27 files changed, 179 insertions, 64 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 101b9681c08c..94186b6c685f 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -10,8 +10,8 @@ config CPU_ARM7TDMI
 	depends on !MMU
 	select CPU_32v4T
 	select CPU_ABRT_LV4T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_V4
+	select CPU_PABRT_LEGACY
 	help
 	  A 32-bit RISC microprocessor based on the ARM7 processor core
 	  which has no memory control unit and cache.
@@ -24,11 +24,11 @@ config CPU_ARM720T
 	bool "Support ARM720T processor" if ARCH_INTEGRATOR
 	select CPU_32v4T
 	select CPU_ABRT_LV4T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_V4
 	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_COPY_V4WT if MMU
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WT if MMU
 	help
 	  A 32-bit RISC processor with 8kByte Cache, Write Buffer and
@@ -43,9 +43,9 @@ config CPU_ARM740T
 	depends on !MMU
 	select CPU_32v4T
 	select CPU_ABRT_LV4T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_V3	# although the core is v4t
 	select CPU_CP15_MPU
+	select CPU_PABRT_LEGACY
 	help
 	  A 32-bit RISC processor with 8KB cache or 4KB variants,
 	  write buffer and MPU(Protection Unit) built around
@@ -60,8 +60,8 @@ config CPU_ARM9TDMI
 	depends on !MMU
 	select CPU_32v4T
 	select CPU_ABRT_NOMMU
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_V4
+	select CPU_PABRT_LEGACY
 	help
 	  A 32-bit RISC microprocessor based on the ARM9 processor core
 	  which has no memory control unit and cache.
@@ -74,11 +74,11 @@ config CPU_ARM920T
 	bool "Support ARM920T processor" if ARCH_INTEGRATOR
 	select CPU_32v4T
 	select CPU_ABRT_EV4T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_V4WT
 	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_COPY_V4WB if MMU
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WBI if MMU
 	help
 	  The ARM920T is licensed to be produced by numerous vendors,
@@ -92,11 +92,11 @@ config CPU_ARM922T
 	bool "Support ARM922T processor" if ARCH_INTEGRATOR
 	select CPU_32v4T
 	select CPU_ABRT_EV4T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_V4WT
 	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_COPY_V4WB if MMU
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WBI if MMU
 	help
 	  The ARM922T is a version of the ARM920T, but with smaller
@@ -111,11 +111,11 @@ config CPU_ARM925T
  	bool "Support ARM925T processor" if ARCH_OMAP1
 	select CPU_32v4T
 	select CPU_ABRT_EV4T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_V4WT
 	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_COPY_V4WB if MMU
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WBI if MMU
  	help
  	  The ARM925T is a mix between the ARM920T and ARM926T, but with
@@ -130,10 +130,10 @@ config CPU_ARM926T
 	bool "Support ARM926T processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB
 	select CPU_32v5
 	select CPU_ABRT_EV5TJ
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_COPY_V4WB if MMU
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WBI if MMU
 	help
 	  This is a variant of the ARM920.  It has slightly different
@@ -148,11 +148,11 @@ config CPU_FA526
 	bool
 	select CPU_32v4
 	select CPU_ABRT_EV4
-	select CPU_PABRT_LEGACY
-	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_CACHE_FA
+	select CPU_CACHE_VIVT
 	select CPU_COPY_FA if MMU
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_FA if MMU
 	help
 	  The FA526 is a version of the ARMv4 compatible processor with
@@ -167,9 +167,9 @@ config CPU_ARM940T
 	depends on !MMU
 	select CPU_32v4T
 	select CPU_ABRT_NOMMU
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_VIVT
 	select CPU_CP15_MPU
+	select CPU_PABRT_LEGACY
 	help
 	  ARM940T is a member of the ARM9TDMI family of general-
 	  purpose microprocessors with MPU and separate 4KB
@@ -185,9 +185,9 @@ config CPU_ARM946E
 	depends on !MMU
 	select CPU_32v5
 	select CPU_ABRT_NOMMU
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_VIVT
 	select CPU_CP15_MPU
+	select CPU_PABRT_LEGACY
 	help
 	  ARM946E-S is a member of the ARM9E-S family of high-
 	  performance, 32-bit system-on-chip processor solutions.
@@ -201,11 +201,11 @@ config CPU_ARM1020
 	bool "Support ARM1020T (rev 0) processor" if ARCH_INTEGRATOR
 	select CPU_32v5
 	select CPU_ABRT_EV4T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_V4WT
 	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_COPY_V4WB if MMU
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WBI if MMU
 	help
 	  The ARM1020 is the 32K cached version of the ARM10 processor,
@@ -217,25 +217,25 @@ config CPU_ARM1020
 # ARM1020E - needs validating
 config CPU_ARM1020E
 	bool "Support ARM1020E processor" if ARCH_INTEGRATOR
+	depends on n
 	select CPU_32v5
 	select CPU_ABRT_EV4T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_V4WT
 	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_COPY_V4WB if MMU
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WBI if MMU
-	depends on n
 
 # ARM1022E
 config CPU_ARM1022
 	bool "Support ARM1022E processor" if ARCH_INTEGRATOR
 	select CPU_32v5
 	select CPU_ABRT_EV4T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_COPY_V4WB if MMU # can probably do better
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WBI if MMU
 	help
 	  The ARM1022E is an implementation of the ARMv5TE architecture
@@ -250,10 +250,10 @@ config CPU_ARM1026
 	bool "Support ARM1026EJ-S processor" if ARCH_INTEGRATOR
 	select CPU_32v5
 	select CPU_ABRT_EV5T # But need Jazelle, but EV5TJ ignores bit 10
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_COPY_V4WB if MMU # can probably do better
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WBI if MMU
 	help
 	  The ARM1026EJ-S is an implementation of the ARMv5TEJ architecture
@@ -268,11 +268,11 @@ config CPU_SA110
 	select CPU_32v3 if ARCH_RPC
 	select CPU_32v4 if !ARCH_RPC
 	select CPU_ABRT_EV4
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_V4WB
 	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_COPY_V4WB if MMU
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WB if MMU
 	help
 	  The Intel StrongARM(R) SA-110 is a 32-bit microprocessor and
@@ -288,10 +288,10 @@ config CPU_SA1100
 	bool
 	select CPU_32v4
 	select CPU_ABRT_EV4
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_V4WB
 	select CPU_CACHE_VIVT
 	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WB if MMU
 
 # XScale
@@ -299,9 +299,9 @@ config CPU_XSCALE
 	bool
 	select CPU_32v5
 	select CPU_ABRT_EV5T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_VIVT
 	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WBI if MMU
 
 # XScale Core Version 3
@@ -309,9 +309,9 @@ config CPU_XSC3
 	bool
 	select CPU_32v5
 	select CPU_ABRT_EV5T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_VIVT
 	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WBI if MMU
 	select IO_36
 
@@ -320,21 +320,21 @@ config CPU_MOHAWK
 	bool
 	select CPU_32v5
 	select CPU_ABRT_EV5T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_VIVT
+	select CPU_COPY_V4WB if MMU
 	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_V4WBI if MMU
-	select CPU_COPY_V4WB if MMU
 
 # Feroceon
 config CPU_FEROCEON
 	bool
 	select CPU_32v5
 	select CPU_ABRT_EV5T
-	select CPU_PABRT_LEGACY
 	select CPU_CACHE_VIVT
-	select CPU_CP15_MMU
 	select CPU_COPY_FEROCEON if MMU
+	select CPU_CP15_MMU
+	select CPU_PABRT_LEGACY
 	select CPU_TLB_FEROCEON if MMU
 
 config CPU_FEROCEON_OLD_ID
@@ -349,20 +349,20 @@ config CPU_FEROCEON_OLD_ID
 # Marvell PJ4
 config CPU_PJ4
 	bool
-	select CPU_V7
 	select ARM_THUMBEE
+	select CPU_V7
 
 # ARMv6
 config CPU_V6
 	bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
 	select CPU_32v6
 	select CPU_ABRT_EV6
-	select CPU_PABRT_V6
 	select CPU_CACHE_V6
 	select CPU_CACHE_VIPT
+	select CPU_COPY_V6 if MMU
 	select CPU_CP15_MMU
 	select CPU_HAS_ASID if MMU
-	select CPU_COPY_V6 if MMU
+	select CPU_PABRT_V6
 	select CPU_TLB_V6 if MMU
 
 # ARMv6k
@@ -371,12 +371,12 @@ config CPU_V6K
 	select CPU_32v6
 	select CPU_32v6K
 	select CPU_ABRT_EV6
-	select CPU_PABRT_V6
 	select CPU_CACHE_V6
 	select CPU_CACHE_VIPT
+	select CPU_COPY_V6 if MMU
 	select CPU_CP15_MMU
 	select CPU_HAS_ASID if MMU
-	select CPU_COPY_V6 if MMU
+	select CPU_PABRT_V6
 	select CPU_TLB_V6 if MMU
 
 # ARMv7
@@ -385,44 +385,44 @@ config CPU_V7
 	select CPU_32v6K
 	select CPU_32v7
 	select CPU_ABRT_EV7
-	select CPU_PABRT_V7
 	select CPU_CACHE_V7
 	select CPU_CACHE_VIPT
+	select CPU_COPY_V6 if MMU
 	select CPU_CP15_MMU
 	select CPU_HAS_ASID if MMU
-	select CPU_COPY_V6 if MMU
+	select CPU_PABRT_V7
 	select CPU_TLB_V7 if MMU
 
 # Figure out what processor architecture version we should be using.
 # This defines the compiler instruction set which depends on the machine type.
 config CPU_32v3
 	bool
-	select TLS_REG_EMUL if SMP || !MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select CPU_USE_DOMAINS if MMU
+	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select TLS_REG_EMUL if SMP || !MMU
 
 config CPU_32v4
 	bool
-	select TLS_REG_EMUL if SMP || !MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select CPU_USE_DOMAINS if MMU
+	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select TLS_REG_EMUL if SMP || !MMU
 
 config CPU_32v4T
 	bool
-	select TLS_REG_EMUL if SMP || !MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select CPU_USE_DOMAINS if MMU
+	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select TLS_REG_EMUL if SMP || !MMU
 
 config CPU_32v5
 	bool
-	select TLS_REG_EMUL if SMP || !MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select CPU_USE_DOMAINS if MMU
+	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select TLS_REG_EMUL if SMP || !MMU
 
 config CPU_32v6
 	bool
-	select TLS_REG_EMUL if !CPU_32v6K && !MMU
 	select CPU_USE_DOMAINS if CPU_V6 && MMU
+	select TLS_REG_EMUL if !CPU_32v6K && !MMU
 
 config CPU_32v6K
 	bool
@@ -624,11 +624,28 @@ config ARM_THUMBEE
 	  Say Y here if you have a CPU with the ThumbEE extension and code to
 	  make use of it. Say N for code that can run on CPUs without ThumbEE.
 
+config ARM_VIRT_EXT
+	bool "Native support for the ARM Virtualization Extensions"
+	depends on MMU && CPU_V7
+	help
+	  Enable the kernel to make use of the ARM Virtualization
+	  Extensions to install hypervisors without run-time firmware
+	  assistance.
+
+	  A compliant bootloader is required in order to make maximum
+	  use of this feature.  Refer to Documentation/arm/Booting for
+	  details.
+
+	  It is safe to enable this option even if the kernel may not be
+	  booted in HYP mode, may not have support for the
+	  virtualization extensions, or may be booted with a
+	  non-compliant bootloader.
+
 config SWP_EMULATE
 	bool "Emulate SWP/SWPB instructions"
 	depends on !CPU_USE_DOMAINS && CPU_V7
-	select HAVE_PROC_CPU if PROC_FS
 	default y if SMP
+	select HAVE_PROC_CPU if PROC_FS
 	help
 	  ARMv6 architecture deprecates use of the SWP/SWPB instructions.
 	  ARMv7 multiprocessing extensions introduce the ability to disable
diff --git a/arch/arm/mm/cache-fa.S b/arch/arm/mm/cache-fa.S
index 072016371093..e505befe51b5 100644
--- a/arch/arm/mm/cache-fa.S
+++ b/arch/arm/mm/cache-fa.S
@@ -240,6 +240,9 @@ ENTRY(fa_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(fa_dma_unmap_area)
 
+	.globl	fa_flush_kern_cache_louis
+	.equ	fa_flush_kern_cache_louis, fa_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S
index 52e35f32eefb..8a3fadece8d3 100644
--- a/arch/arm/mm/cache-v3.S
+++ b/arch/arm/mm/cache-v3.S
@@ -128,6 +128,9 @@ ENTRY(v3_dma_map_area)
 ENDPROC(v3_dma_unmap_area)
 ENDPROC(v3_dma_map_area)
 
+	.globl	v3_flush_kern_cache_louis
+	.equ	v3_flush_kern_cache_louis, v3_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index 022135d2b7e4..43e5d77be677 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -140,6 +140,9 @@ ENTRY(v4_dma_map_area)
 ENDPROC(v4_dma_unmap_area)
 ENDPROC(v4_dma_map_area)
 
+	.globl	v4_flush_kern_cache_louis
+	.equ	v4_flush_kern_cache_louis, v4_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S
index 8f1eeae340c8..cd4945321407 100644
--- a/arch/arm/mm/cache-v4wb.S
+++ b/arch/arm/mm/cache-v4wb.S
@@ -251,6 +251,9 @@ ENTRY(v4wb_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(v4wb_dma_unmap_area)
 
+	.globl	v4wb_flush_kern_cache_louis
+	.equ	v4wb_flush_kern_cache_louis, v4wb_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S
index b34a5f908a82..11e5e5838bc5 100644
--- a/arch/arm/mm/cache-v4wt.S
+++ b/arch/arm/mm/cache-v4wt.S
@@ -196,6 +196,9 @@ ENTRY(v4wt_dma_map_area)
 ENDPROC(v4wt_dma_unmap_area)
 ENDPROC(v4wt_dma_map_area)
 
+	.globl	v4wt_flush_kern_cache_louis
+	.equ	v4wt_flush_kern_cache_louis, v4wt_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 4b10760c56d6..d8fd4d4bd3d4 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -326,6 +326,9 @@ ENTRY(v6_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(v6_dma_unmap_area)
 
+	.globl	v6_flush_kern_cache_louis
+	.equ	v6_flush_kern_cache_louis, v6_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 3b172275262e..cd956647c21a 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -33,6 +33,24 @@ ENTRY(v7_flush_icache_all)
 	mov	pc, lr
 ENDPROC(v7_flush_icache_all)
 
+ /*
+ *     v7_flush_dcache_louis()
+ *
+ *     Flush the D-cache up to the Level of Unification Inner Shareable
+ *
+ *     Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode)
+ */
+
+ENTRY(v7_flush_dcache_louis)
+	dmb					@ ensure ordering with previous memory accesses
+	mrc	p15, 1, r0, c0, c0, 1		@ read clidr, r0 = clidr
+	ands	r3, r0, #0xe00000		@ extract LoUIS from clidr
+	mov	r3, r3, lsr #20			@ r3 = LoUIS * 2
+	moveq	pc, lr				@ return if level == 0
+	mov	r10, #0				@ r10 (starting level) = 0
+	b	flush_levels			@ start flushing cache levels
+ENDPROC(v7_flush_dcache_louis)
+
 /*
  *	v7_flush_dcache_all()
  *
@@ -49,7 +67,7 @@ ENTRY(v7_flush_dcache_all)
 	mov	r3, r3, lsr #23			@ left align loc bit field
 	beq	finished			@ if loc is 0, then no need to clean
 	mov	r10, #0				@ start clean at cache level 0
-loop1:
+flush_levels:
 	add	r2, r10, r10, lsr #1		@ work out 3x current cache level
 	mov	r1, r0, lsr r2			@ extract cache type bits from clidr
 	and	r1, r1, #7			@ mask of the bits for current cache only
@@ -71,9 +89,9 @@ loop1:
 	clz	r5, r4				@ find bit position of way size increment
 	ldr	r7, =0x7fff
 	ands	r7, r7, r1, lsr #13		@ extract max number of the index size
-loop2:
+loop1:
 	mov	r9, r4				@ create working copy of max way size
-loop3:
+loop2:
  ARM(	orr	r11, r10, r9, lsl r5	)	@ factor way and cache number into r11
  THUMB(	lsl	r6, r9, r5		)
  THUMB(	orr	r11, r10, r6		)	@ factor way and cache number into r11
@@ -82,13 +100,13 @@ loop3:
  THUMB(	orr	r11, r11, r6		)	@ factor index number into r11
 	mcr	p15, 0, r11, c7, c14, 2		@ clean & invalidate by set/way
 	subs	r9, r9, #1			@ decrement the way
-	bge	loop3
-	subs	r7, r7, #1			@ decrement the index
 	bge	loop2
+	subs	r7, r7, #1			@ decrement the index
+	bge	loop1
 skip:
 	add	r10, r10, #2			@ increment cache number
 	cmp	r3, r10
-	bgt	loop1
+	bgt	flush_levels
 finished:
 	mov	r10, #0				@ swith back to cache level 0
 	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
@@ -120,6 +138,24 @@ ENTRY(v7_flush_kern_cache_all)
 	mov	pc, lr
 ENDPROC(v7_flush_kern_cache_all)
 
+ /*
+ *     v7_flush_kern_cache_louis(void)
+ *
+ *     Flush the data cache up to Level of Unification Inner Shareable.
+ *     Invalidate the I-cache to the point of unification.
+ */
+ENTRY(v7_flush_kern_cache_louis)
+ ARM(	stmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
+ THUMB(	stmfd	sp!, {r4-r7, r9-r11, lr}	)
+	bl	v7_flush_dcache_louis
+	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
+ ARM(	ldmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
+ THUMB(	ldmfd	sp!, {r4-r7, r9-r11, lr}	)
+	mov	pc, lr
+ENDPROC(v7_flush_kern_cache_louis)
+
 /*
  *	v7_flush_cache_all()
  *
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 7599e2625c7d..2a5907b5c8d2 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -134,7 +134,6 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *mpnt;
-	struct prio_tree_iter iter;
 	unsigned long offset;
 	pgoff_t pgoff;
 	int aliases = 0;
@@ -147,7 +146,7 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 	 * cache coherency.
 	 */
 	flush_dcache_mmap_lock(mapping);
-	vma_prio_tree_foreach(mpnt, &iter, &mapping->i_mmap, pgoff, pgoff) {
+	vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
 		/*
 		 * If this VMA is not in our MM, we can ignore it.
 		 * Note that we intentionally mask out the VMA
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index c3bd83450227..5dbf13f954f6 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -336,6 +336,7 @@ retry:
 			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
 			* of starvation. */
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}
 	}
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 40ca11ed6e5f..1c8f7f564175 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -196,7 +196,6 @@ static void __flush_dcache_aliases(struct address_space *mapping, struct page *p
 {
 	struct mm_struct *mm = current->active_mm;
 	struct vm_area_struct *mpnt;
-	struct prio_tree_iter iter;
 	pgoff_t pgoff;
 
 	/*
@@ -208,7 +207,7 @@ static void __flush_dcache_aliases(struct address_space *mapping, struct page *p
 	pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 
 	flush_dcache_mmap_lock(mapping);
-	vma_prio_tree_foreach(mpnt, &iter, &mapping->i_mmap, pgoff, pgoff) {
+	vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
 		unsigned long offset;
 
 		/*
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index 0650bb87c1e3..2bb61e703d6c 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -368,6 +368,9 @@ ENTRY(arm1020_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm1020_dma_unmap_area)
 
+	.globl	arm1020_flush_kern_cache_louis
+	.equ	arm1020_flush_kern_cache_louis, arm1020_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm1020
 
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index 4188478325a6..8f96aa40f510 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -354,6 +354,9 @@ ENTRY(arm1020e_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm1020e_dma_unmap_area)
 
+	.globl	arm1020e_flush_kern_cache_louis
+	.equ	arm1020e_flush_kern_cache_louis, arm1020e_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm1020e
 
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index 33c68824bff0..8ebe4a469a22 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -343,6 +343,9 @@ ENTRY(arm1022_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm1022_dma_unmap_area)
 
+	.globl	arm1022_flush_kern_cache_louis
+	.equ	arm1022_flush_kern_cache_louis, arm1022_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm1022
 
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index fbc1d5fc24dc..093fc7e520c3 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -337,6 +337,9 @@ ENTRY(arm1026_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm1026_dma_unmap_area)
 
+	.globl	arm1026_flush_kern_cache_louis
+	.equ	arm1026_flush_kern_cache_louis, arm1026_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm1026
 
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 1a8c138eb897..2c3b9421ab5e 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -319,6 +319,9 @@ ENTRY(arm920_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm920_dma_unmap_area)
 
+	.globl	arm920_flush_kern_cache_louis
+	.equ	arm920_flush_kern_cache_louis, arm920_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm920
 #endif
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index 4c44d7e1c3ca..4464c49d7449 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -321,6 +321,9 @@ ENTRY(arm922_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm922_dma_unmap_area)
 
+	.globl	arm922_flush_kern_cache_louis
+	.equ	arm922_flush_kern_cache_louis, arm922_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm922
 #endif
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index ec5b1180994f..281eb9b9c1d6 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -376,6 +376,9 @@ ENTRY(arm925_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm925_dma_unmap_area)
 
+	.globl	arm925_flush_kern_cache_louis
+	.equ	arm925_flush_kern_cache_louis, arm925_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm925
 
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index c31e62c606c0..f1803f7e2972 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -339,6 +339,9 @@ ENTRY(arm926_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm926_dma_unmap_area)
 
+	.globl	arm926_flush_kern_cache_louis
+	.equ	arm926_flush_kern_cache_louis, arm926_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm926
 
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index a613a7dd7146..8da189d4a402 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -267,6 +267,9 @@ ENTRY(arm940_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm940_dma_unmap_area)
 
+	.globl	arm940_flush_kern_cache_louis
+	.equ	arm940_flush_kern_cache_louis, arm940_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm940
 
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index 9f4f2999fdd0..f666cf34075a 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -310,6 +310,9 @@ ENTRY(arm946_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm946_dma_unmap_area)
 
+	.globl	arm946_flush_kern_cache_louis
+	.equ	arm946_flush_kern_cache_louis, arm946_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm946
 
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index 23a8e4c7f2bd..4106b09e0c29 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -415,6 +415,9 @@ ENTRY(feroceon_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(feroceon_dma_unmap_area)
 
+	.globl	feroceon_flush_kern_cache_louis
+	.equ	feroceon_flush_kern_cache_louis, feroceon_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions feroceon
 
@@ -431,6 +434,7 @@ ENDPROC(feroceon_dma_unmap_area)
 	range_alias flush_icache_all
 	range_alias flush_user_cache_all
 	range_alias flush_kern_cache_all
+	range_alias flush_kern_cache_louis
 	range_alias flush_user_cache_range
 	range_alias coherent_kern_range
 	range_alias coherent_user_range
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 2d8ff3ad86d3..b29a2265af01 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -299,6 +299,7 @@ ENTRY(\name\()_processor_functions)
 ENTRY(\name\()_cache_fns)
 	.long	\name\()_flush_icache_all
 	.long	\name\()_flush_kern_cache_all
+	.long   \name\()_flush_kern_cache_louis
 	.long	\name\()_flush_user_cache_all
 	.long	\name\()_flush_user_cache_range
 	.long	\name\()_coherent_kern_range
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index fbb2124a547d..82f9cdc751d6 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -303,6 +303,9 @@ ENTRY(mohawk_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(mohawk_dma_unmap_area)
 
+	.globl	mohawk_flush_kern_cache_louis
+	.equ	mohawk_flush_kern_cache_louis, mohawk_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions mohawk
 
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index c2e2b66f72b5..846d279f3176 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -172,7 +172,7 @@ __v7_ca15mp_setup:
 __v7_setup:
 	adr	r12, __v7_setup_stack		@ the local stack
 	stmia	r12, {r0-r5, r7, r9, r11, lr}
-	bl	v7_flush_dcache_all
+	bl      v7_flush_dcache_louis
 	ldmia	r12, {r0-r5, r7, r9, r11, lr}
 
 	mrc	p15, 0, r0, c0, c0, 0		@ read main ID register
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index b0d57869da2d..eb93d6487f35 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -337,6 +337,9 @@ ENTRY(xsc3_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(xsc3_dma_unmap_area)
 
+	.globl	xsc3_flush_kern_cache_louis
+	.equ	xsc3_flush_kern_cache_louis, xsc3_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions xsc3
 
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 4ffebaa595ee..25510361aa18 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -410,6 +410,9 @@ ENTRY(xscale_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(xscale_dma_unmap_area)
 
+	.globl	xscale_flush_kern_cache_louis
+	.equ	xscale_flush_kern_cache_louis, xscale_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions xscale
 
@@ -439,6 +442,7 @@ ENDPROC(xscale_dma_unmap_area)
 	a0_alias flush_icache_all
 	a0_alias flush_user_cache_all
 	a0_alias flush_kern_cache_all
+	a0_alias flush_kern_cache_louis
 	a0_alias flush_user_cache_range
 	a0_alias coherent_kern_range
 	a0_alias coherent_user_range