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

Pull ARM updates from Russell King:
 "Included in this update:

   - perf updates from Will Deacon:

     The main changes are callchain stability fixes from Jean Pihet and
     event mapping and PMU name rework from Mark Rutland

     The latter is preparatory work for enabling some code re-use with
     arm64 in the future.

   - updates for nommu from Uwe Kleine-König:

     Two different fixes for the same problem making some ARM nommu
     configurations not boot since 3.6-rc1.  The problem is that
     user_addr_max returned the biggest available RAM address which
     makes some copy_from_user variants fail to read from XIP memory.

   - deprecate legacy OMAP DMA API, in preparation for it's removal.

     The popular drivers have been converted over, leaving a very small
     number of rarely used drivers, which hopefully can be converted
     during the next cycle with a bit more visibility (and hopefully
     people popping out of the woodwork to help test)

   - more tweaks for BE systems, particularly with the kernel image
     format.  In connection with this, I've cleaned up the way we
     generate the linker script for the decompressor.

   - removal of hard-coded assumptions of the kernel stack size, making
     everywhere depend on the value of THREAD_SIZE_ORDER.

   - MCPM updates from Nicolas Pitre.

   - Make it easier for proper CPU part number checks (which should
     always include the vendor field).

   - Assembly code optimisation - use the "bx" instruction when
     returning from a function on ARMv6+ rather than "mov pc, reg".

   - Save the last kernel misaligned fault location and report it via
     the procfs alignment file.

   - Clean up the way we create the initial stack frame, which is a
     repeated pattern in several different locations.

   - Support for 8-byte get_user(), needed for some DRM implementations.

   - mcs locking from Will Deacon.

   - Save and restore a few more Cortex-A9 registers (for errata
     workarounds)

   - Fix various aspects of the SWP emulation, and the ELF hwcap for the
     SWP instruction.

   - Update LPAE logic for pte_write and pmd_write to make it more
     correct.

   - Support for Broadcom Brahma15 CPU cores.

   - ARM assembly crypto updates from Ard Biesheuvel"

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (53 commits)
  ARM: add comments to the early page table remap code
  ARM: 8122/1: smp_scu: enable SCU standby support
  ARM: 8121/1: smp_scu: use macro for SCU enable bit
  ARM: 8120/1: crypto: sha512: add ARM NEON implementation
  ARM: 8119/1: crypto: sha1: add ARM NEON implementation
  ARM: 8118/1: crypto: sha1/make use of common SHA-1 structures
  ARM: 8113/1: remove remaining definitions of PLAT_PHYS_OFFSET from <mach/memory.h>
  ARM: 8111/1: Enable erratum 798181 for Broadcom Brahma-B15
  ARM: 8110/1: do CPU-specific init for Broadcom Brahma15 cores
  ARM: 8109/1: mm: Modify pte_write and pmd_write logic for LPAE
  ARM: 8108/1: mm: Introduce {pte,pmd}_isset and {pte,pmd}_isclear
  ARM: hwcap: disable HWCAP_SWP if the CPU advertises it has exclusives
  ARM: SWP emulation: only initialise on ARMv7 CPUs
  ARM: SWP emulation: always enable when SMP is enabled
  ARM: 8103/1: save/restore Cortex-A9 CP15 registers on suspend/resume
  ARM: 8098/1: mcs lock: implement wfe-based polling for MCS locking
  ARM: 8091/2: add get_user() support for 8 byte types
  ARM: 8097/1: unistd.h: relocate comments back to place
  ARM: 8096/1: Describe required sort order for textofs-y (TEXT_OFFSET)
  ARM: 8090/1: add revision info for PL310 errata 588369 and 727915
  ...

arch/arm/Kconfig

@@ -263,8 +263,22 @@ config NEED_MACH_MEMORY_H
 
 config PHYS_OFFSET
 	hex "Physical address of main memory" if MMU
-	depends on !ARM_PATCH_PHYS_VIRT && !NEED_MACH_MEMORY_H
+	depends on !ARM_PATCH_PHYS_VIRT
 	default DRAM_BASE if !MMU
+	default 0x00000000 if ARCH_EBSA110 || \
+			EP93XX_SDCE3_SYNC_PHYS_OFFSET || \
+			ARCH_FOOTBRIDGE || \
+			ARCH_INTEGRATOR || \
+			ARCH_IOP13XX || \
+			ARCH_KS8695 || \
+			(ARCH_REALVIEW && !REALVIEW_HIGH_PHYS_OFFSET)
+	default 0x10000000 if ARCH_OMAP1 || ARCH_RPC
+	default 0x20000000 if ARCH_S5PV210
+	default 0x70000000 if REALVIEW_HIGH_PHYS_OFFSET
+	default 0xc0000000 if EP93XX_SDCE0_PHYS_OFFSET || ARCH_SA1100
+	default 0xd0000000 if EP93XX_SDCE1_PHYS_OFFSET
+	default 0xe0000000 if EP93XX_SDCE2_PHYS_OFFSET
+	default 0xf0000000 if EP93XX_SDCE3_ASYNC_PHYS_OFFSET
 	help
 	  Please provide the physical address corresponding to the
 	  location of main memory in your system.
@@ -436,7 +450,6 @@ config ARCH_EP93XX
 	select ARM_VIC
 	select CLKDEV_LOOKUP
 	select CPU_ARM920T
-	select NEED_MACH_MEMORY_H
 	help
 	  This enables support for the Cirrus EP93xx series of CPUs.
 

arch/arm/Makefile

@@ -127,6 +127,9 @@ CHECKFLAGS	+= -D__arm__
 
 #Default value
 head-y		:= arch/arm/kernel/head$(MMUEXT).o
+
+# Text offset. This list is sorted numerically by address in order to
+# provide a means to avoid/resolve conflicts in multi-arch kernels.
 textofs-y	:= 0x00008000
 textofs-$(CONFIG_ARCH_CLPS711X) := 0x00028000
 # We don't want the htc bootloader to corrupt kernel during resume

arch/arm/boot/compressed/Makefile

@@ -81,7 +81,7 @@ ZTEXTADDR	:= 0
 ZBSSADDR	:= ALIGN(8)
 endif
 
-SEDFLAGS	= s/TEXT_START/$(ZTEXTADDR)/;s/BSS_START/$(ZBSSADDR)/
+CPPFLAGS_vmlinux.lds := -DTEXT_START="$(ZTEXTADDR)" -DBSS_START="$(ZBSSADDR)"
 
 suffix_$(CONFIG_KERNEL_GZIP) = gzip
 suffix_$(CONFIG_KERNEL_LZO)  = lzo
@@ -199,8 +199,5 @@ CFLAGS_font.o := -Dstatic=
 $(obj)/font.c: $(FONTC)
 	$(call cmd,shipped)
 
-$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile $(KCONFIG_CONFIG)
-	@sed "$(SEDFLAGS)" < $< > $@
-
 $(obj)/hyp-stub.S: $(srctree)/arch/$(SRCARCH)/kernel/hyp-stub.S
 	$(call cmd,shipped)

arch/arm/boot/compressed/head.S

@@ -125,9 +125,11 @@ start:
  THUMB(		adr	r12, BSYM(1f)	)
  THUMB(		bx	r12		)
 
-		.word	0x016f2818		@ Magic numbers to help the loader
-		.word	start			@ absolute load/run zImage address
-		.word	_edata			@ zImage end address
+		.word	_magic_sig	@ Magic numbers to help the loader
+		.word	_magic_start	@ absolute load/run zImage address
+		.word	_magic_end	@ zImage end address
+		.word	0x04030201	@ endianness flag
+
  THUMB(		.thumb			)
 1:
  ARM_BE8(	setend	be )			@ go BE8 if compiled for BE8

arch/arm/boot/compressed/vmlinux.lds.in → arch/arm/boot/compressed/vmlinux.lds.S

@@ -1,12 +1,20 @@
 /*
- *  linux/arch/arm/boot/compressed/vmlinux.lds.in
- *
  *  Copyright (C) 2000 Russell King
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define ZIMAGE_MAGIC(x) ( (((x) >> 24) & 0x000000ff) | \
+			  (((x) >>  8) & 0x0000ff00) | \
+			  (((x) <<  8) & 0x00ff0000) | \
+			  (((x) << 24) & 0xff000000) )
+#else
+#define ZIMAGE_MAGIC(x) (x)
+#endif
+
 OUTPUT_ARCH(arm)
 ENTRY(_start)
 SECTIONS
@@ -57,6 +65,10 @@ SECTIONS
   .pad			: { BYTE(0); . = ALIGN(8); }
   _edata = .;
 
+  _magic_sig = ZIMAGE_MAGIC(0x016f2818);
+  _magic_start = ZIMAGE_MAGIC(_start);
+  _magic_end = ZIMAGE_MAGIC(_edata);
+
   . = BSS_START;
   __bss_start = .;
   .bss			: { *(.bss) }
@@ -73,4 +85,3 @@ SECTIONS
   .stab.indexstr 0	: { *(.stab.indexstr) }
   .comment 0		: { *(.comment) }
 }
-

arch/arm/common/mcpm_entry.c

@@ -12,11 +12,13 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/irqflags.h>
+#include <linux/cpu_pm.h>
 
 #include <asm/mcpm.h>
 #include <asm/cacheflush.h>
 #include <asm/idmap.h>
 #include <asm/cputype.h>
+#include <asm/suspend.h>
 
 extern unsigned long mcpm_entry_vectors[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER];
 
@@ -146,6 +148,56 @@ int mcpm_cpu_powered_up(void)
 	return 0;
 }
 
+#ifdef CONFIG_ARM_CPU_SUSPEND
+
+static int __init nocache_trampoline(unsigned long _arg)
+{
+	void (*cache_disable)(void) = (void *)_arg;
+	unsigned int mpidr = read_cpuid_mpidr();
+	unsigned int cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	unsigned int cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	phys_reset_t phys_reset;
+
+	mcpm_set_entry_vector(cpu, cluster, cpu_resume);
+	setup_mm_for_reboot();
+
+	__mcpm_cpu_going_down(cpu, cluster);
+	BUG_ON(!__mcpm_outbound_enter_critical(cpu, cluster));
+	cache_disable();
+	__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+	__mcpm_cpu_down(cpu, cluster);
+
+	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
+	phys_reset(virt_to_phys(mcpm_entry_point));
+	BUG();
+}
+
+int __init mcpm_loopback(void (*cache_disable)(void))
+{
+	int ret;
+
+	/*
+	 * We're going to soft-restart the current CPU through the
+	 * low-level MCPM code by leveraging the suspend/resume
+	 * infrastructure. Let's play it safe by using cpu_pm_enter()
+	 * in case the CPU init code path resets the VFP or similar.
+	 */
+	local_irq_disable();
+	local_fiq_disable();
+	ret = cpu_pm_enter();
+	if (!ret) {
+		ret = cpu_suspend((unsigned long)cache_disable, nocache_trampoline);
+		cpu_pm_exit();
+	}
+	local_fiq_enable();
+	local_irq_enable();
+	if (ret)
+		pr_err("%s returned %d\n", __func__, ret);
+	return ret;
+}
+
+#endif
+
 struct sync_struct mcpm_sync;
 
 /*

arch/arm/crypto/Makefile

@@ -5,10 +5,14 @@
 obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o
 obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
+obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
+obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o
 
 aes-arm-y	:= aes-armv4.o aes_glue.o
 aes-arm-bs-y	:= aesbs-core.o aesbs-glue.o
 sha1-arm-y	:= sha1-armv4-large.o sha1_glue.o
+sha1-arm-neon-y	:= sha1-armv7-neon.o sha1_neon_glue.o
+sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
 
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $(<) > $(@)

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

arch/arm/crypto/sha1-armv7-neon.S

@@ -0,0 +1,634 @@
+/* sha1-armv7-neon.S - ARM/NEON accelerated SHA-1 transform function
+ *
+ * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/linkage.h>
+
+
+.syntax unified
+.code   32
+.fpu neon
+
+.text
+
+
+/* Context structure */
+
+#define state_h0 0
+#define state_h1 4
+#define state_h2 8
+#define state_h3 12
+#define state_h4 16
+
+
+/* Constants */
+
+#define K1  0x5A827999
+#define K2  0x6ED9EBA1
+#define K3  0x8F1BBCDC
+#define K4  0xCA62C1D6
+.align 4
+.LK_VEC:
+.LK1:	.long K1, K1, K1, K1
+.LK2:	.long K2, K2, K2, K2
+.LK3:	.long K3, K3, K3, K3
+.LK4:	.long K4, K4, K4, K4
+
+
+/* Register macros */
+
+#define RSTATE r0
+#define RDATA r1
+#define RNBLKS r2
+#define ROLDSTACK r3
+#define RWK lr
+
+#define _a r4
+#define _b r5
+#define _c r6
+#define _d r7
+#define _e r8
+
+#define RT0 r9
+#define RT1 r10
+#define RT2 r11
+#define RT3 r12
+
+#define W0 q0
+#define W1 q1
+#define W2 q2
+#define W3 q3
+#define W4 q4
+#define W5 q5
+#define W6 q6
+#define W7 q7
+
+#define tmp0 q8
+#define tmp1 q9
+#define tmp2 q10
+#define tmp3 q11
+
+#define qK1 q12
+#define qK2 q13
+#define qK3 q14
+#define qK4 q15
+
+
+/* Round function macros. */
+
+#define WK_offs(i) (((i) & 15) * 4)
+
+#define _R_F1(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	      W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	ldr RT3, [sp, WK_offs(i)]; \
+		pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	bic RT0, d, b; \
+	add e, e, a, ror #(32 - 5); \
+	and RT1, c, b; \
+		pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	add RT0, RT0, RT3; \
+	add e, e, RT1; \
+	ror b, #(32 - 30); \
+		pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	add e, e, RT0;
+
+#define _R_F2(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	      W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	ldr RT3, [sp, WK_offs(i)]; \
+		pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	eor RT0, d, b; \
+	add e, e, a, ror #(32 - 5); \
+	eor RT0, RT0, c; \
+		pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	add e, e, RT3; \
+	ror b, #(32 - 30); \
+		pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	add e, e, RT0; \
+
+#define _R_F3(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	      W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	ldr RT3, [sp, WK_offs(i)]; \
+		pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	eor RT0, b, c; \
+	and RT1, b, c; \
+	add e, e, a, ror #(32 - 5); \
+		pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	and RT0, RT0, d; \
+	add RT1, RT1, RT3; \
+	add e, e, RT0; \
+	ror b, #(32 - 30); \
+		pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	add e, e, RT1;
+
+#define _R_F4(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	      W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	_R_F2(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	      W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
+
+#define _R(a,b,c,d,e,f,i,pre1,pre2,pre3,i16,\
+           W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	_R_##f(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	       W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
+
+#define R(a,b,c,d,e,f,i) \
+	_R_##f(a,b,c,d,e,i,dummy,dummy,dummy,i16,\
+	       W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
+
+#define dummy(...)
+
+
+/* Input expansion macros. */
+
+/********* Precalc macros for rounds 0-15 *************************************/
+
+#define W_PRECALC_00_15() \
+	add       RWK, sp, #(WK_offs(0));			\
+	\
+	vld1.32   {tmp0, tmp1}, [RDATA]!;			\
+	vrev32.8  W0, tmp0;		/* big => little */	\
+	vld1.32   {tmp2, tmp3}, [RDATA]!;			\
+	vadd.u32  tmp0, W0, curK;				\
+	vrev32.8  W7, tmp1;		/* big => little */	\
+	vrev32.8  W6, tmp2;		/* big => little */	\
+	vadd.u32  tmp1, W7, curK;				\
+	vrev32.8  W5, tmp3;		/* big => little */	\
+	vadd.u32  tmp2, W6, curK;				\
+	vst1.32   {tmp0, tmp1}, [RWK]!;				\
+	vadd.u32  tmp3, W5, curK;				\
+	vst1.32   {tmp2, tmp3}, [RWK];				\
+
+#define WPRECALC_00_15_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vld1.32   {tmp0, tmp1}, [RDATA]!;			\
+
+#define WPRECALC_00_15_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	add       RWK, sp, #(WK_offs(0));			\
+
+#define WPRECALC_00_15_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vrev32.8  W0, tmp0;		/* big => little */	\
+
+#define WPRECALC_00_15_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vld1.32   {tmp2, tmp3}, [RDATA]!;			\
+
+#define WPRECALC_00_15_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32  tmp0, W0, curK;				\
+
+#define WPRECALC_00_15_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vrev32.8  W7, tmp1;		/* big => little */	\
+
+#define WPRECALC_00_15_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vrev32.8  W6, tmp2;		/* big => little */	\
+
+#define WPRECALC_00_15_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32  tmp1, W7, curK;				\
+
+#define WPRECALC_00_15_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vrev32.8  W5, tmp3;		/* big => little */	\
+
+#define WPRECALC_00_15_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32  tmp2, W6, curK;				\
+
+#define WPRECALC_00_15_10(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vst1.32   {tmp0, tmp1}, [RWK]!;				\
+
+#define WPRECALC_00_15_11(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32  tmp3, W5, curK;				\
+
+#define WPRECALC_00_15_12(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vst1.32   {tmp2, tmp3}, [RWK];				\
+
+
+/********* Precalc macros for rounds 16-31 ************************************/
+
+#define WPRECALC_16_31_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor      tmp0, tmp0;			\
+	vext.8    W, W_m16, W_m12, #8;		\
+
+#define WPRECALC_16_31_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	add       RWK, sp, #(WK_offs(i));	\
+	vext.8    tmp0, W_m04, tmp0, #4;	\
+
+#define WPRECALC_16_31_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor      tmp0, tmp0, W_m16;		\
+	veor.32   W, W, W_m08;			\
+
+#define WPRECALC_16_31_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor      tmp1, tmp1;			\
+	veor      W, W, tmp0;			\
+
+#define WPRECALC_16_31_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vshl.u32  tmp0, W, #1;			\
+
+#define WPRECALC_16_31_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vext.8    tmp1, tmp1, W, #(16-12);	\
+	vshr.u32  W, W, #31;			\
+
+#define WPRECALC_16_31_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vorr      tmp0, tmp0, W;		\
+	vshr.u32  W, tmp1, #30;			\
+
+#define WPRECALC_16_31_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vshl.u32  tmp1, tmp1, #2;		\
+
+#define WPRECALC_16_31_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor      tmp0, tmp0, W;		\
+
+#define WPRECALC_16_31_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor      W, tmp0, tmp1;		\
+
+#define WPRECALC_16_31_10(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32  tmp0, W, curK;		\
+
+#define WPRECALC_16_31_11(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vst1.32   {tmp0}, [RWK];
+
+
+/********* Precalc macros for rounds 32-79 ************************************/
+
+#define WPRECALC_32_79_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor W, W_m28; \
+
+#define WPRECALC_32_79_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vext.8 tmp0, W_m08, W_m04, #8; \
+
+#define WPRECALC_32_79_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor W, W_m16; \
+
+#define WPRECALC_32_79_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor W, tmp0; \
+
+#define WPRECALC_32_79_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	add RWK, sp, #(WK_offs(i&~3)); \
+
+#define WPRECALC_32_79_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vshl.u32 tmp1, W, #2; \
+
+#define WPRECALC_32_79_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vshr.u32 tmp0, W, #30; \
+
+#define WPRECALC_32_79_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vorr W, tmp0, tmp1; \
+
+#define WPRECALC_32_79_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32 tmp0, W, curK; \
+
+#define WPRECALC_32_79_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vst1.32 {tmp0}, [RWK];
+
+
+/*
+ * Transform nblks*64 bytes (nblks*16 32-bit words) at DATA.
+ *
+ * unsigned int
+ * sha1_transform_neon (void *ctx, const unsigned char *data,
+ *                      unsigned int nblks)
+ */
+.align 3
+ENTRY(sha1_transform_neon)
+  /* input:
+   *	r0: ctx, CTX
+   *	r1: data (64*nblks bytes)
+   *	r2: nblks
+   */
+
+  cmp RNBLKS, #0;
+  beq .Ldo_nothing;
+
+  push {r4-r12, lr};
+  /*vpush {q4-q7};*/
+
+  adr RT3, .LK_VEC;
+
+  mov ROLDSTACK, sp;
+
+  /* Align stack. */
+  sub RT0, sp, #(16*4);
+  and RT0, #(~(16-1));
+  mov sp, RT0;
+
+  vld1.32 {qK1-qK2}, [RT3]!; /* Load K1,K2 */
+
+  /* Get the values of the chaining variables. */
+  ldm RSTATE, {_a-_e};
+
+  vld1.32 {qK3-qK4}, [RT3]; /* Load K3,K4 */
+
+#undef curK
+#define curK qK1
+  /* Precalc 0-15. */
+  W_PRECALC_00_15();
+
+.Loop:
+  /* Transform 0-15 + Precalc 16-31. */
+  _R( _a, _b, _c, _d, _e, F1,  0,
+      WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 16,
+      W4, W5, W6, W7, W0, _, _, _ );
+  _R( _e, _a, _b, _c, _d, F1,  1,
+      WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 16,
+      W4, W5, W6, W7, W0, _, _, _ );
+  _R( _d, _e, _a, _b, _c, F1,  2,
+      WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 16,
+      W4, W5, W6, W7, W0, _, _, _ );
+  _R( _c, _d, _e, _a, _b, F1,  3,
+      WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,16,
+      W4, W5, W6, W7, W0, _, _, _ );
+
+#undef curK
+#define curK qK2
+  _R( _b, _c, _d, _e, _a, F1,  4,
+      WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 20,
+      W3, W4, W5, W6, W7, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F1,  5,
+      WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 20,
+      W3, W4, W5, W6, W7, _, _, _ );
+  _R( _e, _a, _b, _c, _d, F1,  6,
+      WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 20,
+      W3, W4, W5, W6, W7, _, _, _ );
+  _R( _d, _e, _a, _b, _c, F1,  7,
+      WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,20,
+      W3, W4, W5, W6, W7, _, _, _ );
+
+  _R( _c, _d, _e, _a, _b, F1,  8,
+      WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 24,
+      W2, W3, W4, W5, W6, _, _, _ );
+  _R( _b, _c, _d, _e, _a, F1,  9,
+      WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 24,
+      W2, W3, W4, W5, W6, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F1, 10,
+      WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 24,
+      W2, W3, W4, W5, W6, _, _, _ );
+  _R( _e, _a, _b, _c, _d, F1, 11,
+      WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,24,
+      W2, W3, W4, W5, W6, _, _, _ );
+
+  _R( _d, _e, _a, _b, _c, F1, 12,
+      WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 28,
+      W1, W2, W3, W4, W5, _, _, _ );
+  _R( _c, _d, _e, _a, _b, F1, 13,
+      WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 28,
+      W1, W2, W3, W4, W5, _, _, _ );
+  _R( _b, _c, _d, _e, _a, F1, 14,
+      WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 28,
+      W1, W2, W3, W4, W5, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F1, 15,
+      WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,28,
+      W1, W2, W3, W4, W5, _, _, _ );
+
+  /* Transform 16-63 + Precalc 32-79. */
+  _R( _e, _a, _b, _c, _d, F1, 16,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 32,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _d, _e, _a, _b, _c, F1, 17,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 32,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _c, _d, _e, _a, _b, F1, 18,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 32,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _b, _c, _d, _e, _a, F1, 19,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 32,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+
+  _R( _a, _b, _c, _d, _e, F2, 20,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 36,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _e, _a, _b, _c, _d, F2, 21,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 36,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _d, _e, _a, _b, _c, F2, 22,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 36,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _c, _d, _e, _a, _b, F2, 23,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 36,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+
+#undef curK
+#define curK qK3
+  _R( _b, _c, _d, _e, _a, F2, 24,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 40,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _a, _b, _c, _d, _e, F2, 25,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 40,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _e, _a, _b, _c, _d, F2, 26,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 40,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _d, _e, _a, _b, _c, F2, 27,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 40,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+
+  _R( _c, _d, _e, _a, _b, F2, 28,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 44,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _b, _c, _d, _e, _a, F2, 29,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 44,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _a, _b, _c, _d, _e, F2, 30,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 44,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _e, _a, _b, _c, _d, F2, 31,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 44,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+
+  _R( _d, _e, _a, _b, _c, F2, 32,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 48,
+      W4, W5, W6, W7, W0, W1, W2, W3);
+  _R( _c, _d, _e, _a, _b, F2, 33,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 48,
+      W4, W5, W6, W7, W0, W1, W2, W3);
+  _R( _b, _c, _d, _e, _a, F2, 34,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 48,
+      W4, W5, W6, W7, W0, W1, W2, W3);
+  _R( _a, _b, _c, _d, _e, F2, 35,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 48,
+      W4, W5, W6, W7, W0, W1, W2, W3);
+
+  _R( _e, _a, _b, _c, _d, F2, 36,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 52,
+      W3, W4, W5, W6, W7, W0, W1, W2);
+  _R( _d, _e, _a, _b, _c, F2, 37,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 52,
+      W3, W4, W5, W6, W7, W0, W1, W2);
+  _R( _c, _d, _e, _a, _b, F2, 38,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 52,
+      W3, W4, W5, W6, W7, W0, W1, W2);
+  _R( _b, _c, _d, _e, _a, F2, 39,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 52,
+      W3, W4, W5, W6, W7, W0, W1, W2);
+
+  _R( _a, _b, _c, _d, _e, F3, 40,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 56,
+      W2, W3, W4, W5, W6, W7, W0, W1);
+  _R( _e, _a, _b, _c, _d, F3, 41,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 56,
+      W2, W3, W4, W5, W6, W7, W0, W1);
+  _R( _d, _e, _a, _b, _c, F3, 42,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 56,
+      W2, W3, W4, W5, W6, W7, W0, W1);
+  _R( _c, _d, _e, _a, _b, F3, 43,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 56,
+      W2, W3, W4, W5, W6, W7, W0, W1);
+
+#undef curK
+#define curK qK4
+  _R( _b, _c, _d, _e, _a, F3, 44,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 60,
+      W1, W2, W3, W4, W5, W6, W7, W0);
+  _R( _a, _b, _c, _d, _e, F3, 45,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 60,
+      W1, W2, W3, W4, W5, W6, W7, W0);
+  _R( _e, _a, _b, _c, _d, F3, 46,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 60,
+      W1, W2, W3, W4, W5, W6, W7, W0);
+  _R( _d, _e, _a, _b, _c, F3, 47,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 60,
+      W1, W2, W3, W4, W5, W6, W7, W0);
+
+  _R( _c, _d, _e, _a, _b, F3, 48,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 64,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _b, _c, _d, _e, _a, F3, 49,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 64,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _a, _b, _c, _d, _e, F3, 50,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 64,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _e, _a, _b, _c, _d, F3, 51,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 64,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+
+  _R( _d, _e, _a, _b, _c, F3, 52,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 68,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _c, _d, _e, _a, _b, F3, 53,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 68,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _b, _c, _d, _e, _a, F3, 54,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 68,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _a, _b, _c, _d, _e, F3, 55,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 68,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+
+  _R( _e, _a, _b, _c, _d, F3, 56,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 72,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _d, _e, _a, _b, _c, F3, 57,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 72,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _c, _d, _e, _a, _b, F3, 58,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 72,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _b, _c, _d, _e, _a, F3, 59,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 72,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+
+  subs RNBLKS, #1;
+
+  _R( _a, _b, _c, _d, _e, F4, 60,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 76,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _e, _a, _b, _c, _d, F4, 61,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 76,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _d, _e, _a, _b, _c, F4, 62,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 76,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _c, _d, _e, _a, _b, F4, 63,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 76,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+
+  beq .Lend;
+
+  /* Transform 64-79 + Precalc 0-15 of next block. */
+#undef curK
+#define curK qK1
+  _R( _b, _c, _d, _e, _a, F4, 64,
+      WPRECALC_00_15_0, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F4, 65,
+      WPRECALC_00_15_1, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _e, _a, _b, _c, _d, F4, 66,
+      WPRECALC_00_15_2, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _d, _e, _a, _b, _c, F4, 67,
+      WPRECALC_00_15_3, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+
+  _R( _c, _d, _e, _a, _b, F4, 68,
+      dummy,            dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _b, _c, _d, _e, _a, F4, 69,
+      dummy,            dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F4, 70,
+      WPRECALC_00_15_4, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _e, _a, _b, _c, _d, F4, 71,
+      WPRECALC_00_15_5, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+
+  _R( _d, _e, _a, _b, _c, F4, 72,
+      dummy,            dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _c, _d, _e, _a, _b, F4, 73,
+      dummy,            dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _b, _c, _d, _e, _a, F4, 74,
+      WPRECALC_00_15_6, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F4, 75,
+      WPRECALC_00_15_7, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+
+  _R( _e, _a, _b, _c, _d, F4, 76,
+      WPRECALC_00_15_8, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _d, _e, _a, _b, _c, F4, 77,
+      WPRECALC_00_15_9, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _c, _d, _e, _a, _b, F4, 78,
+      WPRECALC_00_15_10, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _b, _c, _d, _e, _a, F4, 79,
+      WPRECALC_00_15_11, dummy, WPRECALC_00_15_12, _, _, _, _, _, _, _, _, _ );
+
+  /* Update the chaining variables. */
+  ldm RSTATE, {RT0-RT3};
+  add _a, RT0;
+  ldr RT0, [RSTATE, #state_h4];
+  add _b, RT1;
+  add _c, RT2;
+  add _d, RT3;
+  add _e, RT0;
+  stm RSTATE, {_a-_e};
+
+  b .Loop;
+
+.Lend:
+  /* Transform 64-79 */
+  R( _b, _c, _d, _e, _a, F4, 64 );
+  R( _a, _b, _c, _d, _e, F4, 65 );
+  R( _e, _a, _b, _c, _d, F4, 66 );
+  R( _d, _e, _a, _b, _c, F4, 67 );
+  R( _c, _d, _e, _a, _b, F4, 68 );
+  R( _b, _c, _d, _e, _a, F4, 69 );
+  R( _a, _b, _c, _d, _e, F4, 70 );
+  R( _e, _a, _b, _c, _d, F4, 71 );
+  R( _d, _e, _a, _b, _c, F4, 72 );
+  R( _c, _d, _e, _a, _b, F4, 73 );
+  R( _b, _c, _d, _e, _a, F4, 74 );
+  R( _a, _b, _c, _d, _e, F4, 75 );
+  R( _e, _a, _b, _c, _d, F4, 76 );
+  R( _d, _e, _a, _b, _c, F4, 77 );
+  R( _c, _d, _e, _a, _b, F4, 78 );
+  R( _b, _c, _d, _e, _a, F4, 79 );
+
+  mov sp, ROLDSTACK;
+
+  /* Update the chaining variables. */
+  ldm RSTATE, {RT0-RT3};
+  add _a, RT0;
+  ldr RT0, [RSTATE, #state_h4];
+  add _b, RT1;
+  add _c, RT2;
+  add _d, RT3;
+  /*vpop {q4-q7};*/
+  add _e, RT0;
+  stm RSTATE, {_a-_e};
+
+  pop {r4-r12, pc};
+
+.Ldo_nothing:
+  bx lr
+ENDPROC(sha1_transform_neon)

arch/arm/crypto/sha1_glue.c

@@ -23,32 +23,27 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <asm/byteorder.h>
+#include <asm/crypto/sha1.h>
 
-struct SHA1_CTX {
-	uint32_t h0,h1,h2,h3,h4;
-	u64 count;
-	u8 data[SHA1_BLOCK_SIZE];
-};
 
-asmlinkage void sha1_block_data_order(struct SHA1_CTX *digest,
+asmlinkage void sha1_block_data_order(u32 *digest,
 		const unsigned char *data, unsigned int rounds);
 
 
 static int sha1_init(struct shash_desc *desc)
 {
-	struct SHA1_CTX *sctx = shash_desc_ctx(desc);
-	memset(sctx, 0, sizeof(*sctx));
-	sctx->h0 = SHA1_H0;
-	sctx->h1 = SHA1_H1;
-	sctx->h2 = SHA1_H2;
-	sctx->h3 = SHA1_H3;
-	sctx->h4 = SHA1_H4;
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha1_state){
+		.state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+	};
+
 	return 0;
 }
 
 
-static int __sha1_update(struct SHA1_CTX *sctx, const u8 *data,
-			       unsigned int len, unsigned int partial)
+static int __sha1_update(struct sha1_state *sctx, const u8 *data,
+			 unsigned int len, unsigned int partial)
 {
 	unsigned int done = 0;
 
@@ -56,43 +51,44 @@ static int __sha1_update(struct SHA1_CTX *sctx, const u8 *data,
 
 	if (partial) {
 		done = SHA1_BLOCK_SIZE - partial;
-		memcpy(sctx->data + partial, data, done);
-		sha1_block_data_order(sctx, sctx->data, 1);
+		memcpy(sctx->buffer + partial, data, done);
+		sha1_block_data_order(sctx->state, sctx->buffer, 1);
 	}
 
 	if (len - done >= SHA1_BLOCK_SIZE) {
 		const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE;
-		sha1_block_data_order(sctx, data + done, rounds);
+		sha1_block_data_order(sctx->state, data + done, rounds);
 		done += rounds * SHA1_BLOCK_SIZE;
 	}
 
-	memcpy(sctx->data, data + done, len - done);
+	memcpy(sctx->buffer, data + done, len - done);
 	return 0;
 }
 
 
-static int sha1_update(struct shash_desc *desc, const u8 *data,
-			     unsigned int len)
+int sha1_update_arm(struct shash_desc *desc, const u8 *data,
+		    unsigned int len)
 {
-	struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+	struct sha1_state *sctx = shash_desc_ctx(desc);
 	unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
 	int res;
 
 	/* Handle the fast case right here */
 	if (partial + len < SHA1_BLOCK_SIZE) {
 		sctx->count += len;
-		memcpy(sctx->data + partial, data, len);
+		memcpy(sctx->buffer + partial, data, len);
 		return 0;
 	}
 	res = __sha1_update(sctx, data, len, partial);
 	return res;
 }
+EXPORT_SYMBOL_GPL(sha1_update_arm);
 
 
 /* Add padding and return the message digest. */
 static int sha1_final(struct shash_desc *desc, u8 *out)
 {
-	struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+	struct sha1_state *sctx = shash_desc_ctx(desc);
 	unsigned int i, index, padlen;
 	__be32 *dst = (__be32 *)out;
 	__be64 bits;
@@ -106,7 +102,7 @@ static int sha1_final(struct shash_desc *desc, u8 *out)
 	/* We need to fill a whole block for __sha1_update() */
 	if (padlen <= 56) {
 		sctx->count += padlen;
-		memcpy(sctx->data + index, padding, padlen);
+		memcpy(sctx->buffer + index, padding, padlen);
 	} else {
 		__sha1_update(sctx, padding, padlen, index);
 	}
@@ -114,7 +110,7 @@ static int sha1_final(struct shash_desc *desc, u8 *out)
 
 	/* Store state in digest */
 	for (i = 0; i < 5; i++)
-		dst[i] = cpu_to_be32(((u32 *)sctx)[i]);
+		dst[i] = cpu_to_be32(sctx->state[i]);
 
 	/* Wipe context */
 	memset(sctx, 0, sizeof(*sctx));
@@ -124,7 +120,7 @@ static int sha1_final(struct shash_desc *desc, u8 *out)
 
 static int sha1_export(struct shash_desc *desc, void *out)
 {
-	struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+	struct sha1_state *sctx = shash_desc_ctx(desc);
 	memcpy(out, sctx, sizeof(*sctx));
 	return 0;
 }
@@ -132,7 +128,7 @@ static int sha1_export(struct shash_desc *desc, void *out)
 
 static int sha1_import(struct shash_desc *desc, const void *in)
 {
-	struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+	struct sha1_state *sctx = shash_desc_ctx(desc);
 	memcpy(sctx, in, sizeof(*sctx));
 	return 0;
 }
@@ -141,12 +137,12 @@ static int sha1_import(struct shash_desc *desc, const void *in)
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_init,
-	.update		=	sha1_update,
+	.update		=	sha1_update_arm,
 	.final		=	sha1_final,
 	.export		=	sha1_export,
 	.import		=	sha1_import,
-	.descsize	=	sizeof(struct SHA1_CTX),
-	.statesize	=	sizeof(struct SHA1_CTX),
+	.descsize	=	sizeof(struct sha1_state),
+	.statesize	=	sizeof(struct sha1_state),
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-asm",

arch/arm/crypto/sha1_neon_glue.c

@@ -0,0 +1,197 @@
+/*
+ * Glue code for the SHA1 Secure Hash Algorithm assembler implementation using
+ * ARM NEON instructions.
+ *
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This file is based on sha1_generic.c and sha1_ssse3_glue.c:
+ *  Copyright (c) Alan Smithee.
+ *  Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
+ *  Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
+ *  Copyright (c) Mathias Krause <minipli@googlemail.com>
+ *  Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <crypto/sha.h>
+#include <asm/byteorder.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/crypto/sha1.h>
+
+
+asmlinkage void sha1_transform_neon(void *state_h, const char *data,
+				    unsigned int rounds);
+
+
+static int sha1_neon_init(struct shash_desc *desc)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha1_state){
+		.state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+	};
+
+	return 0;
+}
+
+static int __sha1_neon_update(struct shash_desc *desc, const u8 *data,
+			       unsigned int len, unsigned int partial)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	unsigned int done = 0;
+
+	sctx->count += len;
+
+	if (partial) {
+		done = SHA1_BLOCK_SIZE - partial;
+		memcpy(sctx->buffer + partial, data, done);
+		sha1_transform_neon(sctx->state, sctx->buffer, 1);
+	}
+
+	if (len - done >= SHA1_BLOCK_SIZE) {
+		const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE;
+
+		sha1_transform_neon(sctx->state, data + done, rounds);
+		done += rounds * SHA1_BLOCK_SIZE;
+	}
+
+	memcpy(sctx->buffer, data + done, len - done);
+
+	return 0;
+}
+
+static int sha1_neon_update(struct shash_desc *desc, const u8 *data,
+			     unsigned int len)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
+	int res;
+
+	/* Handle the fast case right here */
+	if (partial + len < SHA1_BLOCK_SIZE) {
+		sctx->count += len;
+		memcpy(sctx->buffer + partial, data, len);
+
+		return 0;
+	}
+
+	if (!may_use_simd()) {
+		res = sha1_update_arm(desc, data, len);
+	} else {
+		kernel_neon_begin();
+		res = __sha1_neon_update(desc, data, len, partial);
+		kernel_neon_end();
+	}
+
+	return res;
+}
+
+
+/* Add padding and return the message digest. */
+static int sha1_neon_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	unsigned int i, index, padlen;
+	__be32 *dst = (__be32 *)out;
+	__be64 bits;
+	static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
+
+	bits = cpu_to_be64(sctx->count << 3);
+
+	/* Pad out to 56 mod 64 and append length */
+	index = sctx->count % SHA1_BLOCK_SIZE;
+	padlen = (index < 56) ? (56 - index) : ((SHA1_BLOCK_SIZE+56) - index);
+	if (!may_use_simd()) {
+		sha1_update_arm(desc, padding, padlen);
+		sha1_update_arm(desc, (const u8 *)&bits, sizeof(bits));
+	} else {
+		kernel_neon_begin();
+		/* We need to fill a whole block for __sha1_neon_update() */
+		if (padlen <= 56) {
+			sctx->count += padlen;
+			memcpy(sctx->buffer + index, padding, padlen);
+		} else {
+			__sha1_neon_update(desc, padding, padlen, index);
+		}
+		__sha1_neon_update(desc, (const u8 *)&bits, sizeof(bits), 56);
+		kernel_neon_end();
+	}
+
+	/* Store state in digest */
+	for (i = 0; i < 5; i++)
+		dst[i] = cpu_to_be32(sctx->state[i]);
+
+	/* Wipe context */
+	memset(sctx, 0, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha1_neon_export(struct shash_desc *desc, void *out)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(out, sctx, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha1_neon_import(struct shash_desc *desc, const void *in)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(sctx, in, sizeof(*sctx));
+
+	return 0;
+}
+
+static struct shash_alg alg = {
+	.digestsize	=	SHA1_DIGEST_SIZE,
+	.init		=	sha1_neon_init,
+	.update		=	sha1_neon_update,
+	.final		=	sha1_neon_final,
+	.export		=	sha1_neon_export,
+	.import		=	sha1_neon_import,
+	.descsize	=	sizeof(struct sha1_state),
+	.statesize	=	sizeof(struct sha1_state),
+	.base		=	{
+		.cra_name		= "sha1",
+		.cra_driver_name	= "sha1-neon",
+		.cra_priority		= 250,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA1_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+};
+
+static int __init sha1_neon_mod_init(void)
+{
+	if (!cpu_has_neon())
+		return -ENODEV;
+
+	return crypto_register_shash(&alg);
+}
+
+static void __exit sha1_neon_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(sha1_neon_mod_init);
+module_exit(sha1_neon_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, NEON accelerated");
+MODULE_ALIAS("sha1");

arch/arm/crypto/sha512-armv7-neon.S

@@ -0,0 +1,455 @@
+/* sha512-armv7-neon.S  -  ARM/NEON assembly implementation of SHA-512 transform
+ *
+ * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/linkage.h>
+
+
+.syntax unified
+.code   32
+.fpu neon
+
+.text
+
+/* structure of SHA512_CONTEXT */
+#define hd_a 0
+#define hd_b ((hd_a) + 8)
+#define hd_c ((hd_b) + 8)
+#define hd_d ((hd_c) + 8)
+#define hd_e ((hd_d) + 8)
+#define hd_f ((hd_e) + 8)
+#define hd_g ((hd_f) + 8)
+
+/* register macros */
+#define RK %r2
+
+#define RA d0
+#define RB d1
+#define RC d2
+#define RD d3
+#define RE d4
+#define RF d5
+#define RG d6
+#define RH d7
+
+#define RT0 d8
+#define RT1 d9
+#define RT2 d10
+#define RT3 d11
+#define RT4 d12
+#define RT5 d13
+#define RT6 d14
+#define RT7 d15
+
+#define RT01q q4
+#define RT23q q5
+#define RT45q q6
+#define RT67q q7
+
+#define RW0 d16
+#define RW1 d17
+#define RW2 d18
+#define RW3 d19
+#define RW4 d20
+#define RW5 d21
+#define RW6 d22
+#define RW7 d23
+#define RW8 d24
+#define RW9 d25
+#define RW10 d26
+#define RW11 d27
+#define RW12 d28
+#define RW13 d29
+#define RW14 d30
+#define RW15 d31
+
+#define RW01q q8
+#define RW23q q9
+#define RW45q q10
+#define RW67q q11
+#define RW89q q12
+#define RW1011q q13
+#define RW1213q q14
+#define RW1415q q15
+
+/***********************************************************************
+ * ARM assembly implementation of sha512 transform
+ ***********************************************************************/
+#define rounds2_0_63(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, rw01q, rw2, \
+                     rw23q, rw1415q, rw9, rw10, interleave_op, arg1) \
+	/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
+	vshr.u64 RT2, re, #14; \
+	vshl.u64 RT3, re, #64 - 14; \
+	interleave_op(arg1); \
+	vshr.u64 RT4, re, #18; \
+	vshl.u64 RT5, re, #64 - 18; \
+	vld1.64 {RT0}, [RK]!; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, re, #41; \
+	vshl.u64 RT5, re, #64 - 41; \
+	vadd.u64 RT0, RT0, rw0; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vmov.64 RT7, re; \
+	veor.64 RT1, RT2, RT3; \
+	vbsl.64 RT7, rf, rg; \
+	\
+	vadd.u64 RT1, RT1, rh; \
+	vshr.u64 RT2, ra, #28; \
+	vshl.u64 RT3, ra, #64 - 28; \
+	vadd.u64 RT1, RT1, RT0; \
+	vshr.u64 RT4, ra, #34; \
+	vshl.u64 RT5, ra, #64 - 34; \
+	vadd.u64 RT1, RT1, RT7; \
+	\
+	/* h = Sum0 (a) + Maj (a, b, c); */ \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, ra, #39; \
+	vshl.u64 RT5, ra, #64 - 39; \
+	veor.64 RT0, ra, rb; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vbsl.64 RT0, rc, rb; \
+	vadd.u64 rd, rd, RT1; /* d+=t1; */ \
+	veor.64 rh, RT2, RT3; \
+	\
+	/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
+	vshr.u64 RT2, rd, #14; \
+	vshl.u64 RT3, rd, #64 - 14; \
+	vadd.u64 rh, rh, RT0; \
+	vshr.u64 RT4, rd, #18; \
+	vshl.u64 RT5, rd, #64 - 18; \
+	vadd.u64 rh, rh, RT1; /* h+=t1; */ \
+	vld1.64 {RT0}, [RK]!; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, rd, #41; \
+	vshl.u64 RT5, rd, #64 - 41; \
+	vadd.u64 RT0, RT0, rw1; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vmov.64 RT7, rd; \
+	veor.64 RT1, RT2, RT3; \
+	vbsl.64 RT7, re, rf; \
+	\
+	vadd.u64 RT1, RT1, rg; \
+	vshr.u64 RT2, rh, #28; \
+	vshl.u64 RT3, rh, #64 - 28; \
+	vadd.u64 RT1, RT1, RT0; \
+	vshr.u64 RT4, rh, #34; \
+	vshl.u64 RT5, rh, #64 - 34; \
+	vadd.u64 RT1, RT1, RT7; \
+	\
+	/* g = Sum0 (h) + Maj (h, a, b); */ \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, rh, #39; \
+	vshl.u64 RT5, rh, #64 - 39; \
+	veor.64 RT0, rh, ra; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vbsl.64 RT0, rb, ra; \
+	vadd.u64 rc, rc, RT1; /* c+=t1; */ \
+	veor.64 rg, RT2, RT3; \
+	\
+	/* w[0] += S1 (w[14]) + w[9] + S0 (w[1]); */ \
+	/* w[1] += S1 (w[15]) + w[10] + S0 (w[2]); */ \
+	\
+	/**** S0(w[1:2]) */ \
+	\
+	/* w[0:1] += w[9:10] */ \
+	/* RT23q = rw1:rw2 */ \
+	vext.u64 RT23q, rw01q, rw23q, #1; \
+	vadd.u64 rw0, rw9; \
+	vadd.u64 rg, rg, RT0; \
+	vadd.u64 rw1, rw10;\
+	vadd.u64 rg, rg, RT1; /* g+=t1; */ \
+	\
+	vshr.u64 RT45q, RT23q, #1; \
+	vshl.u64 RT67q, RT23q, #64 - 1; \
+	vshr.u64 RT01q, RT23q, #8; \
+	veor.u64 RT45q, RT45q, RT67q; \
+	vshl.u64 RT67q, RT23q, #64 - 8; \
+	veor.u64 RT45q, RT45q, RT01q; \
+	vshr.u64 RT01q, RT23q, #7; \
+	veor.u64 RT45q, RT45q, RT67q; \
+	\
+	/**** S1(w[14:15]) */ \
+	vshr.u64 RT23q, rw1415q, #6; \
+	veor.u64 RT01q, RT01q, RT45q; \
+	vshr.u64 RT45q, rw1415q, #19; \
+	vshl.u64 RT67q, rw1415q, #64 - 19; \
+	veor.u64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT45q, rw1415q, #61; \
+	veor.u64 RT23q, RT23q, RT67q; \
+	vshl.u64 RT67q, rw1415q, #64 - 61; \
+	veor.u64 RT23q, RT23q, RT45q; \
+	vadd.u64 rw01q, RT01q; /* w[0:1] += S(w[1:2]) */ \
+	veor.u64 RT01q, RT23q, RT67q;
+#define vadd_RT01q(rw01q) \
+	/* w[0:1] += S(w[14:15]) */ \
+	vadd.u64 rw01q, RT01q;
+
+#define dummy(_) /*_*/
+
+#define rounds2_64_79(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, \
+	              interleave_op1, arg1, interleave_op2, arg2) \
+	/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
+	vshr.u64 RT2, re, #14; \
+	vshl.u64 RT3, re, #64 - 14; \
+	interleave_op1(arg1); \
+	vshr.u64 RT4, re, #18; \
+	vshl.u64 RT5, re, #64 - 18; \
+	interleave_op2(arg2); \
+	vld1.64 {RT0}, [RK]!; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, re, #41; \
+	vshl.u64 RT5, re, #64 - 41; \
+	vadd.u64 RT0, RT0, rw0; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vmov.64 RT7, re; \
+	veor.64 RT1, RT2, RT3; \
+	vbsl.64 RT7, rf, rg; \
+	\
+	vadd.u64 RT1, RT1, rh; \
+	vshr.u64 RT2, ra, #28; \
+	vshl.u64 RT3, ra, #64 - 28; \
+	vadd.u64 RT1, RT1, RT0; \
+	vshr.u64 RT4, ra, #34; \
+	vshl.u64 RT5, ra, #64 - 34; \
+	vadd.u64 RT1, RT1, RT7; \
+	\
+	/* h = Sum0 (a) + Maj (a, b, c); */ \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, ra, #39; \
+	vshl.u64 RT5, ra, #64 - 39; \
+	veor.64 RT0, ra, rb; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vbsl.64 RT0, rc, rb; \
+	vadd.u64 rd, rd, RT1; /* d+=t1; */ \
+	veor.64 rh, RT2, RT3; \
+	\
+	/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
+	vshr.u64 RT2, rd, #14; \
+	vshl.u64 RT3, rd, #64 - 14; \
+	vadd.u64 rh, rh, RT0; \
+	vshr.u64 RT4, rd, #18; \
+	vshl.u64 RT5, rd, #64 - 18; \
+	vadd.u64 rh, rh, RT1; /* h+=t1; */ \
+	vld1.64 {RT0}, [RK]!; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, rd, #41; \
+	vshl.u64 RT5, rd, #64 - 41; \
+	vadd.u64 RT0, RT0, rw1; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vmov.64 RT7, rd; \
+	veor.64 RT1, RT2, RT3; \
+	vbsl.64 RT7, re, rf; \
+	\
+	vadd.u64 RT1, RT1, rg; \
+	vshr.u64 RT2, rh, #28; \
+	vshl.u64 RT3, rh, #64 - 28; \
+	vadd.u64 RT1, RT1, RT0; \
+	vshr.u64 RT4, rh, #34; \
+	vshl.u64 RT5, rh, #64 - 34; \
+	vadd.u64 RT1, RT1, RT7; \
+	\
+	/* g = Sum0 (h) + Maj (h, a, b); */ \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, rh, #39; \
+	vshl.u64 RT5, rh, #64 - 39; \
+	veor.64 RT0, rh, ra; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vbsl.64 RT0, rb, ra; \
+	vadd.u64 rc, rc, RT1; /* c+=t1; */ \
+	veor.64 rg, RT2, RT3;
+#define vadd_rg_RT0(rg) \
+	vadd.u64 rg, rg, RT0;
+#define vadd_rg_RT1(rg) \
+	vadd.u64 rg, rg, RT1; /* g+=t1; */
+
+.align 3
+ENTRY(sha512_transform_neon)
+	/* Input:
+	 *	%r0: SHA512_CONTEXT
+	 *	%r1: data
+	 *	%r2: u64 k[] constants
+	 *	%r3: nblks
+	 */
+	push {%lr};
+
+	mov %lr, #0;
+
+	/* Load context to d0-d7 */
+	vld1.64 {RA-RD}, [%r0]!;
+	vld1.64 {RE-RH}, [%r0];
+	sub %r0, #(4*8);
+
+	/* Load input to w[16], d16-d31 */
+	/* NOTE: Assumes that on ARMv7 unaligned accesses are always allowed. */
+	vld1.64 {RW0-RW3}, [%r1]!;
+	vld1.64 {RW4-RW7}, [%r1]!;
+	vld1.64 {RW8-RW11}, [%r1]!;
+	vld1.64 {RW12-RW15}, [%r1]!;
+#ifdef __ARMEL__
+	/* byteswap */
+	vrev64.8 RW01q, RW01q;
+	vrev64.8 RW23q, RW23q;
+	vrev64.8 RW45q, RW45q;
+	vrev64.8 RW67q, RW67q;
+	vrev64.8 RW89q, RW89q;
+	vrev64.8 RW1011q, RW1011q;
+	vrev64.8 RW1213q, RW1213q;
+	vrev64.8 RW1415q, RW1415q;
+#endif
+
+	/* EABI says that d8-d15 must be preserved by callee. */
+	/*vpush {RT0-RT7};*/
+
+.Loop:
+	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
+		     RW23q, RW1415q, RW9, RW10, dummy, _);
+	b .Lenter_rounds;
+
+.Loop_rounds:
+	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
+		     RW23q, RW1415q, RW9, RW10, vadd_RT01q, RW1415q);
+.Lenter_rounds:
+	rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3, RW23q, RW4,
+		     RW45q, RW01q, RW11, RW12, vadd_RT01q, RW01q);
+	rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5, RW45q, RW6,
+		     RW67q, RW23q, RW13, RW14, vadd_RT01q, RW23q);
+	rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7, RW67q, RW8,
+		     RW89q, RW45q, RW15, RW0, vadd_RT01q, RW45q);
+	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9, RW89q, RW10,
+		     RW1011q, RW67q, RW1, RW2, vadd_RT01q, RW67q);
+	rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11, RW1011q, RW12,
+		     RW1213q, RW89q, RW3, RW4, vadd_RT01q, RW89q);
+	add %lr, #16;
+	rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13, RW1213q, RW14,
+		     RW1415q, RW1011q, RW5, RW6, vadd_RT01q, RW1011q);
+	cmp %lr, #64;
+	rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15, RW1415q, RW0,
+		     RW01q, RW1213q, RW7, RW8, vadd_RT01q, RW1213q);
+	bne .Loop_rounds;
+
+	subs %r3, #1;
+
+	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1,
+		      vadd_RT01q, RW1415q, dummy, _);
+	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3,
+		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
+	beq .Lhandle_tail;
+	vld1.64 {RW0-RW3}, [%r1]!;
+	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
+		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
+		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+#ifdef __ARMEL__
+	vrev64.8 RW01q, RW01q;
+	vrev64.8 RW23q, RW23q;
+#endif
+	vld1.64 {RW4-RW7}, [%r1]!;
+	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
+		      vadd_rg_RT0, RA, vadd_rg_RT1, RA);
+	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
+		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
+#ifdef __ARMEL__
+	vrev64.8 RW45q, RW45q;
+	vrev64.8 RW67q, RW67q;
+#endif
+	vld1.64 {RW8-RW11}, [%r1]!;
+	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
+		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
+		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+#ifdef __ARMEL__
+	vrev64.8 RW89q, RW89q;
+	vrev64.8 RW1011q, RW1011q;
+#endif
+	vld1.64 {RW12-RW15}, [%r1]!;
+	vadd_rg_RT0(RA);
+	vadd_rg_RT1(RA);
+
+	/* Load context */
+	vld1.64 {RT0-RT3}, [%r0]!;
+	vld1.64 {RT4-RT7}, [%r0];
+	sub %r0, #(4*8);
+
+#ifdef __ARMEL__
+	vrev64.8 RW1213q, RW1213q;
+	vrev64.8 RW1415q, RW1415q;
+#endif
+
+	vadd.u64 RA, RT0;
+	vadd.u64 RB, RT1;
+	vadd.u64 RC, RT2;
+	vadd.u64 RD, RT3;
+	vadd.u64 RE, RT4;
+	vadd.u64 RF, RT5;
+	vadd.u64 RG, RT6;
+	vadd.u64 RH, RT7;
+
+	/* Store the first half of context */
+	vst1.64 {RA-RD}, [%r0]!;
+	sub RK, $(8*80);
+	vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
+	mov %lr, #0;
+	sub %r0, #(4*8);
+
+	b .Loop;
+
+.Lhandle_tail:
+	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
+		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
+		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
+		      vadd_rg_RT0, RA, vadd_rg_RT1, RA);
+	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
+		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
+	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
+		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
+		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+
+	/* Load context to d16-d23 */
+	vld1.64 {RW0-RW3}, [%r0]!;
+	vadd_rg_RT0(RA);
+	vld1.64 {RW4-RW7}, [%r0];
+	vadd_rg_RT1(RA);
+	sub %r0, #(4*8);
+
+	vadd.u64 RA, RW0;
+	vadd.u64 RB, RW1;
+	vadd.u64 RC, RW2;
+	vadd.u64 RD, RW3;
+	vadd.u64 RE, RW4;
+	vadd.u64 RF, RW5;
+	vadd.u64 RG, RW6;
+	vadd.u64 RH, RW7;
+
+	/* Store the first half of context */
+	vst1.64 {RA-RD}, [%r0]!;
+
+	/* Clear used registers */
+	/* d16-d31 */
+	veor.u64 RW01q, RW01q;
+	veor.u64 RW23q, RW23q;
+	veor.u64 RW45q, RW45q;
+	veor.u64 RW67q, RW67q;
+	vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
+	veor.u64 RW89q, RW89q;
+	veor.u64 RW1011q, RW1011q;
+	veor.u64 RW1213q, RW1213q;
+	veor.u64 RW1415q, RW1415q;
+	/* d8-d15 */
+	/*vpop {RT0-RT7};*/
+	/* d0-d7 (q0-q3) */
+	veor.u64 %q0, %q0;
+	veor.u64 %q1, %q1;
+	veor.u64 %q2, %q2;
+	veor.u64 %q3, %q3;
+
+	pop {%pc};
+ENDPROC(sha512_transform_neon)

arch/arm/crypto/sha512_neon_glue.c

@@ -0,0 +1,305 @@
+/*
+ * Glue code for the SHA512 Secure Hash Algorithm assembly implementation
+ * using NEON instructions.
+ *
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This file is based on sha512_ssse3_glue.c:
+ *   Copyright (C) 2013 Intel Corporation
+ *   Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <crypto/sha.h>
+#include <asm/byteorder.h>
+#include <asm/simd.h>
+#include <asm/neon.h>
+
+
+static const u64 sha512_k[] = {
+	0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL,
+	0xb5c0fbcfec4d3b2fULL, 0xe9b5dba58189dbbcULL,
+	0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
+	0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL,
+	0xd807aa98a3030242ULL, 0x12835b0145706fbeULL,
+	0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,
+	0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL,
+	0x9bdc06a725c71235ULL, 0xc19bf174cf692694ULL,
+	0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,
+	0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL,
+	0x2de92c6f592b0275ULL, 0x4a7484aa6ea6e483ULL,
+	0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,
+	0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL,
+	0xb00327c898fb213fULL, 0xbf597fc7beef0ee4ULL,
+	0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,
+	0x06ca6351e003826fULL, 0x142929670a0e6e70ULL,
+	0x27b70a8546d22ffcULL, 0x2e1b21385c26c926ULL,
+	0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,
+	0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL,
+	0x81c2c92e47edaee6ULL, 0x92722c851482353bULL,
+	0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,
+	0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL,
+	0xd192e819d6ef5218ULL, 0xd69906245565a910ULL,
+	0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,
+	0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL,
+	0x2748774cdf8eeb99ULL, 0x34b0bcb5e19b48a8ULL,
+	0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,
+	0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL,
+	0x748f82ee5defb2fcULL, 0x78a5636f43172f60ULL,
+	0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,
+	0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL,
+	0xbef9a3f7b2c67915ULL, 0xc67178f2e372532bULL,
+	0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,
+	0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL,
+	0x06f067aa72176fbaULL, 0x0a637dc5a2c898a6ULL,
+	0x113f9804bef90daeULL, 0x1b710b35131c471bULL,
+	0x28db77f523047d84ULL, 0x32caab7b40c72493ULL,
+	0x3c9ebe0a15c9bebcULL, 0x431d67c49c100d4cULL,
+	0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,
+	0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL
+};
+
+
+asmlinkage void sha512_transform_neon(u64 *digest, const void *data,
+				      const u64 k[], unsigned int num_blks);
+
+
+static int sha512_neon_init(struct shash_desc *desc)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	sctx->state[0] = SHA512_H0;
+	sctx->state[1] = SHA512_H1;
+	sctx->state[2] = SHA512_H2;
+	sctx->state[3] = SHA512_H3;
+	sctx->state[4] = SHA512_H4;
+	sctx->state[5] = SHA512_H5;
+	sctx->state[6] = SHA512_H6;
+	sctx->state[7] = SHA512_H7;
+	sctx->count[0] = sctx->count[1] = 0;
+
+	return 0;
+}
+
+static int __sha512_neon_update(struct shash_desc *desc, const u8 *data,
+				unsigned int len, unsigned int partial)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+	unsigned int done = 0;
+
+	sctx->count[0] += len;
+	if (sctx->count[0] < len)
+		sctx->count[1]++;
+
+	if (partial) {
+		done = SHA512_BLOCK_SIZE - partial;
+		memcpy(sctx->buf + partial, data, done);
+		sha512_transform_neon(sctx->state, sctx->buf, sha512_k, 1);
+	}
+
+	if (len - done >= SHA512_BLOCK_SIZE) {
+		const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE;
+
+		sha512_transform_neon(sctx->state, data + done, sha512_k,
+				      rounds);
+
+		done += rounds * SHA512_BLOCK_SIZE;
+	}
+
+	memcpy(sctx->buf, data + done, len - done);
+
+	return 0;
+}
+
+static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
+			     unsigned int len)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE;
+	int res;
+
+	/* Handle the fast case right here */
+	if (partial + len < SHA512_BLOCK_SIZE) {
+		sctx->count[0] += len;
+		if (sctx->count[0] < len)
+			sctx->count[1]++;
+		memcpy(sctx->buf + partial, data, len);
+
+		return 0;
+	}
+
+	if (!may_use_simd()) {
+		res = crypto_sha512_update(desc, data, len);
+	} else {
+		kernel_neon_begin();
+		res = __sha512_neon_update(desc, data, len, partial);
+		kernel_neon_end();
+	}
+
+	return res;
+}
+
+
+/* Add padding and return the message digest. */
+static int sha512_neon_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+	unsigned int i, index, padlen;
+	__be64 *dst = (__be64 *)out;
+	__be64 bits[2];
+	static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, };
+
+	/* save number of bits */
+	bits[1] = cpu_to_be64(sctx->count[0] << 3);
+	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
+
+	/* Pad out to 112 mod 128 and append length */
+	index = sctx->count[0] & 0x7f;
+	padlen = (index < 112) ? (112 - index) : ((128+112) - index);
+
+	if (!may_use_simd()) {
+		crypto_sha512_update(desc, padding, padlen);
+		crypto_sha512_update(desc, (const u8 *)&bits, sizeof(bits));
+	} else {
+		kernel_neon_begin();
+		/* We need to fill a whole block for __sha512_neon_update() */
+		if (padlen <= 112) {
+			sctx->count[0] += padlen;
+			if (sctx->count[0] < padlen)
+				sctx->count[1]++;
+			memcpy(sctx->buf + index, padding, padlen);
+		} else {
+			__sha512_neon_update(desc, padding, padlen, index);
+		}
+		__sha512_neon_update(desc, (const u8 *)&bits,
+					sizeof(bits), 112);
+		kernel_neon_end();
+	}
+
+	/* Store state in digest */
+	for (i = 0; i < 8; i++)
+		dst[i] = cpu_to_be64(sctx->state[i]);
+
+	/* Wipe context */
+	memset(sctx, 0, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha512_neon_export(struct shash_desc *desc, void *out)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(out, sctx, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha512_neon_import(struct shash_desc *desc, const void *in)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(sctx, in, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha384_neon_init(struct shash_desc *desc)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	sctx->state[0] = SHA384_H0;
+	sctx->state[1] = SHA384_H1;
+	sctx->state[2] = SHA384_H2;
+	sctx->state[3] = SHA384_H3;
+	sctx->state[4] = SHA384_H4;
+	sctx->state[5] = SHA384_H5;
+	sctx->state[6] = SHA384_H6;
+	sctx->state[7] = SHA384_H7;
+
+	sctx->count[0] = sctx->count[1] = 0;
+
+	return 0;
+}
+
+static int sha384_neon_final(struct shash_desc *desc, u8 *hash)
+{
+	u8 D[SHA512_DIGEST_SIZE];
+
+	sha512_neon_final(desc, D);
+
+	memcpy(hash, D, SHA384_DIGEST_SIZE);
+	memset(D, 0, SHA512_DIGEST_SIZE);
+
+	return 0;
+}
+
+static struct shash_alg algs[] = { {
+	.digestsize	=	SHA512_DIGEST_SIZE,
+	.init		=	sha512_neon_init,
+	.update		=	sha512_neon_update,
+	.final		=	sha512_neon_final,
+	.export		=	sha512_neon_export,
+	.import		=	sha512_neon_import,
+	.descsize	=	sizeof(struct sha512_state),
+	.statesize	=	sizeof(struct sha512_state),
+	.base		=	{
+		.cra_name	=	"sha512",
+		.cra_driver_name =	"sha512-neon",
+		.cra_priority	=	250,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA512_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+},  {
+	.digestsize	=	SHA384_DIGEST_SIZE,
+	.init		=	sha384_neon_init,
+	.update		=	sha512_neon_update,
+	.final		=	sha384_neon_final,
+	.export		=	sha512_neon_export,
+	.import		=	sha512_neon_import,
+	.descsize	=	sizeof(struct sha512_state),
+	.statesize	=	sizeof(struct sha512_state),
+	.base		=	{
+		.cra_name	=	"sha384",
+		.cra_driver_name =	"sha384-neon",
+		.cra_priority	=	250,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA384_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+} };
+
+static int __init sha512_neon_mod_init(void)
+{
+	if (!cpu_has_neon())
+		return -ENODEV;
+
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha512_neon_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_init(sha512_neon_mod_init);
+module_exit(sha512_neon_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated");
+
+MODULE_ALIAS("sha512");
+MODULE_ALIAS("sha384");

arch/arm/include/asm/assembler.h

@@ -24,6 +24,8 @@
 #include <asm/domain.h>
 #include <asm/opcodes-virt.h>
 #include <asm/asm-offsets.h>
+#include <asm/page.h>
+#include <asm/thread_info.h>
 
 #define IOMEM(x)	(x)
 
@@ -179,10 +181,10 @@
  * Get current thread_info.
  */
 	.macro	get_thread_info, rd
- ARM(	mov	\rd, sp, lsr #13	)
+ ARM(	mov	\rd, sp, lsr #THREAD_SIZE_ORDER + PAGE_SHIFT	)
  THUMB(	mov	\rd, sp			)
- THUMB(	lsr	\rd, \rd, #13		)
-	mov	\rd, \rd, lsl #13
+ THUMB(	lsr	\rd, \rd, #THREAD_SIZE_ORDER + PAGE_SHIFT	)
+	mov	\rd, \rd, lsl #THREAD_SIZE_ORDER + PAGE_SHIFT
 	.endm
 
 /*
@@ -425,4 +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__ */

arch/arm/include/asm/cputype.h

@@ -62,17 +62,18 @@
 #define ARM_CPU_IMP_ARM			0x41
 #define ARM_CPU_IMP_INTEL		0x69
 
-#define ARM_CPU_PART_ARM1136		0xB360
-#define ARM_CPU_PART_ARM1156		0xB560
-#define ARM_CPU_PART_ARM1176		0xB760
-#define ARM_CPU_PART_ARM11MPCORE	0xB020
-#define ARM_CPU_PART_CORTEX_A8		0xC080
-#define ARM_CPU_PART_CORTEX_A9		0xC090
-#define ARM_CPU_PART_CORTEX_A5		0xC050
-#define ARM_CPU_PART_CORTEX_A15		0xC0F0
-#define ARM_CPU_PART_CORTEX_A7		0xC070
-#define ARM_CPU_PART_CORTEX_A12		0xC0D0
-#define ARM_CPU_PART_CORTEX_A17		0xC0E0
+/* ARM implemented processors */
+#define ARM_CPU_PART_ARM1136		0x4100b360
+#define ARM_CPU_PART_ARM1156		0x4100b560
+#define ARM_CPU_PART_ARM1176		0x4100b760
+#define ARM_CPU_PART_ARM11MPCORE	0x4100b020
+#define ARM_CPU_PART_CORTEX_A8		0x4100c080
+#define ARM_CPU_PART_CORTEX_A9		0x4100c090
+#define ARM_CPU_PART_CORTEX_A5		0x4100c050
+#define ARM_CPU_PART_CORTEX_A7		0x4100c070
+#define ARM_CPU_PART_CORTEX_A12		0x4100c0d0
+#define ARM_CPU_PART_CORTEX_A17		0x4100c0e0
+#define ARM_CPU_PART_CORTEX_A15		0x4100c0f0
 
 #define ARM_CPU_XSCALE_ARCH_MASK	0xe000
 #define ARM_CPU_XSCALE_ARCH_V1		0x2000
@@ -171,14 +172,24 @@ static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
 	return (read_cpuid_id() & 0xFF000000) >> 24;
 }
 
-static inline unsigned int __attribute_const__ read_cpuid_part_number(void)
+/*
+ * The CPU part number is meaningless without referring to the CPU
+ * implementer: implementers are free to define their own part numbers
+ * which are permitted to clash with other implementer part numbers.
+ */
+static inline unsigned int __attribute_const__ read_cpuid_part(void)
+{
+	return read_cpuid_id() & 0xff00fff0;
+}
+
+static inline unsigned int __attribute_const__ __deprecated read_cpuid_part_number(void)
 {
 	return read_cpuid_id() & 0xFFF0;
 }
 
 static inline unsigned int __attribute_const__ xscale_cpu_arch_version(void)
 {
-	return read_cpuid_part_number() & ARM_CPU_XSCALE_ARCH_MASK;
+	return read_cpuid_id() & ARM_CPU_XSCALE_ARCH_MASK;
 }
 
 static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)

arch/arm/include/asm/crypto/sha1.h

@@ -0,0 +1,10 @@
+#ifndef ASM_ARM_CRYPTO_SHA1_H
+#define ASM_ARM_CRYPTO_SHA1_H
+
+#include <linux/crypto.h>
+#include <crypto/sha.h>
+
+extern int sha1_update_arm(struct shash_desc *desc, const u8 *data,
+			   unsigned int len);
+
+#endif

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

arch/arm/include/asm/glue-proc.h

@@ -221,15 +221,6 @@
 # endif
 #endif
 
-#ifdef CONFIG_CPU_V7
-# ifdef CPU_NAME
-#  undef  MULTI_CPU
-#  define MULTI_CPU
-# else
-#  define CPU_NAME cpu_v7
-# endif
-#endif
-
 #ifdef CONFIG_CPU_V7M
 # ifdef CPU_NAME
 #  undef  MULTI_CPU
@@ -248,6 +239,15 @@
 # endif
 #endif
 
+#ifdef CONFIG_CPU_V7
+/*
+ * Cortex-A9 needs a different suspend/resume function, so we need
+ * multiple CPU support for ARMv7 anyway.
+ */
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+#endif
+
 #ifndef MULTI_CPU
 #define cpu_proc_init			__glue(CPU_NAME,_proc_init)
 #define cpu_proc_fin			__glue(CPU_NAME,_proc_fin)

arch/arm/include/asm/mcpm.h

@@ -217,6 +217,22 @@ int __mcpm_cluster_state(unsigned int cluster);
 int __init mcpm_sync_init(
 	void (*power_up_setup)(unsigned int affinity_level));
 
+/**
+ * mcpm_loopback - make a run through the MCPM low-level code
+ *
+ * @cache_disable: pointer to function performing cache disabling
+ *
+ * This exercises the MCPM machinery by soft resetting the CPU and branching
+ * to the MCPM low-level entry code before returning to the caller.
+ * The @cache_disable function must do the necessary cache disabling to
+ * let the regular kernel init code turn it back on as if the CPU was
+ * hotplugged in. The MCPM state machine is set as if the cluster was
+ * initialized meaning the power_up_setup callback passed to mcpm_sync_init()
+ * will be invoked for all affinity levels. This may be useful to initialize
+ * some resources such as enabling the CCI that requires the cache to be off, or simply for testing purposes.
+ */
+int __init mcpm_loopback(void (*cache_disable)(void));
+
 void __init mcpm_smp_set_ops(void);
 
 #else

arch/arm/include/asm/mcs_spinlock.h

@@ -0,0 +1,23 @@
+#ifndef __ASM_MCS_LOCK_H
+#define __ASM_MCS_LOCK_H
+
+#ifdef CONFIG_SMP
+#include <asm/spinlock.h>
+
+/* MCS spin-locking. */
+#define arch_mcs_spin_lock_contended(lock)				\
+do {									\
+	/* Ensure prior stores are observed before we enter wfe. */	\
+	smp_mb();							\
+	while (!(smp_load_acquire(lock)))				\
+		wfe();							\
+} while (0)								\
+
+#define arch_mcs_spin_unlock_contended(lock)				\
+do {									\
+	smp_store_release(lock, 1);					\
+	dsb_sev();							\
+} while (0)
+
+#endif	/* CONFIG_SMP */
+#endif	/* __ASM_MCS_LOCK_H */

arch/arm/include/asm/memory.h

@@ -91,9 +91,7 @@
  * of this define that was meant to.
  * Fortunately, there is no reference for this in noMMU mode, for now.
  */
-#ifndef TASK_SIZE
-#define TASK_SIZE		(CONFIG_DRAM_SIZE)
-#endif
+#define TASK_SIZE		UL(0xffffffff)
 
 #ifndef TASK_UNMAPPED_BASE
 #define TASK_UNMAPPED_BASE	UL(0x00000000)
@@ -150,13 +148,11 @@
 
 /*
  * PLAT_PHYS_OFFSET is the offset (from zero) of the start of physical
- * memory.  This is used for XIP and NoMMU kernels, or by kernels which
- * have their own mach/memory.h.  Assembly code must always use
+ * memory.  This is used for XIP and NoMMU kernels, and on platforms that don't
+ * have CONFIG_ARM_PATCH_PHYS_VIRT. Assembly code must always use
  * PLAT_PHYS_OFFSET and not PHYS_OFFSET.
  */
-#ifndef PLAT_PHYS_OFFSET
 #define PLAT_PHYS_OFFSET	UL(CONFIG_PHYS_OFFSET)
-#endif
 
 #ifndef __ASSEMBLY__
 

arch/arm/include/asm/perf_event.h

@@ -12,15 +12,6 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-/*
- * The ARMv7 CPU PMU supports up to 32 event counters.
- */
-#define ARMPMU_MAX_HWEVENTS		32
-
-#define HW_OP_UNSUPPORTED		0xFFFF
-#define C(_x)				PERF_COUNT_HW_CACHE_##_x
-#define CACHE_OP_UNSUPPORTED		0xFFFF
-
 #ifdef CONFIG_HW_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);

arch/arm/include/asm/pgtable-3level-hwdef.h

@@ -43,7 +43,7 @@
 #define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
 #define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
 #define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
-#define PMD_SECT_RDONLY		(_AT(pmdval_t, 1) << 7)		/* AP[2] */
+#define PMD_SECT_AP2		(_AT(pmdval_t, 1) << 7)		/* read only */
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
 #define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
 #define PMD_SECT_nG		(_AT(pmdval_t, 1) << 11)
@@ -72,6 +72,7 @@
 #define PTE_TABLE_BIT		(_AT(pteval_t, 1) << 1)
 #define PTE_BUFFERABLE		(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
 #define PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
+#define PTE_AP2			(_AT(pteval_t, 1) << 7)		/* AP[2] */
 #define PTE_EXT_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define PTE_EXT_AF		(_AT(pteval_t, 1) << 10)	/* Access Flag */
 #define PTE_EXT_NG		(_AT(pteval_t, 1) << 11)	/* nG */

arch/arm/include/asm/pgtable-3level.h

@@ -79,18 +79,19 @@
 #define L_PTE_PRESENT		(_AT(pteval_t, 3) << 0)		/* Present */
 #define L_PTE_FILE		(_AT(pteval_t, 1) << 2)		/* only when !PRESENT */
 #define L_PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
-#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)		/* AP[2] */
 #define L_PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define L_PTE_YOUNG		(_AT(pteval_t, 1) << 10)	/* AF */
 #define L_PTE_XN		(_AT(pteval_t, 1) << 54)	/* XN */
-#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 55)	/* unused */
-#define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)	/* unused */
+#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 55)
+#define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
 #define L_PTE_NONE		(_AT(pteval_t, 1) << 57)	/* PROT_NONE */
+#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 58)	/* READ ONLY */
 
-#define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
-#define PMD_SECT_DIRTY		(_AT(pmdval_t, 1) << 55)
-#define PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
-#define PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
+#define L_PMD_SECT_VALID	(_AT(pmdval_t, 1) << 0)
+#define L_PMD_SECT_DIRTY	(_AT(pmdval_t, 1) << 55)
+#define L_PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
+#define L_PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
+#define L_PMD_SECT_RDONLY	(_AT(pteval_t, 1) << 58)
 
 /*
  * To be used in assembly code with the upper page attributes.
@@ -207,27 +208,32 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pte_huge(pte)		(pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT))
 #define pte_mkhuge(pte)		(__pte(pte_val(pte) & ~PTE_TABLE_BIT))
 
-#define pmd_young(pmd)		(pmd_val(pmd) & PMD_SECT_AF)
+#define pmd_isset(pmd, val)	((u32)(val) == (val) ? pmd_val(pmd) & (val) \
+						: !!(pmd_val(pmd) & (val)))
+#define pmd_isclear(pmd, val)	(!(pmd_val(pmd) & (val)))
+
+#define pmd_young(pmd)		(pmd_isset((pmd), PMD_SECT_AF))
 
 #define __HAVE_ARCH_PMD_WRITE
-#define pmd_write(pmd)		(!(pmd_val(pmd) & PMD_SECT_RDONLY))
+#define pmd_write(pmd)		(pmd_isclear((pmd), L_PMD_SECT_RDONLY))
+#define pmd_dirty(pmd)		(pmd_isset((pmd), L_PMD_SECT_DIRTY))
 
 #define pmd_hugewillfault(pmd)	(!pmd_young(pmd) || !pmd_write(pmd))
 #define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
-#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !pmd_table(pmd))
+#define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING))
 #endif
 
 #define PMD_BIT_FUNC(fn,op) \
 static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
 
-PMD_BIT_FUNC(wrprotect,	|= PMD_SECT_RDONLY);
+PMD_BIT_FUNC(wrprotect,	|= L_PMD_SECT_RDONLY);
 PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
-PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
-PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
-PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING);
+PMD_BIT_FUNC(mkwrite,   &= ~L_PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkdirty,   |= L_PMD_SECT_DIRTY);
 PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
@@ -241,8 +247,8 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | PMD_SECT_RDONLY |
-				PMD_SECT_VALID | PMD_SECT_NONE;
+	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | L_PMD_SECT_RDONLY |
+				L_PMD_SECT_VALID | L_PMD_SECT_NONE;
 	pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
 	return pmd;
 }
@@ -253,8 +259,13 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	BUG_ON(addr >= TASK_SIZE);
 
 	/* create a faulting entry if PROT_NONE protected */
-	if (pmd_val(pmd) & PMD_SECT_NONE)
-		pmd_val(pmd) &= ~PMD_SECT_VALID;
+	if (pmd_val(pmd) & L_PMD_SECT_NONE)
+		pmd_val(pmd) &= ~L_PMD_SECT_VALID;
+
+	if (pmd_write(pmd) && pmd_dirty(pmd))
+		pmd_val(pmd) &= ~PMD_SECT_AP2;
+	else
+		pmd_val(pmd) |= PMD_SECT_AP2;
 
 	*pmdp = __pmd(pmd_val(pmd) | PMD_SECT_nG);
 	flush_pmd_entry(pmdp);

arch/arm/include/asm/pgtable.h

@@ -214,18 +214,22 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
+#define pte_isset(pte, val)	((u32)(val) == (val) ? pte_val(pte) & (val) \
+						: !!(pte_val(pte) & (val)))
+#define pte_isclear(pte, val)	(!(pte_val(pte) & (val)))
+
 #define pte_none(pte)		(!pte_val(pte))
-#define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
-#define pte_valid(pte)		(pte_val(pte) & L_PTE_VALID)
+#define pte_present(pte)	(pte_isset((pte), L_PTE_PRESENT))
+#define pte_valid(pte)		(pte_isset((pte), L_PTE_VALID))
 #define pte_accessible(mm, pte)	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))
-#define pte_write(pte)		(!(pte_val(pte) & L_PTE_RDONLY))
-#define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
-#define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
-#define pte_exec(pte)		(!(pte_val(pte) & L_PTE_XN))
+#define pte_write(pte)		(pte_isclear((pte), L_PTE_RDONLY))
+#define pte_dirty(pte)		(pte_isset((pte), L_PTE_DIRTY))
+#define pte_young(pte)		(pte_isset((pte), L_PTE_YOUNG))
+#define pte_exec(pte)		(pte_isclear((pte), L_PTE_XN))
 #define pte_special(pte)	(0)
 
 #define pte_valid_user(pte)	\
-	(pte_valid(pte) && (pte_val(pte) & L_PTE_USER) && pte_young(pte))
+	(pte_valid(pte) && pte_isset((pte), L_PTE_USER) && pte_young(pte))
 
 #if __LINUX_ARM_ARCH__ < 6
 static inline void __sync_icache_dcache(pte_t pteval)

arch/arm/include/asm/pmu.h

@@ -42,6 +42,25 @@ struct arm_pmu_platdata {
 
 #ifdef CONFIG_HW_PERF_EVENTS
 
+/*
+ * The ARMv7 CPU PMU supports up to 32 event counters.
+ */
+#define ARMPMU_MAX_HWEVENTS		32
+
+#define HW_OP_UNSUPPORTED		0xFFFF
+#define C(_x)				PERF_COUNT_HW_CACHE_##_x
+#define CACHE_OP_UNSUPPORTED		0xFFFF
+
+#define PERF_MAP_ALL_UNSUPPORTED					\
+	[0 ... PERF_COUNT_HW_MAX - 1] = HW_OP_UNSUPPORTED
+
+#define PERF_CACHE_MAP_ALL_UNSUPPORTED					\
+[0 ... C(MAX) - 1] = {							\
+	[0 ... C(OP_MAX) - 1] = {					\
+		[0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED,	\
+	},								\
+}
+
 /* The events for a given PMU register set. */
 struct pmu_hw_events {
 	/*

arch/arm/include/asm/ptrace.h

@@ -84,6 +84,12 @@ static inline long regs_return_value(struct pt_regs *regs)
 
 #define instruction_pointer(regs)	(regs)->ARM_pc
 
+#ifdef CONFIG_THUMB2_KERNEL
+#define frame_pointer(regs) (regs)->ARM_r7
+#else
+#define frame_pointer(regs) (regs)->ARM_fp
+#endif
+
 static inline void instruction_pointer_set(struct pt_regs *regs,
 					   unsigned long val)
 {

arch/arm/include/asm/smp_scu.h

@@ -11,7 +11,7 @@
 
 static inline bool scu_a9_has_base(void)
 {
-	return read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9;
+	return read_cpuid_part() == ARM_CPU_PART_CORTEX_A9;
 }
 
 static inline unsigned long scu_a9_get_base(void)

arch/arm/include/asm/stacktrace.h

@@ -1,13 +1,28 @@
 #ifndef __ASM_STACKTRACE_H
 #define __ASM_STACKTRACE_H
 
+#include <asm/ptrace.h>
+
 struct stackframe {
+	/*
+	 * FP member should hold R7 when CONFIG_THUMB2_KERNEL is enabled
+	 * and R11 otherwise.
+	 */
 	unsigned long fp;
 	unsigned long sp;
 	unsigned long lr;
 	unsigned long pc;
 };
 
+static __always_inline
+void arm_get_current_stackframe(struct pt_regs *regs, struct stackframe *frame)
+{
+		frame->fp = frame_pointer(regs);
+		frame->sp = regs->ARM_sp;
+		frame->lr = regs->ARM_lr;
+		frame->pc = regs->ARM_pc;
+}
+
 extern int unwind_frame(struct stackframe *frame);
 extern void walk_stackframe(struct stackframe *frame,
 			    int (*fn)(struct stackframe *, void *), void *data);

arch/arm/include/asm/thread_info.h

@@ -14,9 +14,10 @@
 
 #include <linux/compiler.h>
 #include <asm/fpstate.h>
+#include <asm/page.h>
 
 #define THREAD_SIZE_ORDER	1
-#define THREAD_SIZE		8192
+#define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 #define THREAD_START_SP		(THREAD_SIZE - 8)
 
 #ifndef __ASSEMBLY__

arch/arm/include/asm/uaccess.h

@@ -107,6 +107,8 @@ static inline void set_fs(mm_segment_t fs)
 extern int __get_user_1(void *);
 extern int __get_user_2(void *);
 extern int __get_user_4(void *);
+extern int __get_user_lo8(void *);
+extern int __get_user_8(void *);
 
 #define __GUP_CLOBBER_1	"lr", "cc"
 #ifdef CONFIG_CPU_USE_DOMAINS
@@ -115,6 +117,8 @@ extern int __get_user_4(void *);
 #define __GUP_CLOBBER_2 "lr", "cc"
 #endif
 #define __GUP_CLOBBER_4	"lr", "cc"
+#define __GUP_CLOBBER_lo8 "lr", "cc"
+#define __GUP_CLOBBER_8	"lr", "cc"
 
 #define __get_user_x(__r2,__p,__e,__l,__s)				\
 	   __asm__ __volatile__ (					\
@@ -125,11 +129,19 @@ extern int __get_user_4(void *);
 		: "0" (__p), "r" (__l)					\
 		: __GUP_CLOBBER_##__s)
 
+/* narrowing a double-word get into a single 32bit word register: */
+#ifdef __ARMEB__
+#define __get_user_xb(__r2, __p, __e, __l, __s)				\
+	__get_user_x(__r2, __p, __e, __l, lo8)
+#else
+#define __get_user_xb __get_user_x
+#endif
+
 #define __get_user_check(x,p)							\
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register const typeof(*(p)) __user *__p asm("r0") = (p);\
-		register unsigned long __r2 asm("r2");			\
+		register typeof(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
@@ -142,6 +154,12 @@ extern int __get_user_4(void *);
 		case 4:							\
 			__get_user_x(__r2, __p, __e, __l, 4);		\
 			break;						\
+		case 8:							\
+			if (sizeof((x)) < 8)				\
+				__get_user_xb(__r2, __p, __e, __l, 4);	\
+			else						\
+				__get_user_x(__r2, __p, __e, __l, 8);	\
+			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
 		x = (typeof(*(p))) __r2;				\
@@ -224,7 +242,7 @@ static inline void set_fs(mm_segment_t fs)
 #define access_ok(type,addr,size)	(__range_ok(addr,size) == 0)
 
 #define user_addr_max() \
-	(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+	(segment_eq(get_fs(), KERNEL_DS) ? ~0UL : get_fs())
 
 /*
  * The "__xxx" versions of the user access functions do not verify the

arch/arm/include/asm/unistd.h

@@ -15,7 +15,17 @@
 
 #include <uapi/asm/unistd.h>
 
+/*
+ * This may need to be greater than __NR_last_syscall+1 in order to
+ * account for the padding in the syscall table
+ */
 #define __NR_syscalls  (384)
+
+/*
+ * *NOTE*: This is a ghost syscall private to the kernel.  Only the
+ * __kuser_cmpxchg code in entry-armv.S should be aware of its
+ * existence.  Don't ever use this from user code.
+ */
 #define __ARM_NR_cmpxchg		(__ARM_NR_BASE+0x00fff0)
 
 #define __ARCH_WANT_STAT64

arch/arm/include/uapi/asm/unistd.h

@@ -410,11 +410,6 @@
 #define __NR_sched_getattr		(__NR_SYSCALL_BASE+381)
 #define __NR_renameat2			(__NR_SYSCALL_BASE+382)
 
-/*
- * This may need to be greater than __NR_last_syscall+1 in order to
- * account for the padding in the syscall table
- */
-
 /*
  * The following SWIs are ARM private.
  */
@@ -425,12 +420,6 @@
 #define __ARM_NR_usr32			(__ARM_NR_BASE+4)
 #define __ARM_NR_set_tls		(__ARM_NR_BASE+5)
 
-/*
- * *NOTE*: This is a ghost syscall private to the kernel.  Only the
- * __kuser_cmpxchg code in entry-armv.S should be aware of its
- * existence.  Don't ever use this from user code.
- */
-
 /*
  * The following syscalls are obsolete and no longer available for EABI.
  */

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

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

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

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 */
 
 /*

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)

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)
 
 /*

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"

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)
 

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

arch/arm/kernel/iwmmxt.S

@@ -100,7 +100,7 @@ ENTRY(iwmmxt_task_enable)
 	get_thread_info r10
 #endif
 4:	dec_preempt_count r10, r3
-	mov	pc, r9				@ normal exit from exception
+	ret	r9				@ normal exit from exception
 
 concan_save:
 
@@ -144,7 +144,7 @@ concan_dump:
 	wstrd	wR15, [r1, #MMX_WR15]
 
 2:	teq	r0, #0				@ anything to load?
-	moveq	pc, lr				@ if not, return
+	reteq	lr				@ if not, return
 
 concan_load:
 
@@ -177,10 +177,10 @@ concan_load:
 	@ clear CUP/MUP (only if r1 != 0)
 	teq	r1, #0
 	mov 	r2, #0
-	moveq	pc, lr
+	reteq	lr
 
 	tmcr	wCon, r2
-	mov	pc, lr
+	ret	lr
 
 /*
  * Back up Concan regs to save area and disable access to them
@@ -266,7 +266,7 @@ 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
@@ -302,7 +302,7 @@ 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
@@ -324,7 +324,7 @@ 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)
@@ -351,7 +351,7 @@ 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:

arch/arm/kernel/perf_event.c

@@ -560,11 +560,16 @@ user_backtrace(struct frame_tail __user *tail,
 	       struct perf_callchain_entry *entry)
 {
 	struct frame_tail buftail;
+	unsigned long err;
 
-	/* Also check accessibility of one struct frame_tail beyond */
 	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
 		return NULL;
-	if (__copy_from_user_inatomic(&buftail, tail, sizeof(buftail)))
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
 		return NULL;
 
 	perf_callchain_store(entry, buftail.lr);
@@ -590,6 +595,10 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	}
 
 	perf_callchain_store(entry, regs->ARM_pc);
+
+	if (!current->mm)
+		return;
+
 	tail = (struct frame_tail __user *)regs->ARM_fp - 1;
 
 	while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
@@ -621,10 +630,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		return;
 	}
 
-	fr.fp = regs->ARM_fp;
-	fr.sp = regs->ARM_sp;
-	fr.lr = regs->ARM_lr;
-	fr.pc = regs->ARM_pc;
+	arm_get_current_stackframe(regs, &fr);
 	walk_stackframe(&fr, callchain_trace, entry);
 }
 

arch/arm/kernel/perf_event_cpu.c

@@ -233,14 +233,17 @@ static struct of_device_id cpu_pmu_of_device_ids[] = {
 	{.compatible = "arm,cortex-a7-pmu",	.data = armv7_a7_pmu_init},
 	{.compatible = "arm,cortex-a5-pmu",	.data = armv7_a5_pmu_init},
 	{.compatible = "arm,arm11mpcore-pmu",	.data = armv6mpcore_pmu_init},
-	{.compatible = "arm,arm1176-pmu",	.data = armv6pmu_init},
-	{.compatible = "arm,arm1136-pmu",	.data = armv6pmu_init},
+	{.compatible = "arm,arm1176-pmu",	.data = armv6_1176_pmu_init},
+	{.compatible = "arm,arm1136-pmu",	.data = armv6_1136_pmu_init},
 	{.compatible = "qcom,krait-pmu",	.data = krait_pmu_init},
 	{},
 };
 
 static struct platform_device_id cpu_pmu_plat_device_ids[] = {
 	{.name = "arm-pmu"},
+	{.name = "armv6-pmu"},
+	{.name = "armv7-pmu"},
+	{.name = "xscale-pmu"},
 	{},
 };
 
@@ -250,40 +253,43 @@ static struct platform_device_id cpu_pmu_plat_device_ids[] = {
 static int probe_current_pmu(struct arm_pmu *pmu)
 {
 	int cpu = get_cpu();
-	unsigned long implementor = read_cpuid_implementor();
-	unsigned long part_number = read_cpuid_part_number();
 	int ret = -ENODEV;
 
 	pr_info("probing PMU on CPU %d\n", cpu);
 
+	switch (read_cpuid_part()) {
 	/* ARM Ltd CPUs. */
-	if (implementor == ARM_CPU_IMP_ARM) {
-		switch (part_number) {
-		case ARM_CPU_PART_ARM1136:
-		case ARM_CPU_PART_ARM1156:
-		case ARM_CPU_PART_ARM1176:
-			ret = armv6pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_ARM11MPCORE:
-			ret = armv6mpcore_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A8:
-			ret = armv7_a8_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A9:
-			ret = armv7_a9_pmu_init(pmu);
-			break;
-		}
-	/* Intel CPUs [xscale]. */
-	} else if (implementor == ARM_CPU_IMP_INTEL) {
-		switch (xscale_cpu_arch_version()) {
-		case ARM_CPU_XSCALE_ARCH_V1:
-			ret = xscale1pmu_init(pmu);
-			break;
-		case ARM_CPU_XSCALE_ARCH_V2:
-			ret = xscale2pmu_init(pmu);
-			break;
+	case ARM_CPU_PART_ARM1136:
+		ret = armv6_1136_pmu_init(pmu);
+		break;
+	case ARM_CPU_PART_ARM1156:
+		ret = armv6_1156_pmu_init(pmu);
+		break;
+	case ARM_CPU_PART_ARM1176:
+		ret = armv6_1176_pmu_init(pmu);
+		break;
+	case ARM_CPU_PART_ARM11MPCORE:
+		ret = armv6mpcore_pmu_init(pmu);
+		break;
+	case ARM_CPU_PART_CORTEX_A8:
+		ret = armv7_a8_pmu_init(pmu);
+		break;
+	case ARM_CPU_PART_CORTEX_A9:
+		ret = armv7_a9_pmu_init(pmu);
+		break;
+
+	default:
+		if (read_cpuid_implementor() == ARM_CPU_IMP_INTEL) {
+			switch (xscale_cpu_arch_version()) {
+			case ARM_CPU_XSCALE_ARCH_V1:
+				ret = xscale1pmu_init(pmu);
+				break;
+			case ARM_CPU_XSCALE_ARCH_V2:
+				ret = xscale2pmu_init(pmu);
+				break;
+			}
 		}
+		break;
 	}
 
 	put_cpu();

arch/arm/kernel/perf_event_v6.c

@@ -65,13 +65,11 @@ enum armv6_counters {
  * accesses/misses in hardware.
  */
 static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV6_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV6_PERFCTR_INSTR_EXEC,
-	[PERF_COUNT_HW_CACHE_REFERENCES]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_CACHE_MISSES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV6_PERFCTR_BR_EXEC,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV6_PERFCTR_BR_MISPREDICT,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV6_PERFCTR_IBUF_STALL,
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV6_PERFCTR_LSU_FULL_STALL,
 };
@@ -79,116 +77,31 @@ static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
 static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					  [PERF_COUNT_HW_CACHE_OP_MAX]
 					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		/*
-		 * The performance counters don't differentiate between read
-		 * and write accesses/misses so this isn't strictly correct,
-		 * but it's the best we can do. Writes and reads get
-		 * combined.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ICACHE_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		/*
-		 * The ARM performance counters can count micro DTLB misses,
-		 * micro ITLB misses and main TLB misses. There isn't an event
-		 * for TLB misses, so use the micro misses here and if users
-		 * want the main TLB misses they can use a raw counter.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	/*
+	 * The performance counters don't differentiate between read and write
+	 * accesses/misses so this isn't strictly correct, but it's the best we
+	 * can do. Writes and reads get combined.
+	 */
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6_PERFCTR_ICACHE_MISS,
+
+	/*
+	 * The ARM performance counters can count micro DTLB misses, micro ITLB
+	 * misses and main TLB misses. There isn't an event for TLB misses, so
+	 * use the micro misses here and if users want the main TLB misses they
+	 * can use a raw counter.
+	 */
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
 };
 
 enum armv6mpcore_perf_types {
@@ -220,13 +133,11 @@ enum armv6mpcore_perf_types {
  * accesses/misses in hardware.
  */
 static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV6MPCORE_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV6MPCORE_PERFCTR_INSTR_EXEC,
-	[PERF_COUNT_HW_CACHE_REFERENCES]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_CACHE_MISSES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV6MPCORE_PERFCTR_BR_EXEC,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV6MPCORE_PERFCTR_IBUF_STALL,
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV6MPCORE_PERFCTR_LSU_FULL_STALL,
 };
@@ -234,114 +145,26 @@ static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
 static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					[PERF_COUNT_HW_CACHE_OP_MAX]
 					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  =
-				ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
-			[C(RESULT_MISS)]    =
-				ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  =
-				ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
-			[C(RESULT_MISS)]    =
-				ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		/*
-		 * The ARM performance counters can count micro DTLB misses,
-		 * micro ITLB misses and main TLB misses. There isn't an event
-		 * for TLB misses, so use the micro misses here and if users
-		 * want the main TLB misses they can use a raw counter.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+
+	/*
+	 * The ARM performance counters can count micro DTLB misses, micro ITLB
+	 * misses and main TLB misses. There isn't an event for TLB misses, so
+	 * use the micro misses here and if users want the main TLB misses they
+	 * can use a raw counter.
+	 */
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DTLB_MISS,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DTLB_MISS,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_ITLB_MISS,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_ITLB_MISS,
 };
 
 static inline unsigned long
@@ -653,9 +476,8 @@ static int armv6_map_event(struct perf_event *event)
 				&armv6_perf_cache_map, 0xFF);
 }
 
-static int armv6pmu_init(struct arm_pmu *cpu_pmu)
+static void armv6pmu_init(struct arm_pmu *cpu_pmu)
 {
-	cpu_pmu->name		= "v6";
 	cpu_pmu->handle_irq	= armv6pmu_handle_irq;
 	cpu_pmu->enable		= armv6pmu_enable_event;
 	cpu_pmu->disable	= armv6pmu_disable_event;
@@ -667,7 +489,26 @@ static int armv6pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->map_event	= armv6_map_event;
 	cpu_pmu->num_events	= 3;
 	cpu_pmu->max_period	= (1LLU << 32) - 1;
+}
+
+static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv6pmu_init(cpu_pmu);
+	cpu_pmu->name		= "armv6_1136";
+	return 0;
+}
 
+static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv6pmu_init(cpu_pmu);
+	cpu_pmu->name		= "armv6_1156";
+	return 0;
+}
+
+static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv6pmu_init(cpu_pmu);
+	cpu_pmu->name		= "armv6_1176";
 	return 0;
 }
 
@@ -687,7 +528,7 @@ static int armv6mpcore_map_event(struct perf_event *event)
 
 static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	cpu_pmu->name		= "v6mpcore";
+	cpu_pmu->name		= "armv6_11mpcore";
 	cpu_pmu->handle_irq	= armv6pmu_handle_irq;
 	cpu_pmu->enable		= armv6pmu_enable_event;
 	cpu_pmu->disable	= armv6mpcore_pmu_disable_event;
@@ -703,7 +544,17 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
 	return 0;
 }
 #else
-static int armv6pmu_init(struct arm_pmu *cpu_pmu)
+static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
+
+static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
+
+static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	return -ENODEV;
 }

arch/arm/kernel/perf_event_v7.c

@@ -148,137 +148,62 @@ enum krait_perf_types {
  * accesses/misses in hardware.
  */
 static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV7_A8_PERFCTR_STALL_ISIDE,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					  [PERF_COUNT_HW_CACHE_OP_MAX]
 					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		/*
-		 * The performance counters don't differentiate between read
-		 * and write accesses/misses so this isn't strictly correct,
-		 * but it's the best we can do. Writes and reads get
-		 * combined.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L2_CACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_A8_PERFCTR_L2_CACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L2_CACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_A8_PERFCTR_L2_CACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	/*
+	 * The performance counters don't differentiate between read and write
+	 * accesses/misses so this isn't strictly correct, but it's the best we
+	 * can do. Writes and reads get combined.
+	 */
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+
+	[C(LL)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L2_CACHE_ACCESS,
+	[C(LL)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_A8_PERFCTR_L2_CACHE_REFILL,
+	[C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L2_CACHE_ACCESS,
+	[C(LL)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_A8_PERFCTR_L2_CACHE_REFILL,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Cortex-A9 HW events mapping
  */
 static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_A9_PERFCTR_INSTR_CORE_RENAME,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV7_A9_PERFCTR_STALL_ICACHE,
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV7_A9_PERFCTR_STALL_DISPATCH,
 };
@@ -286,238 +211,83 @@ static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
 static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					  [PERF_COUNT_HW_CACHE_OP_MAX]
 					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		/*
-		 * The performance counters don't differentiate between read
-		 * and write accesses/misses so this isn't strictly correct,
-		 * but it's the best we can do. Writes and reads get
-		 * combined.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	/*
+	 * The performance counters don't differentiate between read and write
+	 * accesses/misses so this isn't strictly correct, but it's the best we
+	 * can do. Writes and reads get combined.
+	 */
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Cortex-A5 HW events mapping
  */
 static const unsigned armv7_a5_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a5_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					[PERF_COUNT_HW_CACHE_OP_MAX]
 					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL,
-			[C(RESULT_MISS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		/*
-		 * The prefetch counters don't differentiate between the I
-		 * side and the D side.
-		 */
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL,
-			[C(RESULT_MISS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_PREFETCH)][C(RESULT_ACCESS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL,
+	[C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+	/*
+	 * The prefetch counters don't differentiate between the I side and the
+	 * D side.
+	 */
+	[C(L1I)][C(OP_PREFETCH)][C(RESULT_ACCESS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL,
+	[C(L1I)][C(OP_PREFETCH)][C(RESULT_MISS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Cortex-A15 HW events mapping
  */
 static const unsigned armv7_a15_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
@@ -525,123 +295,48 @@ static const unsigned armv7_a15_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_A15_PERFCTR_PC_WRITE_SPEC,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					[PERF_COUNT_HW_CACHE_OP_MAX]
 					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ,
-			[C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE,
-			[C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		/*
-		 * Not all performance counters differentiate between read
-		 * and write accesses/misses so we're not always strictly
-		 * correct, but it's the best we can do. Writes and reads get
-		 * combined in these cases.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ,
-			[C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE,
-			[C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE,
+
+	/*
+	 * Not all performance counters differentiate between read and write
+	 * accesses/misses so we're not always strictly correct, but it's the
+	 * best we can do. Writes and reads get combined in these cases.
+	 */
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+
+	[C(LL)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ,
+	[C(LL)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ,
+	[C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE,
+	[C(LL)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Cortex-A7 HW events mapping
  */
 static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
@@ -649,123 +344,48 @@ static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					[PERF_COUNT_HW_CACHE_OP_MAX]
 					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		/*
-		 * The performance counters don't differentiate between read
-		 * and write accesses/misses so this isn't strictly correct,
-		 * but it's the best we can do. Writes and reads get
-		 * combined.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	/*
+	 * The performance counters don't differentiate between read and write
+	 * accesses/misses so this isn't strictly correct, but it's the best we
+	 * can do. Writes and reads get combined.
+	 */
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+
+	[C(LL)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+	[C(LL)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+	[C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+	[C(LL)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Cortex-A12 HW events mapping
  */
 static const unsigned armv7_a12_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
@@ -773,138 +393,60 @@ static const unsigned armv7_a12_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_A12_PERFCTR_PC_WRITE_SPEC,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a12_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					[PERF_COUNT_HW_CACHE_OP_MAX]
 					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		/*
-		 * Not all performance counters differentiate between read
-		 * and write accesses/misses so we're not always strictly
-		 * correct, but it's the best we can do. Writes and reads get
-		 * combined in these cases.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_A12_PERFCTR_PF_TLB_REFILL,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+
+	/*
+	 * Not all performance counters differentiate between read and write
+	 * accesses/misses so we're not always strictly correct, but it's the
+	 * best we can do. Writes and reads get combined in these cases.
+	 */
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+
+	[C(LL)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ,
+	[C(LL)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+	[C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE,
+	[C(LL)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_PREFETCH)][C(RESULT_MISS)]	= ARMV7_A12_PERFCTR_PF_TLB_REFILL,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Krait HW events mapping
  */
 static const unsigned krait_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV7_PERFCTR_INSTR_EXECUTED,
-	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
 	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
 };
 
 static const unsigned krait_perf_map_no_branch[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV7_PERFCTR_INSTR_EXECUTED,
-	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
 };
@@ -912,110 +454,31 @@ static const unsigned krait_perf_map_no_branch[PERF_COUNT_HW_MAX] = {
 static const unsigned krait_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					  [PERF_COUNT_HW_CACHE_OP_MAX]
 					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		/*
-		 * The performance counters don't differentiate between read
-		 * and write accesses/misses so this isn't strictly correct,
-		 * but it's the best we can do. Writes and reads get
-		 * combined.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= KRAIT_PERFCTR_L1_ICACHE_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	/*
+	 * The performance counters don't differentiate between read and write
+	 * accesses/misses so this isn't strictly correct, but it's the best we
+	 * can do. Writes and reads get combined.
+	 */
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= KRAIT_PERFCTR_L1_ICACHE_MISS,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
@@ -1545,7 +1008,7 @@ static u32 armv7_read_num_pmnc_events(void)
 static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A8";
+	cpu_pmu->name		= "armv7_cortex_a8";
 	cpu_pmu->map_event	= armv7_a8_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1554,7 +1017,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A9";
+	cpu_pmu->name		= "armv7_cortex_a9";
 	cpu_pmu->map_event	= armv7_a9_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1563,7 +1026,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A5";
+	cpu_pmu->name		= "armv7_cortex_a5";
 	cpu_pmu->map_event	= armv7_a5_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1572,7 +1035,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A15";
+	cpu_pmu->name		= "armv7_cortex_a15";
 	cpu_pmu->map_event	= armv7_a15_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
@@ -1582,7 +1045,7 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A7";
+	cpu_pmu->name		= "armv7_cortex_a7";
 	cpu_pmu->map_event	= armv7_a7_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
@@ -1592,7 +1055,7 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A12";
+	cpu_pmu->name		= "armv7_cortex_a12";
 	cpu_pmu->map_event	= armv7_a12_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
@@ -1602,7 +1065,7 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7_a12_pmu_init(cpu_pmu);
-	cpu_pmu->name = "ARMv7 Cortex-A17";
+	cpu_pmu->name = "armv7_cortex_a17";
 	return 0;
 }
 
@@ -1823,6 +1286,7 @@ static void krait_pmu_disable_event(struct perf_event *event)
 	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	/* Disable counter and interrupt */
@@ -1848,6 +1312,7 @@ static void krait_pmu_enable_event(struct perf_event *event)
 	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	/*
@@ -1981,7 +1446,7 @@ static void krait_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
 static int krait_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Krait";
+	cpu_pmu->name		= "armv7_krait";
 	/* Some early versions of Krait don't support PC write events */
 	if (of_property_read_bool(cpu_pmu->plat_device->dev.of_node,
 				  "qcom,no-pc-write"))

arch/arm/kernel/perf_event_xscale.c

@@ -48,118 +48,31 @@ enum xscale_counters {
 };
 
 static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= XSCALE_PERFCTR_CCNT,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= XSCALE_PERFCTR_INSTRUCTION,
-	[PERF_COUNT_HW_CACHE_REFERENCES]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_CACHE_MISSES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= XSCALE_PERFCTR_BRANCH,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= XSCALE_PERFCTR_BRANCH_MISS,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= XSCALE_PERFCTR_ICACHE_NO_DELIVER,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					   [PERF_COUNT_HW_CACHE_OP_MAX]
 					   [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= XSCALE_PERFCTR_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= XSCALE_PERFCTR_DCACHE_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= XSCALE_PERFCTR_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= XSCALE_PERFCTR_DCACHE_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= XSCALE_PERFCTR_ICACHE_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= XSCALE_PERFCTR_DTLB_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= XSCALE_PERFCTR_DTLB_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= XSCALE_PERFCTR_ITLB_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= XSCALE_PERFCTR_ITLB_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= XSCALE_PERFCTR_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= XSCALE_PERFCTR_DCACHE_MISS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= XSCALE_PERFCTR_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= XSCALE_PERFCTR_DCACHE_MISS,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= XSCALE_PERFCTR_ICACHE_MISS,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= XSCALE_PERFCTR_DTLB_MISS,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= XSCALE_PERFCTR_DTLB_MISS,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= XSCALE_PERFCTR_ITLB_MISS,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= XSCALE_PERFCTR_ITLB_MISS,
 };
 
 #define	XSCALE_PMU_ENABLE	0x001
@@ -442,7 +355,7 @@ static int xscale_map_event(struct perf_event *event)
 
 static int xscale1pmu_init(struct arm_pmu *cpu_pmu)
 {
-	cpu_pmu->name		= "xscale1";
+	cpu_pmu->name		= "armv5_xscale1";
 	cpu_pmu->handle_irq	= xscale1pmu_handle_irq;
 	cpu_pmu->enable		= xscale1pmu_enable_event;
 	cpu_pmu->disable	= xscale1pmu_disable_event;
@@ -812,7 +725,7 @@ static inline void xscale2pmu_write_counter(struct perf_event *event, u32 val)
 
 static int xscale2pmu_init(struct arm_pmu *cpu_pmu)
 {
-	cpu_pmu->name		= "xscale2";
+	cpu_pmu->name		= "armv5_xscale2";
 	cpu_pmu->handle_irq	= xscale2pmu_handle_irq;
 	cpu_pmu->enable		= xscale2pmu_enable_event;
 	cpu_pmu->disable	= xscale2pmu_disable_event;

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

arch/arm/kernel/setup.c

@@ -393,19 +393,34 @@ static void __init cpuid_init_hwcaps(void)
 		elf_hwcap |= HWCAP_LPAE;
 }
 
-static void __init feat_v6_fixup(void)
+static void __init elf_hwcap_fixup(void)
 {
-	int id = read_cpuid_id();
-
-	if ((id & 0xff0f0000) != 0x41070000)
-		return;
+	unsigned id = read_cpuid_id();
+	unsigned sync_prim;
 
 	/*
 	 * HWCAP_TLS is available only on 1136 r1p0 and later,
 	 * see also kuser_get_tls_init.
 	 */
-	if ((((id >> 4) & 0xfff) == 0xb36) && (((id >> 20) & 3) == 0))
+	if (read_cpuid_part() == ARM_CPU_PART_ARM1136 &&
+	    ((id >> 20) & 3) == 0) {
 		elf_hwcap &= ~HWCAP_TLS;
+		return;
+	}
+
+	/* Verify if CPUID scheme is implemented */
+	if ((id & 0x000f0000) != 0x000f0000)
+		return;
+
+	/*
+	 * If the CPU supports LDREX/STREX and LDREXB/STREXB,
+	 * avoid advertising SWP; it may not be atomic with
+	 * multiprocessing cores.
+	 */
+	sync_prim = ((read_cpuid_ext(CPUID_EXT_ISAR3) >> 8) & 0xf0) |
+		    ((read_cpuid_ext(CPUID_EXT_ISAR4) >> 20) & 0x0f);
+	if (sync_prim >= 0x13)
+		elf_hwcap &= ~HWCAP_SWP;
 }
 
 /*
@@ -609,7 +624,7 @@ static void __init setup_processor(void)
 #endif
 	erratum_a15_798181_init();
 
-	feat_v6_fixup();
+	elf_hwcap_fixup();
 
 	cacheid_init();
 	cpu_init();

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:

arch/arm/kernel/smp_scu.c

@@ -17,6 +17,8 @@
 #include <asm/cputype.h>
 
 #define SCU_CTRL		0x00
+#define SCU_ENABLE		(1 << 0)
+#define SCU_STANDBY_ENABLE	(1 << 5)
 #define SCU_CONFIG		0x04
 #define SCU_CPU_STATUS		0x08
 #define SCU_INVALIDATE		0x0c
@@ -50,10 +52,16 @@ void scu_enable(void __iomem *scu_base)
 
 	scu_ctrl = readl_relaxed(scu_base + SCU_CTRL);
 	/* already enabled? */
-	if (scu_ctrl & 1)
+	if (scu_ctrl & SCU_ENABLE)
 		return;
 
-	scu_ctrl |= 1;
+	scu_ctrl |= SCU_ENABLE;
+
+	/* Cortex-A9 earlier than r2p0 has no standby bit in SCU */
+	if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090 &&
+	    (read_cpuid_id() & 0x00f0000f) >= 0x00200000)
+		scu_ctrl |= SCU_STANDBY_ENABLE;
+
 	writel_relaxed(scu_ctrl, scu_base + SCU_CTRL);
 
 	/*

arch/arm/kernel/smp_tlb.c

@@ -92,15 +92,19 @@ void erratum_a15_798181_init(void)
 	unsigned int midr = read_cpuid_id();
 	unsigned int revidr = read_cpuid(CPUID_REVIDR);
 
-	/* Cortex-A15 r0p0..r3p2 w/o ECO fix affected */
-	if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2 ||
-	    (revidr & 0x210) == 0x210) {
-		return;
-	}
-	if (revidr & 0x10)
-		erratum_a15_798181_handler = erratum_a15_798181_partial;
-	else
+	/* Brahma-B15 r0p0..r0p2 affected
+	 * Cortex-A15 r0p0..r3p2 w/o ECO fix affected */
+	if ((midr & 0xff0ffff0) == 0x420f00f0 && midr <= 0x420f00f2)
 		erratum_a15_798181_handler = erratum_a15_798181_broadcast;
+	else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr <= 0x413fc0f2 &&
+		 (revidr & 0x210) != 0x210) {
+		if (revidr & 0x10)
+			erratum_a15_798181_handler =
+				erratum_a15_798181_partial;
+		else
+			erratum_a15_798181_handler =
+				erratum_a15_798181_broadcast;
+	}
 }
 #endif
 

arch/arm/kernel/swp_emulate.c

@@ -27,6 +27,7 @@
 #include <linux/perf_event.h>
 
 #include <asm/opcodes.h>
+#include <asm/system_info.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
 
@@ -266,6 +267,9 @@ static struct undef_hook swp_hook = {
  */
 static int __init swp_emulation_init(void)
 {
+	if (cpu_architecture() < CPU_ARCH_ARMv7)
+		return 0;
+
 #ifdef CONFIG_PROC_FS
 	if (!proc_create("cpu/swp_emulation", S_IRUGO, NULL, &proc_status_fops))
 		return -ENOMEM;

arch/arm/kernel/time.c

@@ -50,10 +50,7 @@ unsigned long profile_pc(struct pt_regs *regs)
 	if (!in_lock_functions(regs->ARM_pc))
 		return regs->ARM_pc;
 
-	frame.fp = regs->ARM_fp;
-	frame.sp = regs->ARM_sp;
-	frame.lr = regs->ARM_lr;
-	frame.pc = regs->ARM_pc;
+	arm_get_current_stackframe(regs, &frame);
 	do {
 		int ret = unwind_frame(&frame);
 		if (ret < 0)

arch/arm/kernel/traps.c

@@ -31,11 +31,13 @@
 #include <asm/exception.h>
 #include <asm/unistd.h>
 #include <asm/traps.h>
+#include <asm/ptrace.h>
 #include <asm/unwind.h>
 #include <asm/tls.h>
 #include <asm/system_misc.h>
 #include <asm/opcodes.h>
 
+
 static const char *handler[]= {
 	"prefetch abort",
 	"data abort",
@@ -184,7 +186,7 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 		tsk = current;
 
 	if (regs) {
-		fp = regs->ARM_fp;
+		fp = frame_pointer(regs);
 		mode = processor_mode(regs);
 	} else if (tsk != current) {
 		fp = thread_saved_fp(tsk);
@@ -719,7 +721,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 		dump_instr("", regs);
 		if (user_mode(regs)) {
 			__show_regs(regs);
-			c_backtrace(regs->ARM_fp, processor_mode(regs));
+			c_backtrace(frame_pointer(regs), processor_mode(regs));
 		}
 	}
 #endif

arch/arm/kernel/unwind.c

@@ -479,12 +479,10 @@ void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 		tsk = current;
 
 	if (regs) {
-		frame.fp = regs->ARM_fp;
-		frame.sp = regs->ARM_sp;
-		frame.lr = regs->ARM_lr;
+		arm_get_current_stackframe(regs, &frame);
 		/* PC might be corrupted, use LR in that case. */
-		frame.pc = kernel_text_address(regs->ARM_pc)
-			 ? regs->ARM_pc : regs->ARM_lr;
+		if (!kernel_text_address(regs->ARM_pc))
+			frame.pc = regs->ARM_lr;
 	} else if (tsk == current) {
 		frame.fp = (unsigned long)__builtin_frame_address(0);
 		frame.sp = current_sp;

arch/arm/kernel/vmlinux.lds.S

@@ -318,7 +318,6 @@ SECTIONS
 	_end = .;
 
 	STABS_DEBUG
-	.comment 0 : { *(.comment) }
 }
 
 /*

arch/arm/kvm/guest.c

@@ -274,13 +274,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 int __attribute_const__ kvm_target_cpu(void)
 {
-	unsigned long implementor = read_cpuid_implementor();
-	unsigned long part_number = read_cpuid_part_number();
-
-	if (implementor != ARM_CPU_IMP_ARM)
-		return -EINVAL;
-
-	switch (part_number) {
+	switch (read_cpuid_part()) {
 	case ARM_CPU_PART_CORTEX_A7:
 		return KVM_ARM_TARGET_CORTEX_A7;
 	case ARM_CPU_PART_CORTEX_A15:

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

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)

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)

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...

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

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

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)

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}

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

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)

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)

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
 

arch/arm/lib/getuser.S

@@ -18,7 +18,7 @@
  * Inputs:	r0 contains the address
  *		r1 contains the address limit, which must be preserved
  * Outputs:	r0 is the error code
- *		r2 contains the zero-extended value
+ *		r2, r3 contains the zero-extended value
  *		lr corrupted
  *
  * No other registers must be altered.  (see <asm/uaccess.h>
@@ -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)
@@ -56,25 +56,60 @@ 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)
 
+ENTRY(__get_user_8)
+	check_uaccess r0, 8, r1, r2, __get_user_bad
+#ifdef CONFIG_THUMB2_KERNEL
+5: TUSER(ldr)	r2, [r0]
+6: TUSER(ldr)	r3, [r0, #4]
+#else
+5: TUSER(ldr)	r2, [r0], #4
+6: TUSER(ldr)	r3, [r0]
+#endif
+	mov	r0, #0
+	ret	lr
+ENDPROC(__get_user_8)
+
+#ifdef __ARMEB__
+ENTRY(__get_user_lo8)
+	check_uaccess r0, 8, r1, r2, __get_user_bad
+#ifdef CONFIG_CPU_USE_DOMAINS
+	add	r0, r0, #4
+7:	ldrt	r2, [r0]
+#else
+7:	ldr	r2, [r0, #4]
+#endif
+	mov	r0, #0
+	ret	lr
+ENDPROC(__get_user_lo8)
+#endif
+
+__get_user_bad8:
+	mov	r3, #0
 __get_user_bad:
 	mov	r2, #0
 	mov	r0, #-EFAULT
-	mov	pc, lr
+	ret	lr
 ENDPROC(__get_user_bad)
+ENDPROC(__get_user_bad8)
 
 .pushsection __ex_table, "a"
 	.long	1b, __get_user_bad
 	.long	2b, __get_user_bad
 	.long	3b, __get_user_bad
 	.long	4b, __get_user_bad
+	.long	5b, __get_user_bad8
+	.long	6b, __get_user_bad8
+#ifdef __ARMEB__
+	.long   7b, __get_user_bad
+#endif
 .popsection

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
 

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)

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
 

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
 

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
 

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)

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
 

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)

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)

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)

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)

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?

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)

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)

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"

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)

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)

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)
 

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:

arch/arm/mach-ebsa110/include/mach/memory.h

@@ -16,11 +16,6 @@
 #ifndef __ASM_ARCH_MEMORY_H
 #define __ASM_ARCH_MEMORY_H
 
-/*
- * Physical DRAM offset.
- */
-#define PLAT_PHYS_OFFSET	UL(0x00000000)
-
 /*
  * Cache flushing area - SRAM
  */

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

arch/arm/mach-ep93xx/include/mach/memory.h

@@ -1,22 +0,0 @@
-/*
- * arch/arm/mach-ep93xx/include/mach/memory.h
- */
-
-#ifndef __ASM_ARCH_MEMORY_H
-#define __ASM_ARCH_MEMORY_H
-
-#if defined(CONFIG_EP93XX_SDCE3_SYNC_PHYS_OFFSET)
-#define PLAT_PHYS_OFFSET		UL(0x00000000)
-#elif defined(CONFIG_EP93XX_SDCE0_PHYS_OFFSET)
-#define PLAT_PHYS_OFFSET		UL(0xc0000000)
-#elif defined(CONFIG_EP93XX_SDCE1_PHYS_OFFSET)
-#define PLAT_PHYS_OFFSET		UL(0xd0000000)
-#elif defined(CONFIG_EP93XX_SDCE2_PHYS_OFFSET)
-#define PLAT_PHYS_OFFSET		UL(0xe0000000)
-#elif defined(CONFIG_EP93XX_SDCE3_ASYNC_PHYS_OFFSET)
-#define PLAT_PHYS_OFFSET		UL(0xf0000000)
-#else
-#error "Kconfig bug: No EP93xx PHYS_OFFSET set"
-#endif
-
-#endif

arch/arm/mach-exynos/Kconfig

@@ -119,6 +119,7 @@ config EXYNOS5420_MCPM
 	bool "Exynos5420 Multi-Cluster PM support"
 	depends on MCPM && SOC_EXYNOS5420
 	select ARM_CCI
+	select ARM_CPU_SUSPEND
 	help
 	  This is needed to provide CPU and cluster power management
 	  on Exynos5420 implementing big.LITTLE.

arch/arm/mach-exynos/mcpm-exynos.c

@@ -196,7 +196,7 @@ static void exynos_power_down(void)
 	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
 		arch_spin_unlock(&exynos_mcpm_lock);
 
-		if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A15) {
+		if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A15) {
 			/*
 			 * On the Cortex-A15 we need to disable
 			 * L2 prefetching before flushing the cache.
@@ -289,6 +289,19 @@ static void __naked exynos_pm_power_up_setup(unsigned int affinity_level)
 	"b	cci_enable_port_for_self");
 }
 
+static void __init exynos_cache_off(void)
+{
+	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A15) {
+		/* disable L2 prefetching on the Cortex-A15 */
+		asm volatile(
+		"mcr	p15, 1, %0, c15, c0, 3\n\t"
+		"isb\n\t"
+		"dsb"
+		: : "r" (0x400));
+	}
+	exynos_v7_exit_coherency_flush(all);
+}
+
 static const struct of_device_id exynos_dt_mcpm_match[] = {
 	{ .compatible = "samsung,exynos5420" },
 	{ .compatible = "samsung,exynos5800" },
@@ -332,6 +345,8 @@ static int __init exynos_mcpm_init(void)
 	ret = mcpm_platform_register(&exynos_power_ops);
 	if (!ret)
 		ret = mcpm_sync_init(exynos_pm_power_up_setup);
+	if (!ret)
+		ret = mcpm_loopback(exynos_cache_off); /* turn on the CCI */
 	if (ret) {
 		iounmap(ns_sram_base_addr);
 		return ret;

arch/arm/mach-exynos/platsmp.c

@@ -190,7 +190,7 @@ static void __init exynos_smp_init_cpus(void)
 	void __iomem *scu_base = scu_base_addr();
 	unsigned int i, ncores;
 
-	if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
+	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9)
 		ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 	else
 		/*
@@ -216,7 +216,7 @@ static void __init exynos_smp_prepare_cpus(unsigned int max_cpus)
 
 	exynos_sysram_init();
 
-	if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
+	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9)
 		scu_enable(scu_base_addr());
 
 	/*

arch/arm/mach-exynos/pm.c

@@ -300,7 +300,7 @@ static int exynos_pm_suspend(void)
 	tmp = (S5P_USE_STANDBY_WFI0 | S5P_USE_STANDBY_WFE0);
 	__raw_writel(tmp, S5P_CENTRAL_SEQ_OPTION);
 
-	if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
+	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9)
 		exynos_cpu_save_register();
 
 	return 0;
@@ -334,7 +334,7 @@ static void exynos_pm_resume(void)
 	if (exynos_pm_central_resume())
 		goto early_wakeup;
 
-	if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
+	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9)
 		exynos_cpu_restore_register();
 
 	/* For release retention */
@@ -353,7 +353,7 @@ static void exynos_pm_resume(void)
 
 	s3c_pm_do_restore_core(exynos_core_save, ARRAY_SIZE(exynos_core_save));
 
-	if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
+	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9)
 		scu_enable(S5P_VA_SCU);
 
 early_wakeup:
@@ -440,15 +440,14 @@ static int exynos_cpu_pm_notifier(struct notifier_block *self,
 	case CPU_PM_ENTER:
 		if (cpu == 0) {
 			exynos_pm_central_suspend();
-			if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
+			if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9)
 				exynos_cpu_save_register();
 		}
 		break;
 
 	case CPU_PM_EXIT:
 		if (cpu == 0) {
-			if (read_cpuid_part_number() ==
-					ARM_CPU_PART_CORTEX_A9) {
+			if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9) {
 				scu_enable(S5P_VA_SCU);
 				exynos_cpu_restore_register();
 			}

arch/arm/mach-footbridge/include/mach/memory.h

@@ -59,11 +59,6 @@ extern unsigned long __bus_to_pfn(unsigned long);
  */
 #define FLUSH_BASE		0xf9000000
 
-/*
- * Physical DRAM offset.
- */
-#define PLAT_PHYS_OFFSET		UL(0x00000000)
-
 #define FLUSH_BASE_PHYS		0x50000000
 
 #endif

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)
 
 /*