Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM changes from Russell King:

 - Perf updates from Will Deacon:
   - Support for Qualcomm Krait processors (run perf on your phone!)
   - Support for Cortex-A12 (run perf stat on your FPGA!)
   - Support for perf_sample_event_took, allowing us to automatically decrease
     the sample rate if we can't handle the PMU interrupts quickly enough
     (run perf record on your FPGA!).

 - Basic uprobes support from David Long:
     This patch series adds basic uprobes support to ARM. It is based on
     patches developed earlier by Rabin Vincent. That approach of adding
     hooks into the kprobes instruction parsing code was not well received.
     This approach separates the ARM instruction parsing code in kprobes out
     into a separate set of functions which can be used by both kprobes and
     uprobes. Both kprobes and uprobes then provide their own semantic action
     tables to process the results of the parsing.

 - ARMv7M (microcontroller) updates from Uwe Kleine-König

 - OMAP DMA updates (recently added Vinod's Ack even though they've been
   sitting in linux-next for a few months) to reduce the reliance of
   omap-dma on the code in arch/arm.

 - SA11x0 changes from Dmitry Eremin-Solenikov and Alexander Shiyan

 - Support for Cortex-A12 CPU

 - Align support for ARMv6 with ARMv7 so they can cooperate better in a
   single zImage.

 - Addition of first AT_HWCAP2 feature bits for ARMv8 crypto support.

 - Removal of IRQ_DISABLED from various ARM files

 - Improved efficiency of virt_to_page() for single zImage

 - Patch from Ulf Hansson to permit runtime PM callbacks to be available for
   AMBA devices for suspend/resume as well.

 - Finally kill asm/system.h on ARM.

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (89 commits)
  dmaengine: omap-dma: more consolidation of CCR register setup
  dmaengine: omap-dma: move IRQ handling to omap-dma
  dmaengine: omap-dma: move register read/writes into omap-dma.c
  ARM: omap: dma: get rid of 'p' allocation and clean up
  ARM: omap: move dma channel allocation into plat-omap code
  ARM: omap: dma: get rid of errata global
  ARM: omap: clean up DMA register accesses
  ARM: omap: remove almost-const variables
  ARM: omap: remove references to disable_irq_lch
  dmaengine: omap-dma: cleanup errata 3.3 handling
  dmaengine: omap-dma: provide register read/write functions
  dmaengine: omap-dma: use cached CCR value when enabling DMA
  dmaengine: omap-dma: move barrier to omap_dma_start_desc()
  dmaengine: omap-dma: move clnk_ctrl setting to preparation functions
  dmaengine: omap-dma: improve efficiency loading C.SA/C.EI/C.FI registers
  dmaengine: omap-dma: consolidate clearing channel status register
  dmaengine: omap-dma: move CCR buffering disable errata out of the fast path
  dmaengine: omap-dma: provide register definitions
  dmaengine: omap-dma: consolidate setup of CCR
  dmaengine: omap-dma: consolidate setup of CSDP
  ...

7 files changed, 197 insertions, 192 deletions

diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index 52886b89706c..9f12ed1eea86 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -37,6 +37,11 @@ UNWIND(	.fnstart	)
 	add	r1, r1, r0, lsl #2	@ Get word offset
 	mov	r3, r2, lsl r3		@ create mask
 	smp_dmb
+#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+	.arch_extension	mp
+	ALT_SMP(W(pldw)	[r1])
+	ALT_UP(W(nop))
+#endif
 1:	ldrex	r2, [r1]
 	ands	r0, r2, r3		@ save old value of bit
 	\instr	r2, r2, r3		@ toggle bit
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S
index 805e3f8fb007..3bc8eb811a73 100644
--- a/arch/arm/lib/copy_template.S
+++ b/arch/arm/lib/copy_template.S
@@ -197,24 +197,24 @@
 
 12:	PLD(	pld	[r1, #124]		)
 13:		ldr4w	r1, r4, r5, r6, r7, abort=19f
-		mov	r3, lr, pull #\pull
+		mov	r3, lr, lspull #\pull
 		subs	r2, r2, #32
 		ldr4w	r1, r8, r9, ip, lr, abort=19f
-		orr	r3, r3, r4, push #\push
-		mov	r4, r4, pull #\pull
-		orr	r4, r4, r5, push #\push
-		mov	r5, r5, pull #\pull
-		orr	r5, r5, r6, push #\push
-		mov	r6, r6, pull #\pull
-		orr	r6, r6, r7, push #\push
-		mov	r7, r7, pull #\pull
-		orr	r7, r7, r8, push #\push
-		mov	r8, r8, pull #\pull
-		orr	r8, r8, r9, push #\push
-		mov	r9, r9, pull #\pull
-		orr	r9, r9, ip, push #\push
-		mov	ip, ip, pull #\pull
-		orr	ip, ip, lr, push #\push
+		orr	r3, r3, r4, lspush #\push
+		mov	r4, r4, lspull #\pull
+		orr	r4, r4, r5, lspush #\push
+		mov	r5, r5, lspull #\pull
+		orr	r5, r5, r6, lspush #\push
+		mov	r6, r6, lspull #\pull
+		orr	r6, r6, r7, lspush #\push
+		mov	r7, r7, lspull #\pull
+		orr	r7, r7, r8, lspush #\push
+		mov	r8, r8, lspull #\pull
+		orr	r8, r8, r9, lspush #\push
+		mov	r9, r9, lspull #\pull
+		orr	r9, r9, ip, lspush #\push
+		mov	ip, ip, lspull #\pull
+		orr	ip, ip, lr, lspush #\push
 		str8w	r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f
 		bge	12b
 	PLD(	cmn	r2, #96			)
@@ -225,10 +225,10 @@
 14:		ands	ip, r2, #28
 		beq	16f
 
-15:		mov	r3, lr, pull #\pull
+15:		mov	r3, lr, lspull #\pull
 		ldr1w	r1, lr, abort=21f
 		subs	ip, ip, #4
-		orr	r3, r3, lr, push #\push
+		orr	r3, r3, lr, lspush #\push
 		str1w	r0, r3, abort=21f
 		bgt	15b
 	CALGN(	cmp	r2, #0			)
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index d620a5f22a09..d6e742d24007 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -141,7 +141,7 @@ FN_ENTRY
 		tst	len, #2
 		mov	r5, r4, get_byte_0
 		beq	.Lexit
-		adcs	sum, sum, r4, push #16
+		adcs	sum, sum, r4, lspush #16
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_1
 		strb	r5, [dst], #1
@@ -171,23 +171,23 @@ FN_ENTRY
 		cmp	ip, #2
 		beq	.Lsrc2_aligned
 		bhi	.Lsrc3_aligned
-		mov	r4, r5, pull #8		@ C = 0
+		mov	r4, r5, lspull #8		@ C = 0
 		bics	ip, len, #15
 		beq	2f
 1:		load4l	r5, r6, r7, r8
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
-		mov	r6, r6, pull #8
-		orr	r6, r6, r7, push #24
-		mov	r7, r7, pull #8
-		orr	r7, r7, r8, push #24
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
+		mov	r6, r6, lspull #8
+		orr	r6, r6, r7, lspush #24
+		mov	r7, r7, lspull #8
+		orr	r7, r7, r8, lspush #24
 		stmia	dst!, {r4, r5, r6, r7}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
 		adcs	sum, sum, r6
 		adcs	sum, sum, r7
-		mov	r4, r8, pull #8
+		mov	r4, r8, lspull #8
 		sub	ip, ip, #16
 		teq	ip, #0
 		bne	1b
@@ -196,50 +196,50 @@ FN_ENTRY
 		tst	ip, #8
 		beq	3f
 		load2l	r5, r6
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
 		stmia	dst!, {r4, r5}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
-		mov	r4, r6, pull #8
+		mov	r4, r6, lspull #8
 		tst	ip, #4
 		beq	4f
 3:		load1l	r5
-		orr	r4, r4, r5, push #24
+		orr	r4, r4, r5, lspush #24
 		str	r4, [dst], #4
 		adcs	sum, sum, r4
-		mov	r4, r5, pull #8
+		mov	r4, r5, lspull #8
 4:		ands	len, len, #3
 		beq	.Ldone
 		mov	r5, r4, get_byte_0
 		tst	len, #2
 		beq	.Lexit
-		adcs	sum, sum, r4, push #16
+		adcs	sum, sum, r4, lspush #16
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_1
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_2
 		b	.Lexit
 
-.Lsrc2_aligned:	mov	r4, r5, pull #16
+.Lsrc2_aligned:	mov	r4, r5, lspull #16
 		adds	sum, sum, #0
 		bics	ip, len, #15
 		beq	2f
 1:		load4l	r5, r6, r7, r8
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
-		mov	r6, r6, pull #16
-		orr	r6, r6, r7, push #16
-		mov	r7, r7, pull #16
-		orr	r7, r7, r8, push #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
+		mov	r6, r6, lspull #16
+		orr	r6, r6, r7, lspush #16
+		mov	r7, r7, lspull #16
+		orr	r7, r7, r8, lspush #16
 		stmia	dst!, {r4, r5, r6, r7}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
 		adcs	sum, sum, r6
 		adcs	sum, sum, r7
-		mov	r4, r8, pull #16
+		mov	r4, r8, lspull #16
 		sub	ip, ip, #16
 		teq	ip, #0
 		bne	1b
@@ -248,20 +248,20 @@ FN_ENTRY
 		tst	ip, #8
 		beq	3f
 		load2l	r5, r6
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
 		stmia	dst!, {r4, r5}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
-		mov	r4, r6, pull #16
+		mov	r4, r6, lspull #16
 		tst	ip, #4
 		beq	4f
 3:		load1l	r5
-		orr	r4, r4, r5, push #16
+		orr	r4, r4, r5, lspush #16
 		str	r4, [dst], #4
 		adcs	sum, sum, r4
-		mov	r4, r5, pull #16
+		mov	r4, r5, lspull #16
 4:		ands	len, len, #3
 		beq	.Ldone
 		mov	r5, r4, get_byte_0
@@ -276,24 +276,24 @@ FN_ENTRY
 		load1b	r5
 		b	.Lexit
 
-.Lsrc3_aligned:	mov	r4, r5, pull #24
+.Lsrc3_aligned:	mov	r4, r5, lspull #24
 		adds	sum, sum, #0
 		bics	ip, len, #15
 		beq	2f
 1:		load4l	r5, r6, r7, r8
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
-		mov	r6, r6, pull #24
-		orr	r6, r6, r7, push #8
-		mov	r7, r7, pull #24
-		orr	r7, r7, r8, push #8
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
+		mov	r6, r6, lspull #24
+		orr	r6, r6, r7, lspush #8
+		mov	r7, r7, lspull #24
+		orr	r7, r7, r8, lspush #8
 		stmia	dst!, {r4, r5, r6, r7}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
 		adcs	sum, sum, r6
 		adcs	sum, sum, r7
-		mov	r4, r8, pull #24
+		mov	r4, r8, lspull #24
 		sub	ip, ip, #16
 		teq	ip, #0
 		bne	1b
@@ -302,20 +302,20 @@ FN_ENTRY
 		tst	ip, #8
 		beq	3f
 		load2l	r5, r6
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
 		stmia	dst!, {r4, r5}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
-		mov	r4, r6, pull #24
+		mov	r4, r6, lspull #24
 		tst	ip, #4
 		beq	4f
 3:		load1l	r5
-		orr	r4, r4, r5, push #8
+		orr	r4, r4, r5, lspush #8
 		str	r4, [dst], #4
 		adcs	sum, sum, r4
-		mov	r4, r5, pull #24
+		mov	r4, r5, lspull #24
 4:		ands	len, len, #3
 		beq	.Ldone
 		mov	r5, r4, get_byte_0
@@ -326,7 +326,7 @@ FN_ENTRY
 		load1l	r4
 		mov	r5, r4, get_byte_0
 		strb	r5, [dst], #1
-		adcs	sum, sum, r4, push #24
+		adcs	sum, sum, r4, lspush #24
 		mov	r5, r4, get_byte_1
 		b	.Lexit
 FN_EXIT
diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S
index 5fb97e7f9f4b..7a7430950c79 100644
--- a/arch/arm/lib/io-readsl.S
+++ b/arch/arm/lib/io-readsl.S
@@ -47,25 +47,25 @@ ENTRY(__raw_readsl)
 		strb	ip, [r1], #1
 
 4:		subs	r2, r2, #1
-		mov	ip, r3, pull #24
+		mov	ip, r3, lspull #24
 		ldrne	r3, [r0]
-		orrne	ip, ip, r3, push #8
+		orrne	ip, ip, r3, lspush #8
 		strne	ip, [r1], #4
 		bne	4b
 		b	8f
 
 5:		subs	r2, r2, #1
-		mov	ip, r3, pull #16
+		mov	ip, r3, lspull #16
 		ldrne	r3, [r0]
-		orrne	ip, ip, r3, push #16
+		orrne	ip, ip, r3, lspush #16
 		strne	ip, [r1], #4
 		bne	5b
 		b	7f
 
 6:		subs	r2, r2, #1
-		mov	ip, r3, pull #8
+		mov	ip, r3, lspull #8
 		ldrne	r3, [r0]
-		orrne	ip, ip, r3, push #24
+		orrne	ip, ip, r3, lspush #24
 		strne	ip, [r1], #4
 		bne	6b
 
diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S
index 8d3b7813725c..d0d104a0dd11 100644
--- a/arch/arm/lib/io-writesl.S
+++ b/arch/arm/lib/io-writesl.S
@@ -41,26 +41,26 @@ ENTRY(__raw_writesl)
 		blt	5f
 		bgt	6f
 
-4:		mov	ip, r3, pull #16
+4:		mov	ip, r3, lspull #16
 		ldr	r3, [r1], #4
 		subs	r2, r2, #1
-		orr	ip, ip, r3, push #16
+		orr	ip, ip, r3, lspush #16
 		str	ip, [r0]
 		bne	4b
 		mov	pc, lr
 
-5:		mov	ip, r3, pull #8
+5:		mov	ip, r3, lspull #8
 		ldr	r3, [r1], #4
 		subs	r2, r2, #1
-		orr	ip, ip, r3, push #24
+		orr	ip, ip, r3, lspush #24
 		str	ip, [r0]
 		bne	5b
 		mov	pc, lr
 
-6:		mov	ip, r3, pull #24
+6:		mov	ip, r3, lspull #24
 		ldr	r3, [r1], #4
 		subs	r2, r2, #1
-		orr	ip, ip, r3, push #8
+		orr	ip, ip, r3, lspush #8
 		str	ip, [r0]
 		bne	6b
 		mov	pc, lr
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index 938fc14f962d..d1fc0c0c342c 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -147,24 +147,24 @@ ENTRY(memmove)
 
 12:	PLD(	pld	[r1, #-128]		)
 13:		ldmdb   r1!, {r7, r8, r9, ip}
-		mov     lr, r3, push #\push
+		mov     lr, r3, lspush #\push
 		subs    r2, r2, #32
 		ldmdb   r1!, {r3, r4, r5, r6}
-		orr     lr, lr, ip, pull #\pull
-		mov     ip, ip, push #\push
-		orr     ip, ip, r9, pull #\pull
-		mov     r9, r9, push #\push
-		orr     r9, r9, r8, pull #\pull
-		mov     r8, r8, push #\push
-		orr     r8, r8, r7, pull #\pull
-		mov     r7, r7, push #\push
-		orr     r7, r7, r6, pull #\pull
-		mov     r6, r6, push #\push
-		orr     r6, r6, r5, pull #\pull
-		mov     r5, r5, push #\push
-		orr     r5, r5, r4, pull #\pull
-		mov     r4, r4, push #\push
-		orr     r4, r4, r3, pull #\pull
+		orr     lr, lr, ip, lspull #\pull
+		mov     ip, ip, lspush #\push
+		orr     ip, ip, r9, lspull #\pull
+		mov     r9, r9, lspush #\push
+		orr     r9, r9, r8, lspull #\pull
+		mov     r8, r8, lspush #\push
+		orr     r8, r8, r7, lspull #\pull
+		mov     r7, r7, lspush #\push
+		orr     r7, r7, r6, lspull #\pull
+		mov     r6, r6, lspush #\push
+		orr     r6, r6, r5, lspull #\pull
+		mov     r5, r5, lspush #\push
+		orr     r5, r5, r4, lspull #\pull
+		mov     r4, r4, lspush #\push
+		orr     r4, r4, r3, lspull #\pull
 		stmdb   r0!, {r4 - r9, ip, lr}
 		bge	12b
 	PLD(	cmn	r2, #96			)
@@ -175,10 +175,10 @@ ENTRY(memmove)
 14:		ands	ip, r2, #28
 		beq	16f
 
-15:		mov     lr, r3, push #\push
+15:		mov     lr, r3, lspush #\push
 		ldr	r3, [r1, #-4]!
 		subs	ip, ip, #4
-		orr	lr, lr, r3, pull #\pull
+		orr	lr, lr, r3, lspull #\pull
 		str	lr, [r0, #-4]!
 		bgt	15b
 	CALGN(	cmp	r2, #0			)
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
index 5c908b1cb8ed..e50520904b76 100644
--- a/arch/arm/lib/uaccess.S
+++ b/arch/arm/lib/uaccess.S
@@ -117,9 +117,9 @@ USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
 .Lc2u_1fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lc2u_1nowords
-		mov	r3, r7, pull #8
+		mov	r3, r7, lspull #8
 		ldr	r7, [r1], #4
-		orr	r3, r3, r7, push #24
+		orr	r3, r3, r7, lspush #24
 USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -131,30 +131,30 @@ USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lc2u_1rem8lp
 
-.Lc2u_1cpy8lp:	mov	r3, r7, pull #8
+.Lc2u_1cpy8lp:	mov	r3, r7, lspull #8
 		ldmia	r1!, {r4 - r7}
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #24
-		mov	r4, r4, pull #8
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
-		mov	r6, r6, pull #8
-		orr	r6, r6, r7, push #24
+		orr	r3, r3, r4, lspush #24
+		mov	r4, r4, lspull #8
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
+		mov	r6, r6, lspull #8
+		orr	r6, r6, r7, lspush #24
 		stmia	r0!, {r3 - r6}			@ Shouldnt fault
 		bpl	.Lc2u_1cpy8lp
 
 .Lc2u_1rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 		ldmneia	r1!, {r4, r7}
-		orrne	r3, r3, r4, push #24
-		movne	r4, r4, pull #8
-		orrne	r4, r4, r7, push #24
+		orrne	r3, r3, r4, lspush #24
+		movne	r4, r4, lspull #8
+		orrne	r4, r4, r7, lspush #24
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 		ldrne	r7, [r1], #4
-		orrne	r3, r3, r7, push #24
+		orrne	r3, r3, r7, lspush #24
 	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_1fupi
@@ -172,9 +172,9 @@ USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
 .Lc2u_2fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lc2u_2nowords
-		mov	r3, r7, pull #16
+		mov	r3, r7, lspull #16
 		ldr	r7, [r1], #4
-		orr	r3, r3, r7, push #16
+		orr	r3, r3, r7, lspush #16
 USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -186,30 +186,30 @@ USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lc2u_2rem8lp
 
-.Lc2u_2cpy8lp:	mov	r3, r7, pull #16
+.Lc2u_2cpy8lp:	mov	r3, r7, lspull #16
 		ldmia	r1!, {r4 - r7}
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #16
-		mov	r4, r4, pull #16
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
-		mov	r6, r6, pull #16
-		orr	r6, r6, r7, push #16
+		orr	r3, r3, r4, lspush #16
+		mov	r4, r4, lspull #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
+		mov	r6, r6, lspull #16
+		orr	r6, r6, r7, lspush #16
 		stmia	r0!, {r3 - r6}			@ Shouldnt fault
 		bpl	.Lc2u_2cpy8lp
 
 .Lc2u_2rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 		ldmneia	r1!, {r4, r7}
-		orrne	r3, r3, r4, push #16
-		movne	r4, r4, pull #16
-		orrne	r4, r4, r7, push #16
+		orrne	r3, r3, r4, lspush #16
+		movne	r4, r4, lspull #16
+		orrne	r4, r4, r7, lspush #16
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 		ldrne	r7, [r1], #4
-		orrne	r3, r3, r7, push #16
+		orrne	r3, r3, r7, lspush #16
 	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_2fupi
@@ -227,9 +227,9 @@ USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
 .Lc2u_3fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lc2u_3nowords
-		mov	r3, r7, pull #24
+		mov	r3, r7, lspull #24
 		ldr	r7, [r1], #4
-		orr	r3, r3, r7, push #8
+		orr	r3, r3, r7, lspush #8
 USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -241,30 +241,30 @@ USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lc2u_3rem8lp
 
-.Lc2u_3cpy8lp:	mov	r3, r7, pull #24
+.Lc2u_3cpy8lp:	mov	r3, r7, lspull #24
 		ldmia	r1!, {r4 - r7}
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #8
-		mov	r4, r4, pull #24
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
-		mov	r6, r6, pull #24
-		orr	r6, r6, r7, push #8
+		orr	r3, r3, r4, lspush #8
+		mov	r4, r4, lspull #24
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
+		mov	r6, r6, lspull #24
+		orr	r6, r6, r7, lspush #8
 		stmia	r0!, {r3 - r6}			@ Shouldnt fault
 		bpl	.Lc2u_3cpy8lp
 
 .Lc2u_3rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 		ldmneia	r1!, {r4, r7}
-		orrne	r3, r3, r4, push #8
-		movne	r4, r4, pull #24
-		orrne	r4, r4, r7, push #8
+		orrne	r3, r3, r4, lspush #8
+		movne	r4, r4, lspull #24
+		orrne	r4, r4, r7, lspush #8
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 		ldrne	r7, [r1], #4
-		orrne	r3, r3, r7, push #8
+		orrne	r3, r3, r7, lspush #8
 	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_3fupi
@@ -382,9 +382,9 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 .Lcfu_1fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_1nowords
-		mov	r3, r7, pull #8
+		mov	r3, r7, lspull #8
 USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
-		orr	r3, r3, r7, push #24
+		orr	r3, r3, r7, lspush #24
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -396,30 +396,30 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lcfu_1rem8lp
 
-.Lcfu_1cpy8lp:	mov	r3, r7, pull #8
+.Lcfu_1cpy8lp:	mov	r3, r7, lspull #8
 		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #24
-		mov	r4, r4, pull #8
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
-		mov	r6, r6, pull #8
-		orr	r6, r6, r7, push #24
+		orr	r3, r3, r4, lspush #24
+		mov	r4, r4, lspull #8
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
+		mov	r6, r6, lspull #8
+		orr	r6, r6, r7, lspush #24
 		stmia	r0!, {r3 - r6}
 		bpl	.Lcfu_1cpy8lp
 
 .Lcfu_1rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
-		orrne	r3, r3, r4, push #24
-		movne	r4, r4, pull #8
-		orrne	r4, r4, r7, push #24
+		orrne	r3, r3, r4, lspush #24
+		movne	r4, r4, lspull #8
+		orrne	r4, r4, r7, lspush #24
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
-		orrne	r3, r3, r7, push #24
+		orrne	r3, r3, r7, lspush #24
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_1fupi
@@ -437,9 +437,9 @@ USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
 .Lcfu_2fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_2nowords
-		mov	r3, r7, pull #16
+		mov	r3, r7, lspull #16
 USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
-		orr	r3, r3, r7, push #16
+		orr	r3, r3, r7, lspush #16
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -452,30 +452,30 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 		blt	.Lcfu_2rem8lp
 
 
-.Lcfu_2cpy8lp:	mov	r3, r7, pull #16
+.Lcfu_2cpy8lp:	mov	r3, r7, lspull #16
 		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #16
-		mov	r4, r4, pull #16
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
-		mov	r6, r6, pull #16
-		orr	r6, r6, r7, push #16
+		orr	r3, r3, r4, lspush #16
+		mov	r4, r4, lspull #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
+		mov	r6, r6, lspull #16
+		orr	r6, r6, r7, lspush #16
 		stmia	r0!, {r3 - r6}
 		bpl	.Lcfu_2cpy8lp
 
 .Lcfu_2rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
-		orrne	r3, r3, r4, push #16
-		movne	r4, r4, pull #16
-		orrne	r4, r4, r7, push #16
+		orrne	r3, r3, r4, lspush #16
+		movne	r4, r4, lspull #16
+		orrne	r4, r4, r7, lspush #16
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
-		orrne	r3, r3, r7, push #16
+		orrne	r3, r3, r7, lspush #16
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_2fupi
@@ -493,9 +493,9 @@ USER(	TUSER(	ldrgtb) r3, [r1], #0)			@ May fault
 .Lcfu_3fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_3nowords
-		mov	r3, r7, pull #24
+		mov	r3, r7, lspull #24
 USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
-		orr	r3, r3, r7, push #8
+		orr	r3, r3, r7, lspush #8
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -507,30 +507,30 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lcfu_3rem8lp
 
-.Lcfu_3cpy8lp:	mov	r3, r7, pull #24
+.Lcfu_3cpy8lp:	mov	r3, r7, lspull #24
 		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
-		orr	r3, r3, r4, push #8
-		mov	r4, r4, pull #24
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
-		mov	r6, r6, pull #24
-		orr	r6, r6, r7, push #8
+		orr	r3, r3, r4, lspush #8
+		mov	r4, r4, lspull #24
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
+		mov	r6, r6, lspull #24
+		orr	r6, r6, r7, lspush #8
 		stmia	r0!, {r3 - r6}
 		subs	ip, ip, #16
 		bpl	.Lcfu_3cpy8lp
 
 .Lcfu_3rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
-		orrne	r3, r3, r4, push #8
-		movne	r4, r4, pull #24
-		orrne	r4, r4, r7, push #8
+		orrne	r3, r3, r4, lspush #8
+		movne	r4, r4, lspull #24
+		orrne	r4, r4, r7, lspush #8
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
-		orrne	r3, r3, r7, push #8
+		orrne	r3, r3, r7, lspush #8
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_3fupi