, r3
 ARM_BE8(rev	r3, r3)
-	mov	pc, lr
+	ret	lr
 ENDPROC(ll_get_coherency_cpumask)
 
 /*
@@ -94,7 +94,7 @@  ENTRY(ll_add_cpu_to_smp_group)
 	strex	r1, r2, [r0]
 	cmp	r1, #0
 	bne	1b
-	mov	pc, lr
+	ret	lr
 ENDPROC(ll_add_cpu_to_smp_group)
 
 ENTRY(ll_enable_coherency)
@@ -118,7 +118,7 @@  ENTRY(ll_enable_coherency)
 	bne	1b
 	dsb
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(ll_enable_coherency)
 
 ENTRY(ll_disable_coherency)
@@ -141,7 +141,7 @@  ENTRY(ll_disable_coherency)
 	cmp	r1, #0
 	bne	1b
 	dsb
-	mov	pc, lr
+	ret	lr
 ENDPROC(ll_disable_coherency)
 
 	.align 2
diff --git a/arch/arm/mach-mvebu/headsmp-a9.S b/arch/arm/mach-mvebu/headsmp-a9.S
index 5925366bc03c..7c91ddb6f1f7 100644
--- a/arch/arm/mach-mvebu/headsmp-a9.S
+++ b/arch/arm/mach-mvebu/headsmp-a9.S
@@ -14,6 +14,7 @@ 
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <asm/assembler.h>
 
 	__CPUINIT
 #define CPU_RESUME_ADDR_REG 0xf10182d4
@@ -24,7 +25,7 @@ 
 armada_375_smp_cpu1_enable_code_start:
 	ldr     r0, [pc, #4]
 	ldr     r1, [r0]
-	mov     pc, r1
+	ret     r1
 	.word   CPU_RESUME_ADDR_REG
 armada_375_smp_cpu1_enable_code_end:
 
diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S
index 9086ce03ae12..b84a0122d823 100644
--- a/arch/arm/mach-omap2/sleep44xx.S
+++ b/arch/arm/mach-omap2/sleep44xx.S
@@ -10,6 +10,7 @@ 
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/smp_scu.h>
 #include <asm/memory.h>
 #include <asm/hardware/cache-l2x0.h>
@@ -334,7 +335,7 @@  ENDPROC(omap4_cpu_resume)
 
 #ifndef CONFIG_OMAP4_ERRATA_I688
 ENTRY(omap_bus_sync)
-	mov	pc, lr
+	ret	lr
 ENDPROC(omap_bus_sync)
 #endif
 
diff --git a/arch/arm/mach-omap2/sram242x.S b/arch/arm/mach-omap2/sram242x.S
index 680a7c56cc3e..2c88ff2d0236 100644
--- a/arch/arm/mach-omap2/sram242x.S
+++ b/arch/arm/mach-omap2/sram242x.S
@@ -101,7 +101,7 @@  i_dll_wait:
 i_dll_delay:
 	subs	r4, r4, #0x1
 	bne	i_dll_delay
-	mov	pc, lr
+	ret	lr
 
 	/*
 	 * shift up or down voltage, use R9 as input to tell level.
@@ -125,7 +125,7 @@  volt_delay:
 	ldr	r7, [r3]		@ get timer value
 	cmp	r5, r7			@ time up?
 	bhi	volt_delay		@ not yet->branch
-	mov	pc, lr			@ back to caller.
+	ret	lr			@ back to caller.
 
 omap242x_sdi_cm_clksel2_pll:
 	.word OMAP2420_CM_REGADDR(PLL_MOD, CM_CLKSEL2)
@@ -220,7 +220,7 @@  volt_delay_c:
 	ldr	r7, [r10]		@ get timer value
 	cmp	r8, r7			@ time up?
 	bhi	volt_delay_c		@ not yet->branch
-	mov	pc, lr			@ back to caller
+	ret	lr			@ back to caller
 
 omap242x_srs_cm_clksel2_pll:
 	.word OMAP2420_CM_REGADDR(PLL_MOD, CM_CLKSEL2)
diff --git a/arch/arm/mach-omap2/sram243x.S b/arch/arm/mach-omap2/sram243x.S
index a1e9edd673f4..d5deb9761fc7 100644
--- a/arch/arm/mach-omap2/sram243x.S
+++ b/arch/arm/mach-omap2/sram243x.S
@@ -101,7 +101,7 @@  i_dll_wait:
 i_dll_delay:
 	subs	r4, r4, #0x1
 	bne	i_dll_delay
-	mov	pc, lr
+	ret	lr
 
 	/*
 	 * shift up or down voltage, use R9 as input to tell level.
@@ -125,7 +125,7 @@  volt_delay:
 	ldr	r7, [r3]		@ get timer value
 	cmp	r5, r7			@ time up?
 	bhi	volt_delay		@ not yet->branch
-	mov	pc, lr			@ back to caller.
+	ret	lr			@ back to caller.
 
 omap243x_sdi_cm_clksel2_pll:
 	.word OMAP2430_CM_REGADDR(PLL_MOD, CM_CLKSEL2)
@@ -220,7 +220,7 @@  volt_delay_c:
 	ldr	r7, [r10]		@ get timer value
 	cmp	r8, r7			@ time up?
 	bhi	volt_delay_c		@ not yet->branch
-	mov	pc, lr			@ back to caller
+	ret	lr			@ back to caller
 
 omap243x_srs_cm_clksel2_pll:
 	.word OMAP2430_CM_REGADDR(PLL_MOD, CM_CLKSEL2)
diff --git a/arch/arm/mach-pxa/mioa701_bootresume.S b/arch/arm/mach-pxa/mioa701_bootresume.S
index 324d25a48c85..81591491ab94 100644
--- a/arch/arm/mach-pxa/mioa701_bootresume.S
+++ b/arch/arm/mach-pxa/mioa701_bootresume.S
@@ -29,7 +29,7 @@  ENTRY(mioa701_jumpaddr)
 	str	r1, [r0]		@ Early disable resume for next boot
 	ldr	r0, mioa701_jumpaddr	@ (Murphy's Law)
 	ldr	r0, [r0]
-	mov	pc, r0
+	ret	r0
 2:
 
 ENTRY(mioa701_bootstrap_lg)
diff --git a/arch/arm/mach-pxa/standby.S b/arch/arm/mach-pxa/standby.S
index 29f5f5c180b7..eab1645bb4ad 100644
--- a/arch/arm/mach-pxa/standby.S
+++ b/arch/arm/mach-pxa/standby.S
@@ -29,7 +29,7 @@  ENTRY(pxa_cpu_standby)
 	.align	5
 1:	mcr	p14, 0, r2, c7, c0, 0	@ put the system into Standby
 	str	r1, [r0]		@ make sure PSSR_PH/STS are clear
-	mov	pc, lr
+	ret	lr
 
 #endif
 
@@ -108,7 +108,7 @@  ENTRY(pm_enter_standby_start)
 	bic	r0, r0, #0x20000000
 	str	r0, [r1, #PXA3_DMCIER]
 
-	mov	pc, lr
+	ret	lr
 ENTRY(pm_enter_standby_end)
 
 #endif
diff --git a/arch/arm/mach-s3c24xx/sleep-s3c2410.S b/arch/arm/mach-s3c24xx/sleep-s3c2410.S
index c9b91223697c..875ba8911127 100644
--- a/arch/arm/mach-s3c24xx/sleep-s3c2410.S
+++ b/arch/arm/mach-s3c24xx/sleep-s3c2410.S
@@ -66,4 +66,4 @@  s3c2410_do_sleep:
 	streq	r8, [r5]			@ SDRAM power-down config
 	streq	r9, [r6]			@ CPU sleep
 1:	beq	1b
-	mov	pc, r14
+	ret	lr
diff --git a/arch/arm/mach-s3c24xx/sleep-s3c2412.S b/arch/arm/mach-s3c24xx/sleep-s3c2412.S
index 5adaceb7da13..6bf5b4d8743c 100644
--- a/arch/arm/mach-s3c24xx/sleep-s3c2412.S
+++ b/arch/arm/mach-s3c24xx/sleep-s3c2412.S
@@ -65,4 +65,4 @@  s3c2412_sleep_enter1:
 	strne	r9, [r3]
 	bne	s3c2412_sleep_enter1
 
-	mov	pc, r14
+	ret	lr
diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S
index e5be5c88644b..293007579b8e 100644
--- a/arch/arm/mach-shmobile/headsmp.S
+++ b/arch/arm/mach-shmobile/headsmp.S
@@ -12,6 +12,7 @@ 
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <asm/assembler.h>
 #include <asm/memory.h>
 
 ENTRY(shmobile_invalidate_start)
@@ -75,7 +76,7 @@  shmobile_smp_boot_next:
 
 shmobile_smp_boot_found:
 	ldr	r0, [r7, r1, lsl #2]
-	mov	pc, r9
+	ret	r9
 ENDPROC(shmobile_smp_boot)
 
 ENTRY(shmobile_smp_sleep)
diff --git a/arch/arm/mach-tegra/sleep-tegra20.S b/arch/arm/mach-tegra/sleep-tegra20.S
index aaaf3abd2688..be4bc5f853f5 100644
--- a/arch/arm/mach-tegra/sleep-tegra20.S
+++ b/arch/arm/mach-tegra/sleep-tegra20.S
@@ -78,7 +78,7 @@  ENTRY(tegra20_hotplug_shutdown)
 	/* Put this CPU down */
 	cpu_id	r0
 	bl	tegra20_cpu_shutdown
-	mov	pc, lr			@ should never get here
+	ret	lr			@ should never get here
 ENDPROC(tegra20_hotplug_shutdown)
 
 /*
@@ -96,7 +96,7 @@  ENDPROC(tegra20_hotplug_shutdown)
  */
 ENTRY(tegra20_cpu_shutdown)
 	cmp	r0, #0
-	moveq	pc, lr			@ must not be called for CPU 0
+	reteq	lr			@ must not be called for CPU 0
 	mov32	r1, TEGRA_PMC_VIRT + PMC_SCRATCH41
 	mov	r12, #CPU_RESETTABLE
 	str	r12, [r1]
@@ -117,7 +117,7 @@  ENTRY(tegra20_cpu_shutdown)
 	cpu_id	r3
 	cmp	r3, r0
 	beq	.
-	mov	pc, lr
+	ret	lr
 ENDPROC(tegra20_cpu_shutdown)
 #endif
 
@@ -164,7 +164,7 @@  ENTRY(tegra_pen_lock)
 	cmpeq	r12, r0			@ !turn == cpu?
 	beq	1b			@ while !turn == cpu && flag[!cpu] == 1
 
-	mov	pc, lr			@ locked
+	ret	lr			@ locked
 ENDPROC(tegra_pen_lock)
 
 ENTRY(tegra_pen_unlock)
@@ -176,7 +176,7 @@  ENTRY(tegra_pen_unlock)
 	addne	r2, r3, #PMC_SCRATCH39
 	mov	r12, #0
 	str	r12, [r2]
-	mov     pc, lr
+	ret     lr
 ENDPROC(tegra_pen_unlock)
 
 /*
@@ -189,7 +189,7 @@  ENTRY(tegra20_cpu_clear_resettable)
 	mov32	r1, TEGRA_PMC_VIRT + PMC_SCRATCH41
 	mov	r12, #CPU_NOT_RESETTABLE
 	str	r12, [r1]
-	mov	pc, lr
+	ret	lr
 ENDPROC(tegra20_cpu_clear_resettable)
 
 /*
@@ -202,7 +202,7 @@  ENTRY(tegra20_cpu_set_resettable_soon)
 	mov32	r1, TEGRA_PMC_VIRT + PMC_SCRATCH41
 	mov	r12, #CPU_RESETTABLE_SOON
 	str	r12, [r1]
-	mov	pc, lr
+	ret	lr
 ENDPROC(tegra20_cpu_set_resettable_soon)
 
 /*
@@ -217,7 +217,7 @@  ENTRY(tegra20_cpu_is_resettable_soon)
 	cmp	r12, #CPU_RESETTABLE_SOON
 	moveq	r0, #1
 	movne	r0, #0
-	mov	pc, lr
+	ret	lr
 ENDPROC(tegra20_cpu_is_resettable_soon)
 
 /*
@@ -239,7 +239,7 @@  ENTRY(tegra20_sleep_core_finish)
 	mov32	r1, TEGRA_IRAM_LPx_RESUME_AREA
 	add	r0, r0, r1
 
-	mov	pc, r3
+	ret	r3
 ENDPROC(tegra20_sleep_core_finish)
 
 /*
@@ -402,7 +402,7 @@  exit_selfrefresh_loop:
 
 	mov32	r0, TEGRA_PMC_BASE
 	ldr	r0, [r0, #PMC_SCRATCH41]
-	mov	pc, r0			@ jump to tegra_resume
+	ret	r0			@ jump to tegra_resume
 ENDPROC(tegra20_lp1_reset)
 
 /*
@@ -455,7 +455,7 @@  tegra20_switch_cpu_to_clk32k:
 	mov	r0, #0	/* brust policy = 32KHz */
 	str	r0, [r5, #CLK_RESET_SCLK_BURST]
 
-	mov	pc, lr
+	ret	lr
 
 /*
  * tegra20_enter_sleep
@@ -535,7 +535,7 @@  padsave_done:
 	adr	r2, tegra20_sclk_save
 	str	r0, [r2]
 	dsb
-	mov	pc, lr
+	ret	lr
 
 tegra20_sdram_pad_address:
 	.word	TEGRA_APB_MISC_BASE + APB_MISC_XM2CFGCPADCTRL
diff --git a/arch/arm/mach-tegra/sleep-tegra30.S b/arch/arm/mach-tegra/sleep-tegra30.S
index b16d4a57fa59..09cad9b071de 100644
--- a/arch/arm/mach-tegra/sleep-tegra30.S
+++ b/arch/arm/mach-tegra/sleep-tegra30.S
@@ -142,7 +142,7 @@  ENTRY(tegra30_hotplug_shutdown)
 	/* Powergate this CPU */
 	mov	r0, #TEGRA30_POWER_HOTPLUG_SHUTDOWN
 	bl	tegra30_cpu_shutdown
-	mov	pc, lr			@ should never get here
+	ret	lr			@ should never get here
 ENDPROC(tegra30_hotplug_shutdown)
 
 /*
@@ -161,7 +161,7 @@  ENTRY(tegra30_cpu_shutdown)
 	bne	_no_cpu0_chk	@ It's not Tegra30
 
 	cmp	r3, #0
-	moveq	pc, lr		@ Must never be called for CPU 0
+	reteq	lr		@ Must never be called for CPU 0
 _no_cpu0_chk:
 
 	ldr	r12, =TEGRA_FLOW_CTRL_VIRT
@@ -266,7 +266,7 @@  ENTRY(tegra30_sleep_core_finish)
 	mov32	r1, TEGRA_IRAM_LPx_RESUME_AREA
 	add	r0, r0, r1
 
-	mov	pc, r3
+	ret	r3
 ENDPROC(tegra30_sleep_core_finish)
 
 /*
@@ -285,7 +285,7 @@  ENTRY(tegra30_sleep_cpu_secondary_finish)
 	mov	r0, #0                          @ power mode flags (!hotplug)
 	bl	tegra30_cpu_shutdown
 	mov	r0, #1                          @ never return here
-	mov	pc, r7
+	ret	r7
 ENDPROC(tegra30_sleep_cpu_secondary_finish)
 
 /*
@@ -529,7 +529,7 @@  __no_dual_emc_chanl:
 
 	mov32	r0, TEGRA_PMC_BASE
 	ldr	r0, [r0, #PMC_SCRATCH41]
-	mov	pc, r0			@ jump to tegra_resume
+	ret	r0			@ jump to tegra_resume
 ENDPROC(tegra30_lp1_reset)
 
 	.align	L1_CACHE_SHIFT
@@ -659,7 +659,7 @@  _no_pll_in_iddq:
 	mov	r0, #0	/* brust policy = 32KHz */
 	str	r0, [r5, #CLK_RESET_SCLK_BURST]
 
-	mov	pc, lr
+	ret	lr
 
 /*
  * tegra30_enter_sleep
@@ -819,7 +819,7 @@  pmc_io_dpd_skip:
 
 	dsb
 
-	mov	pc, lr
+	ret	lr
 
 	.ltorg
 /* dummy symbol for end of IRAM */
diff --git a/arch/arm/mach-tegra/sleep.S b/arch/arm/mach-tegra/sleep.S
index 8d06213fbc47..f024a5109e8e 100644
--- a/arch/arm/mach-tegra/sleep.S
+++ b/arch/arm/mach-tegra/sleep.S
@@ -87,7 +87,7 @@  ENTRY(tegra_init_l2_for_a15)
 	mcrne	p15, 0x1, r0, c9, c0, 2
 _exit_init_l2_a15:
 
-	mov	pc, lr
+	ret	lr
 ENDPROC(tegra_init_l2_for_a15)
 
 /*
@@ -111,7 +111,7 @@  ENTRY(tegra_sleep_cpu_finish)
 	add	r3, r3, r0
 	mov	r0, r1
 
-	mov	pc, r3
+	ret	r3
 ENDPROC(tegra_sleep_cpu_finish)
 
 /*
@@ -139,7 +139,7 @@  ENTRY(tegra_shut_off_mmu)
 	moveq	r3, #0
 	streq	r3, [r2, #L2X0_CTRL]
 #endif
-	mov	pc, r0
+	ret	r0
 ENDPROC(tegra_shut_off_mmu)
 	.popsection
 
@@ -156,6 +156,6 @@  ENTRY(tegra_switch_cpu_to_pllp)
 	str	r0, [r5, #CLK_RESET_CCLK_BURST]
 	mov	r0, #0
 	str	r0, [r5, #CLK_RESET_CCLK_DIVIDER]
-	mov	pc, lr
+	ret	lr
 ENDPROC(tegra_switch_cpu_to_pllp)
 #endif
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
diff --git a/arch/arm/mm/cache-nop.S b/arch/arm/mm/cache-nop.S
index 8e12ddca0031..f1cc9861031f 100644
--- a/arch/arm/mm/cache-nop.S
+++ b/arch/arm/mm/cache-nop.S
@@ -5,11 +5,12 @@ 
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <asm/assembler.h>
 
 #include "proc-macros.S"
 
 ENTRY(nop_flush_icache_all)
-	mov	pc, lr
+	ret	lr
 ENDPROC(nop_flush_icache_all)
 
 	.globl nop_flush_kern_cache_all
@@ -29,7 +30,7 @@  ENDPROC(nop_flush_icache_all)
 
 ENTRY(nop_coherent_user_range)
 	mov	r0, 0
-	mov	pc, lr
+	ret	lr
 ENDPROC(nop_coherent_user_range)
 
 	.globl nop_flush_kern_dcache_area
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index a7ba68f59f0c..91e3adf155cb 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -9,6 +9,7 @@ 
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <asm/assembler.h>
 #include <asm/page.h>
 #include "proc-macros.S"
 
@@ -18,7 +19,7 @@ 
  *	Unconditionally clean and invalidate the entire icache.
  */
 ENTRY(v4_flush_icache_all)
-	mov	pc, lr
+	ret	lr
 ENDPROC(v4_flush_icache_all)
 
 /*
@@ -40,7 +41,7 @@  ENTRY(v4_flush_kern_cache_all)
 #ifdef CONFIG_CPU_CP15
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c7, 0		@ flush ID cache
-	mov	pc, lr
+	ret	lr
 #else
 	/* FALLTHROUGH */
 #endif
@@ -59,7 +60,7 @@  ENTRY(v4_flush_user_cache_range)
 #ifdef CONFIG_CPU_CP15
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0		@ flush ID cache
-	mov	pc, lr
+	ret	lr
 #else
 	/* FALLTHROUGH */
 #endif
@@ -89,7 +90,7 @@  ENTRY(v4_coherent_kern_range)
  */
 ENTRY(v4_coherent_user_range)
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_kern_dcache_area(void *addr, size_t size)
@@ -116,7 +117,7 @@  ENTRY(v4_dma_flush_range)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c7, 0		@ flush ID cache
 #endif
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_unmap_area(start, size, dir)
@@ -136,7 +137,7 @@  ENTRY(v4_dma_unmap_area)
  *	- dir	- DMA direction
  */
 ENTRY(v4_dma_map_area)
-	mov	pc, lr
+	ret	lr
 ENDPROC(v4_dma_unmap_area)
 ENDPROC(v4_dma_map_area)
 
diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S
index cd4945321407..2522f8c8fbb1 100644
--- a/arch/arm/mm/cache-v4wb.S
+++ b/arch/arm/mm/cache-v4wb.S
@@ -9,6 +9,7 @@ 
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <asm/assembler.h>
 #include <asm/memory.h>
 #include <asm/page.h>
 #include "proc-macros.S"
@@ -58,7 +59,7 @@  flush_base:
 ENTRY(v4wb_flush_icache_all)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
-	mov	pc, lr
+	ret	lr
 ENDPROC(v4wb_flush_icache_all)
 
 /*
@@ -94,7 +95,7 @@  __flush_whole_cache:
 	blo	1b
 #endif
 	mcr	p15, 0, ip, c7, c10, 4		@ drain write buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_user_cache_range(start, end, flags)
@@ -122,7 +123,7 @@  ENTRY(v4wb_flush_user_cache_range)
 	blo	1b
 	tst	r2, #VM_EXEC
 	mcrne	p15, 0, ip, c7, c10, 4		@ drain write buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_kern_dcache_area(void *addr, size_t size)
@@ -170,7 +171,7 @@  ENTRY(v4wb_coherent_user_range)
 	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
 
 
 /*
@@ -195,7 +196,7 @@  v4wb_dma_inv_range:
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_clean_range(start, end)
@@ -212,7 +213,7 @@  v4wb_dma_clean_range:
 	cmp	r0, r1
 	blo	1b
 	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_flush_range(start, end)
@@ -248,7 +249,7 @@  ENDPROC(v4wb_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(v4wb_dma_unmap_area)
-	mov	pc, lr
+	ret	lr
 ENDPROC(v4wb_dma_unmap_area)
 
 	.globl	v4wb_flush_kern_cache_louis
diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S
index 11e5e5838bc5..a0982ce49007 100644
--- a/arch/arm/mm/cache-v4wt.S
+++ b/arch/arm/mm/cache-v4wt.S
@@ -13,6 +13,7 @@ 
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <asm/assembler.h>
 #include <asm/page.h>
 #include "proc-macros.S"
 
@@ -48,7 +49,7 @@ 
 ENTRY(v4wt_flush_icache_all)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
-	mov	pc, lr
+	ret	lr
 ENDPROC(v4wt_flush_icache_all)
 
 /*
@@ -71,7 +72,7 @@  __flush_whole_cache:
 	tst	r2, #VM_EXEC
 	mcrne	p15, 0, ip, c7, c5, 0		@ invalidate I cache
 	mcr	p15, 0, ip, c7, c6, 0		@ invalidate D cache
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_user_cache_range(start, end, flags)
@@ -94,7 +95,7 @@  ENTRY(v4wt_flush_user_cache_range)
 	add	r0, r0, #CACHE_DLINESIZE
 	cmp	r0, r1
 	blo	1b
-	mov	pc, lr
+	ret	lr
 
 /*
  *	coherent_kern_range(start, end)
@@ -126,7 +127,7 @@  ENTRY(v4wt_coherent_user_range)
 	cmp	r0, r1
 	blo	1b
 	mov	r0, #0
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_kern_dcache_area(void *addr, size_t size)
@@ -160,7 +161,7 @@  v4wt_dma_inv_range:
 	add	r0, r0, #CACHE_DLINESIZE
 	cmp	r0, r1
 	blo	1b
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_flush_range(start, end)
@@ -192,7 +193,7 @@  ENTRY(v4wt_dma_unmap_area)
  *	- dir	- DMA direction
  */
 ENTRY(v4wt_dma_map_area)
-	mov	pc, lr
+	ret	lr
 ENDPROC(v4wt_dma_unmap_area)
 ENDPROC(v4wt_dma_map_area)
 
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index d8fd4d4bd3d4..24659952c278 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -51,7 +51,7 @@  ENTRY(v6_flush_icache_all)
 #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 @@  ENTRY(v6_flush_kern_cache_all)
 #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 @@  ENTRY(v6_flush_user_cache_all)
  *	- 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 @@  ENTRY(v6_coherent_user_range)
 #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 @@  ENTRY(v6_coherent_user_range)
  */
 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 @@  ENTRY(v6_flush_kern_dcache_area)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c10, 4
 #endif
-	mov	pc, lr
+	ret	lr
 
 
 /*
@@ -239,7 +239,7 @@  v6_dma_inv_range:
 	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 @@  v6_dma_clean_range:
 	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 @@  ENTRY(v6_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)
@@ -323,7 +323,7 @@  ENTRY(v6_dma_unmap_area)
 	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
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 615c99e38ba1..b966656d2c2d 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -61,7 +61,7 @@  ENTRY(v7_invalidate_l1)
        bgt     1b
        dsb     st
        isb
-       mov     pc, lr
+       ret     lr
 ENDPROC(v7_invalidate_l1)
 
 /*
@@ -76,7 +76,7 @@  ENTRY(v7_flush_icache_all)
 	mov	r0, #0
 	ALT_SMP(mcr	p15, 0, r0, c7, c1, 0)		@ invalidate I-cache inner shareable
 	ALT_UP(mcr	p15, 0, r0, c7, c5, 0)		@ I+BTB cache invalidate
-	mov	pc, lr
+	ret	lr
 ENDPROC(v7_flush_icache_all)
 
  /*
@@ -94,7 +94,7 @@  ENTRY(v7_flush_dcache_louis)
 	ALT_UP(ands	r3, r0, #(7 << 27))	@ extract LoUU from clidr
 #ifdef CONFIG_ARM_ERRATA_643719
 	ALT_SMP(mrceq	p15, 0, r2, c0, c0, 0)	@ read main ID register
-	ALT_UP(moveq	pc, lr)			@ LoUU is zero, so nothing to do
+	ALT_UP(reteq	lr)			@ LoUU is zero, so nothing to do
 	ldreq	r1, =0x410fc090                 @ ID of ARM Cortex A9 r0p?
 	biceq	r2, r2, #0x0000000f             @ clear minor revision number
 	teqeq	r2, r1                          @ test for errata affected core and if so...
@@ -102,7 +102,7 @@  ENTRY(v7_flush_dcache_louis)
 #endif
 	ALT_SMP(mov	r3, r3, lsr #20)	@ r3 = LoUIS * 2
 	ALT_UP(mov	r3, r3, lsr #26)	@ r3 = LoUU * 2
-	moveq	pc, lr				@ return if level == 0
+	reteq	lr				@ return if level == 0
 	mov	r10, #0				@ r10 (starting level) = 0
 	b	flush_levels			@ start flushing cache levels
 ENDPROC(v7_flush_dcache_louis)
@@ -168,7 +168,7 @@  finished:
 	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
 	dsb	st
 	isb
-	mov	pc, lr
+	ret	lr
 ENDPROC(v7_flush_dcache_all)
 
 /*
@@ -191,7 +191,7 @@  ENTRY(v7_flush_kern_cache_all)
 	ALT_UP(mcr	p15, 0, r0, c7, c5, 0)	@ I+BTB cache invalidate
  ARM(	ldmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
  THUMB(	ldmfd	sp!, {r4-r7, r9-r11, lr}	)
-	mov	pc, lr
+	ret	lr
 ENDPROC(v7_flush_kern_cache_all)
 
  /*
@@ -209,7 +209,7 @@  ENTRY(v7_flush_kern_cache_louis)
 	ALT_UP(mcr	p15, 0, r0, c7, c5, 0)	@ I+BTB cache invalidate
  ARM(	ldmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
  THUMB(	ldmfd	sp!, {r4-r7, r9-r11, lr}	)
-	mov	pc, lr
+	ret	lr
 ENDPROC(v7_flush_kern_cache_louis)
 
 /*
@@ -235,7 +235,7 @@  ENTRY(v7_flush_user_cache_all)
  *	- we have a VIPT cache.
  */
 ENTRY(v7_flush_user_cache_range)
-	mov	pc, lr
+	ret	lr
 ENDPROC(v7_flush_user_cache_all)
 ENDPROC(v7_flush_user_cache_range)
 
@@ -296,7 +296,7 @@  ENTRY(v7_coherent_user_range)
 	ALT_UP(mcr	p15, 0, r0, c7, c5, 6)	@ invalidate BTB
 	dsb	ishst
 	isb
-	mov	pc, lr
+	ret	lr
 
 /*
  * Fault handling for the cache operation above. If the virtual address in r0
@@ -307,7 +307,7 @@  ENTRY(v7_coherent_user_range)
 	dsb
 #endif
 	mov	r0, #-EFAULT
-	mov	pc, lr
+	ret	lr
  UNWIND(.fnend		)
 ENDPROC(v7_coherent_kern_range)
 ENDPROC(v7_coherent_user_range)
@@ -336,7 +336,7 @@  ENTRY(v7_flush_kern_dcache_area)
 	cmp	r0, r1
 	blo	1b
 	dsb	st
-	mov	pc, lr
+	ret	lr
 ENDPROC(v7_flush_kern_dcache_area)
 
 /*
@@ -369,7 +369,7 @@  v7_dma_inv_range:
 	cmp	r0, r1
 	blo	1b
 	dsb	st
-	mov	pc, lr
+	ret	lr
 ENDPROC(v7_dma_inv_range)
 
 /*
@@ -391,7 +391,7 @@  v7_dma_clean_range:
 	cmp	r0, r1
 	blo	1b
 	dsb	st
-	mov	pc, lr
+	ret	lr
 ENDPROC(v7_dma_clean_range)
 
 /*
@@ -413,7 +413,7 @@  ENTRY(v7_dma_flush_range)
 	cmp	r0, r1
 	blo	1b
 	dsb	st
-	mov	pc, lr
+	ret	lr
 ENDPROC(v7_dma_flush_range)
 
 /*
@@ -439,7 +439,7 @@  ENTRY(v7_dma_unmap_area)
 	add	r1, r1, r0
 	teq	r2, #DMA_TO_DEVICE
 	bne	v7_dma_inv_range
-	mov	pc, lr
+	ret	lr
 ENDPROC(v7_dma_unmap_area)
 
 	__INITDATA
diff --git a/arch/arm/mm/l2c-l2x0-resume.S b/arch/arm/mm/l2c-l2x0-resume.S
index 99b05f21a59a..fda415e4ca8f 100644
--- a/arch/arm/mm/l2c-l2x0-resume.S
+++ b/arch/arm/mm/l2c-l2x0-resume.S
@@ -6,6 +6,7 @@ 
  * This code can only be used to if you are running in the secure world.
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/hardware/cache-l2x0.h>
 
 	.text
@@ -27,7 +28,7 @@  ENTRY(l2c310_early_resume)
 
 	@ Check that the address has been initialised
 	teq	r1, #0
-	moveq	pc, lr
+	reteq	lr
 
 	@ The prefetch and power control registers are revision dependent
 	@ and can be written whether or not the L2 cache is enabled
@@ -41,7 +42,7 @@  ENTRY(l2c310_early_resume)
 	@ Don't setup the L2 cache if it is already enabled
 	ldr	r0, [r1, #L2X0_CTRL]
 	tst	r0, #L2X0_CTRL_EN
-	movne	pc, lr
+	retne	lr
 
 	str	r3, [r1, #L310_TAG_LATENCY_CTRL]
 	str	r4, [r1, #L310_DATA_LATENCY_CTRL]
@@ -51,7 +52,7 @@  ENTRY(l2c310_early_resume)
 	str	r2, [r1, #L2X0_AUX_CTRL]
 	mov	r9, #L2X0_CTRL_EN
 	str	r9, [r1, #L2X0_CTRL]
-	mov	pc, lr
+	ret	lr
 ENDPROC(l2c310_early_resume)
 
 	.align
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index d1a2d05971e0..86ee5d47ce3c 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -73,7 +73,7 @@ 
  * cpu_arm1020_proc_init()
  */
 ENTRY(cpu_arm1020_proc_init)
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_arm1020_proc_fin()
@@ -83,7 +83,7 @@  ENTRY(cpu_arm1020_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_arm1020_reset(loc)
@@ -107,7 +107,7 @@  ENTRY(cpu_arm1020_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_arm1020_reset)
 	.popsection
 
@@ -117,7 +117,7 @@  ENDPROC(cpu_arm1020_reset)
 	.align	5
 ENTRY(cpu_arm1020_do_idle)
 	mcr	p15, 0, r0, c7, c0, 4		@ Wait for interrupt
-	mov	pc, lr
+	ret	lr
 
 /* ================================= CACHE ================================ */
 
@@ -133,7 +133,7 @@  ENTRY(arm1020_flush_icache_all)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 #endif
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm1020_flush_icache_all)
 
 /*
@@ -169,7 +169,7 @@  __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)
@@ -200,7 +200,7 @@  ENTRY(arm1020_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)
@@ -242,7 +242,7 @@  ENTRY(arm1020_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)
@@ -264,7 +264,7 @@  ENTRY(arm1020_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)
@@ -297,7 +297,7 @@  arm1020_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)
@@ -320,7 +320,7 @@  arm1020_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)
@@ -342,7 +342,7 @@  ENTRY(arm1020_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)
@@ -365,7 +365,7 @@  ENDPROC(arm1020_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(arm1020_dma_unmap_area)
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm1020_dma_unmap_area)
 
 	.globl	arm1020_flush_kern_cache_louis
@@ -384,7 +384,7 @@  ENTRY(cpu_arm1020_dcache_clean_area)
 	subs	r1, r1, #CACHE_DLINESIZE
 	bhi	1b
 #endif
-	mov	pc, lr
+	ret	lr
 
 /* =============================== PageTable ============================== */
 
@@ -423,7 +423,7 @@  ENTRY(cpu_arm1020_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 /* CONFIG_MMU */
-	mov	pc, lr
+	ret	lr
         
 /*
  * cpu_arm1020_set_pte(ptep, pte)
@@ -441,7 +441,7 @@  ENTRY(cpu_arm1020_set_pte_ext)
 #endif
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 #endif /* CONFIG_MMU */
-	mov	pc, lr
+	ret	lr
 
 	.type	__arm1020_setup, #function
 __arm1020_setup:
@@ -460,7 +460,7 @@  __arm1020_setup:
 #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN
 	orr	r0, r0, #0x4000 		@ .R.. .... .... ....
 #endif
-	mov	pc, lr
+	ret	lr
 	.size	__arm1020_setup, . - __arm1020_setup
 
 	/*
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index 9d89405c3d03..a6331d78601f 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -73,7 +73,7 @@ 
  * cpu_arm1020e_proc_init()
  */
 ENTRY(cpu_arm1020e_proc_init)
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_arm1020e_proc_fin()
@@ -83,7 +83,7 @@  ENTRY(cpu_arm1020e_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_arm1020e_reset(loc)
@@ -107,7 +107,7 @@  ENTRY(cpu_arm1020e_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_arm1020e_reset)
 	.popsection
 
@@ -117,7 +117,7 @@  ENDPROC(cpu_arm1020e_reset)
 	.align	5
 ENTRY(cpu_arm1020e_do_idle)
 	mcr	p15, 0, r0, c7, c0, 4		@ Wait for interrupt
-	mov	pc, lr
+	ret	lr
 
 /* ================================= CACHE ================================ */
 
@@ -133,7 +133,7 @@  ENTRY(arm1020e_flush_icache_all)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 #endif
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm1020e_flush_icache_all)
 
 /*
@@ -168,7 +168,7 @@  __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)
@@ -197,7 +197,7 @@  ENTRY(arm1020e_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)
@@ -236,7 +236,7 @@  ENTRY(arm1020e_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)
@@ -257,7 +257,7 @@  ENTRY(arm1020e_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)
@@ -286,7 +286,7 @@  arm1020e_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)
@@ -308,7 +308,7 @@  arm1020e_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)
@@ -328,7 +328,7 @@  ENTRY(arm1020e_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)
@@ -351,7 +351,7 @@  ENDPROC(arm1020e_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(arm1020e_dma_unmap_area)
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm1020e_dma_unmap_area)
 
 	.globl	arm1020e_flush_kern_cache_louis
@@ -369,7 +369,7 @@  ENTRY(cpu_arm1020e_dcache_clean_area)
 	subs	r1, r1, #CACHE_DLINESIZE
 	bhi	1b
 #endif
-	mov	pc, lr
+	ret	lr
 
 /* =============================== PageTable ============================== */
 
@@ -407,7 +407,7 @@  ENTRY(cpu_arm1020e_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_arm1020e_set_pte(ptep, pte)
@@ -423,7 +423,7 @@  ENTRY(cpu_arm1020e_set_pte_ext)
 	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 #endif
 #endif /* CONFIG_MMU */
-	mov	pc, lr
+	ret	lr
 
 	.type	__arm1020e_setup, #function
 __arm1020e_setup:
@@ -441,7 +441,7 @@  __arm1020e_setup:
 #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN
 	orr	r0, r0, #0x4000 		@ .R.. .... .... ....
 #endif
-	mov	pc, lr
+	ret	lr
 	.size	__arm1020e_setup, . - __arm1020e_setup
 
 	/*
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
 
 	/*
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index 4799a24b43e6..fc294067e977 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -62,7 +62,7 @@ 
  * cpu_arm1026_proc_init()
  */
 ENTRY(cpu_arm1026_proc_init)
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_arm1026_proc_fin()
@@ -72,7 +72,7 @@  ENTRY(cpu_arm1026_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_arm1026_reset(loc)
@@ -96,7 +96,7 @@  ENTRY(cpu_arm1026_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_arm1026_reset)
 	.popsection
 
@@ -106,7 +106,7 @@  ENDPROC(cpu_arm1026_reset)
 	.align	5
 ENTRY(cpu_arm1026_do_idle)
 	mcr	p15, 0, r0, c7, c0, 4		@ Wait for interrupt
-	mov	pc, lr
+	ret	lr
 
 /* ================================= CACHE ================================ */
 
@@ -122,7 +122,7 @@  ENTRY(arm1026_flush_icache_all)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 #endif
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm1026_flush_icache_all)
 
 /*
@@ -151,7 +151,7 @@  __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)
@@ -180,7 +180,7 @@  ENTRY(arm1026_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)
@@ -219,7 +219,7 @@  ENTRY(arm1026_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)
@@ -240,7 +240,7 @@  ENTRY(arm1026_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)
@@ -269,7 +269,7 @@  arm1026_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)
@@ -291,7 +291,7 @@  arm1026_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)
@@ -311,7 +311,7 @@  ENTRY(arm1026_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)
@@ -334,7 +334,7 @@  ENDPROC(arm1026_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(arm1026_dma_unmap_area)
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm1026_dma_unmap_area)
 
 	.globl	arm1026_flush_kern_cache_louis
@@ -352,7 +352,7 @@  ENTRY(cpu_arm1026_dcache_clean_area)
 	subs	r1, r1, #CACHE_DLINESIZE
 	bhi	1b
 #endif
-	mov	pc, lr
+	ret	lr
 
 /* =============================== PageTable ============================== */
 
@@ -378,7 +378,7 @@  ENTRY(cpu_arm1026_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_arm1026_set_pte_ext(ptep, pte, ext)
@@ -394,7 +394,7 @@  ENTRY(cpu_arm1026_set_pte_ext)
 	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 #endif
 #endif /* CONFIG_MMU */
-	mov	pc, lr
+	ret	lr
 
 	.type	__arm1026_setup, #function
 __arm1026_setup:
@@ -417,7 +417,7 @@  __arm1026_setup:
 #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN
 	orr	r0, r0, #0x4000 		@ .R.. .... .... ....
 #endif
-	mov	pc, lr
+	ret	lr
 	.size	__arm1026_setup, . - __arm1026_setup
 
 	/*
diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S
index d42c37f9f5bc..2baa66b3ac9b 100644
--- a/arch/arm/mm/proc-arm720.S
+++ b/arch/arm/mm/proc-arm720.S
@@ -51,14 +51,14 @@ 
  */
 ENTRY(cpu_arm720_dcache_clean_area)
 ENTRY(cpu_arm720_proc_init)
-		mov	pc, lr
+		ret	lr
 
 ENTRY(cpu_arm720_proc_fin)
 		mrc	p15, 0, r0, c1, c0, 0
 		bic	r0, r0, #0x1000			@ ...i............
 		bic	r0, r0, #0x000e			@ ............wca.
 		mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-		mov	pc, lr
+		ret	lr
 
 /*
  * Function: arm720_proc_do_idle(void)
@@ -66,7 +66,7 @@  ENTRY(cpu_arm720_proc_fin)
  * Purpose : put the processor in proper idle mode
  */
 ENTRY(cpu_arm720_do_idle)
-		mov	pc, lr
+		ret	lr
 
 /*
  * Function: arm720_switch_mm(unsigned long pgd_phys)
@@ -81,7 +81,7 @@  ENTRY(cpu_arm720_switch_mm)
 		mcr	p15, 0, r0, c2, c0, 0		@ update page table ptr
 		mcr	p15, 0, r1, c8, c7, 0		@ flush TLB (v4)
 #endif
-		mov	pc, lr
+		ret	lr
 
 /*
  * Function: arm720_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext)
@@ -94,7 +94,7 @@  ENTRY(cpu_arm720_set_pte_ext)
 #ifdef CONFIG_MMU
 	armv3_set_pte_ext wc_disable=0
 #endif
-	mov	pc, lr
+	ret	lr
 
 /*
  * Function: arm720_reset
@@ -112,7 +112,7 @@  ENTRY(cpu_arm720_reset)
 		bic	ip, ip, #0x000f			@ ............wcam
 		bic	ip, ip, #0x2100			@ ..v....s........
 		mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
-		mov	pc, r0
+		ret	r0
 ENDPROC(cpu_arm720_reset)
 		.popsection
 
@@ -128,7 +128,7 @@  __arm710_setup:
 	bic	r0, r0, r5
 	ldr	r5, arm710_cr1_set
 	orr	r0, r0, r5
-	mov	pc, lr				@ __ret (head.S)
+	ret	lr				@ __ret (head.S)
 	.size	__arm710_setup, . - __arm710_setup
 
 	/*
@@ -156,7 +156,7 @@  __arm720_setup:
 	mrc	p15, 0, r0, c1, c0		@ get control register
 	bic	r0, r0, r5
 	orr	r0, r0, r6
-	mov	pc, lr				@ __ret (head.S)
+	ret	lr				@ __ret (head.S)
 	.size	__arm720_setup, . - __arm720_setup
 
 	/*
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index 9b0ae90cbf17..ac1ea6b3bce4 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -32,7 +32,7 @@  ENTRY(cpu_arm740_proc_init)
 ENTRY(cpu_arm740_do_idle)
 ENTRY(cpu_arm740_dcache_clean_area)
 ENTRY(cpu_arm740_switch_mm)
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_arm740_proc_fin()
@@ -42,7 +42,7 @@  ENTRY(cpu_arm740_proc_fin)
 	bic	r0, r0, #0x3f000000		@ bank/f/lock/s
 	bic	r0, r0, #0x0000000c		@ w-buffer/cache
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_arm740_reset(loc)
@@ -56,7 +56,7 @@  ENTRY(cpu_arm740_reset)
 	mrc	p15, 0, ip, c1, c0, 0		@ get ctrl register
 	bic	ip, ip, #0x0000000c		@ ............wc..
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
-	mov	pc, r0
+	ret	r0
 ENDPROC(cpu_arm740_reset)
 	.popsection
 
@@ -115,7 +115,7 @@  __arm740_setup:
 						@ need some benchmark
 	orr	r0, r0, #0x0000000d		@ MPU/Cache/WB
 
-	mov	pc, lr
+	ret	lr
 
 	.size	__arm740_setup, . - __arm740_setup
 
diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S
index f6cc3f63ce39..bf6ba4bc30ff 100644
--- a/arch/arm/mm/proc-arm7tdmi.S
+++ b/arch/arm/mm/proc-arm7tdmi.S
@@ -32,13 +32,13 @@  ENTRY(cpu_arm7tdmi_proc_init)
 ENTRY(cpu_arm7tdmi_do_idle)
 ENTRY(cpu_arm7tdmi_dcache_clean_area)
 ENTRY(cpu_arm7tdmi_switch_mm)
-		mov	pc, lr
+		ret	lr
 
 /*
  * cpu_arm7tdmi_proc_fin()
  */
 ENTRY(cpu_arm7tdmi_proc_fin)
-		mov	pc, lr
+		ret	lr
 
 /*
  * Function: cpu_arm7tdmi_reset(loc)
@@ -47,13 +47,13 @@  ENTRY(cpu_arm7tdmi_proc_fin)
  */
 		.pushsection	.idmap.text, "ax"
 ENTRY(cpu_arm7tdmi_reset)
-		mov	pc, r0
+		ret	r0
 ENDPROC(cpu_arm7tdmi_reset)
 		.popsection
 
 		.type	__arm7tdmi_setup, #function
 __arm7tdmi_setup:
-		mov	pc, lr
+		ret	lr
 		.size	__arm7tdmi_setup, . - __arm7tdmi_setup
 
 		__INITDATA
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
 
 	/*
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index 2a758b06c6f6..0c6d5ac5a6d4 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -65,7 +65,7 @@ 
  * cpu_arm922_proc_init()
  */
 ENTRY(cpu_arm922_proc_init)
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_arm922_proc_fin()
@@ -75,7 +75,7 @@  ENTRY(cpu_arm922_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_arm922_reset(loc)
@@ -99,7 +99,7 @@  ENTRY(cpu_arm922_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_arm922_reset)
 	.popsection
 
@@ -109,7 +109,7 @@  ENDPROC(cpu_arm922_reset)
 	.align	5
 ENTRY(cpu_arm922_do_idle)
 	mcr	p15, 0, r0, c7, c0, 4		@ Wait for interrupt
-	mov	pc, lr
+	ret	lr
 
 
 #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
@@ -122,7 +122,7 @@  ENTRY(cpu_arm922_do_idle)
 ENTRY(arm922_flush_icache_all)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm922_flush_icache_all)
 
 /*
@@ -153,7 +153,7 @@  __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)
@@ -179,7 +179,7 @@  ENTRY(arm922_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)
@@ -213,7 +213,7 @@  ENTRY(arm922_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)
@@ -233,7 +233,7 @@  ENTRY(arm922_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)
@@ -259,7 +259,7 @@  arm922_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)
@@ -278,7 +278,7 @@  arm922_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)
@@ -295,7 +295,7 @@  ENTRY(arm922_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)
@@ -318,7 +318,7 @@  ENDPROC(arm922_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(arm922_dma_unmap_area)
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm922_dma_unmap_area)
 
 	.globl	arm922_flush_kern_cache_louis
@@ -336,7 +336,7 @@  ENTRY(cpu_arm922_dcache_clean_area)
 	subs	r1, r1, #CACHE_DLINESIZE
 	bhi	1b
 #endif
-	mov	pc, lr
+	ret	lr
 
 /* =============================== PageTable ============================== */
 
@@ -371,7 +371,7 @@  ENTRY(cpu_arm922_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_arm922_set_pte_ext(ptep, pte, ext)
@@ -386,7 +386,7 @@  ENTRY(cpu_arm922_set_pte_ext)
 	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 #endif /* CONFIG_MMU */
-	mov	pc, lr
+	ret	lr
 
 	.type	__arm922_setup, #function
 __arm922_setup:
@@ -401,7 +401,7 @@  __arm922_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	__arm922_setup, . - __arm922_setup
 
 	/*
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index ba0d58e1a2a2..c32d073282ea 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -86,7 +86,7 @@ 
  * cpu_arm925_proc_init()
  */
 ENTRY(cpu_arm925_proc_init)
-	mov	pc, lr
+	ret	lr
 
 /*
  * cpu_arm925_proc_fin()
@@ -96,7 +96,7 @@  ENTRY(cpu_arm925_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_arm925_reset(loc)
@@ -129,7 +129,7 @@  ENDPROC(cpu_arm925_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
 
 /*
  * cpu_arm925_do_idle()
@@ -145,7 +145,7 @@  ENTRY(cpu_arm925_do_idle)
 	mcr	p15, 0, r2, c1, c0, 0		@ Disable I cache
 	mcr	p15, 0, r0, c7, c0, 4		@ Wait for interrupt
 	mcr	p15, 0, r1, c1, c0, 0		@ Restore ICache enable
-	mov	pc, lr
+	ret	lr
 
 /*
  *	flush_icache_all()
@@ -155,7 +155,7 @@  ENTRY(cpu_arm925_do_idle)
 ENTRY(arm925_flush_icache_all)
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm925_flush_icache_all)
 
 /*
@@ -188,7 +188,7 @@  __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)
@@ -225,7 +225,7 @@  ENTRY(arm925_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)
@@ -259,7 +259,7 @@  ENTRY(arm925_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)
@@ -279,7 +279,7 @@  ENTRY(arm925_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)
@@ -307,7 +307,7 @@  arm925_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)
@@ -328,7 +328,7 @@  arm925_dma_clean_range:
 	blo	1b
 #endif
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /*
  *	dma_flush_range(start, end)
@@ -350,7 +350,7 @@  ENTRY(arm925_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)
@@ -373,7 +373,7 @@  ENDPROC(arm925_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(arm925_dma_unmap_area)
-	mov	pc, lr
+	ret	lr
 ENDPROC(arm925_dma_unmap_area)
 
 	.globl	arm925_flush_kern_cache_louis
@@ -390,7 +390,7 @@  ENTRY(cpu_arm925_dcache_clean_area)
 	bhi	1b
 #endif
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
-	mov	pc, lr
+	ret	lr
 
 /* =============================== PageTable ============================== */
 
@@ -419,7 +419,7 @@  ENTRY(cpu_arm925_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_arm925_set_pte_ext(ptep, pte, ext)
@@ -436,7 +436,7 @@  ENTRY(cpu_arm925_set_pte_ext)
 #endif
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 #endif /* CONFIG_MMU */
-	mov	pc, lr
+	ret	lr
 
 	.type	__arm925_setup, #function
 __arm925_setup:
@@ -469,7 +469,7 @@  __arm925_setup:
 #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN
 	orr	r0, r0, #0x4000			@ .1.. .... .... ....
 #endif
-	mov	pc, lr
+	ret	lr
 	.size	__arm925_setup, . - __arm925_setup
 
 	/*