Merge branch 'devel-stable' into for-next

Conflicts:
	arch/arm/include/asm/atomic.h
	arch/arm/include/asm/hardirq.h
	arch/arm/kernel/smp.c

arch/arm/Kconfig

@@ -52,6 +52,8 @@ config ARM
 	select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UID16
@@ -482,6 +484,7 @@ config ARCH_IXP4XX
 	bool "IXP4xx-based"
 	depends on MMU
 	select ARCH_HAS_DMA_SET_COHERENT_MASK
+	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARCH_REQUIRE_GPIOLIB
 	select CLKSRC_MMIO
 	select CPU_XSCALE
@@ -1545,6 +1548,32 @@ config MCPM
 	  for (multi-)cluster based systems, such as big.LITTLE based
 	  systems.
 
+config BIG_LITTLE
+	bool "big.LITTLE support (Experimental)"
+	depends on CPU_V7 && SMP
+	select MCPM
+	help
+	  This option enables support selections for the big.LITTLE
+	  system architecture.
+
+config BL_SWITCHER
+	bool "big.LITTLE switcher support"
+	depends on BIG_LITTLE && MCPM && HOTPLUG_CPU
+	select CPU_PM
+	select ARM_CPU_SUSPEND
+	help
+	  The big.LITTLE "switcher" provides the core functionality to
+	  transparently handle transition between a cluster of A15's
+	  and a cluster of A7's in a big.LITTLE system.
+
+config BL_SWITCHER_DUMMY_IF
+	tristate "Simple big.LITTLE switcher user interface"
+	depends on BL_SWITCHER && DEBUG_KERNEL
+	help
+	  This is a simple and dummy char dev interface to control
+	  the big.LITTLE switcher core code.  It is meant for
+	  debugging purposes only.
+
 choice
 	prompt "Memory split"
 	default VMSPLIT_3G

arch/arm/Makefile

@@ -16,6 +16,7 @@ LDFLAGS		:=
 LDFLAGS_vmlinux	:=-p --no-undefined -X
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux	+= --be8
+LDFLAGS_MODULE	+= --be8
 endif
 
 OBJCOPYFLAGS	:=-O binary -R .comment -S

arch/arm/boot/compressed/head.S

@@ -135,6 +135,7 @@ start:
 		.word	_edata			@ zImage end address
  THUMB(		.thumb			)
 1:
+ ARM_BE8(	setend	be )			@ go BE8 if compiled for BE8
 		mrs	r9, cpsr
 #ifdef CONFIG_ARM_VIRT_EXT
 		bl	__hyp_stub_install	@ get into SVC mode, reversibly
@@ -699,9 +700,7 @@ __armv4_mmu_cache_on:
 		mrc	p15, 0, r0, c1, c0, 0	@ read control reg
 		orr	r0, r0, #0x5000		@ I-cache enable, RR cache replacement
 		orr	r0, r0, #0x0030
-#ifdef CONFIG_CPU_ENDIAN_BE8
-		orr	r0, r0, #1 << 25	@ big-endian page tables
-#endif
+ ARM_BE8(	orr	r0, r0, #1 << 25 )	@ big-endian page tables
 		bl	__common_mmu_cache_on
 		mov	r0, #0
 		mcr	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
@@ -728,9 +727,7 @@ __armv7_mmu_cache_on:
 		orr	r0, r0, #1 << 22	@ U (v6 unaligned access model)
 						@ (needed for ARM1176)
 #ifdef CONFIG_MMU
-#ifdef CONFIG_CPU_ENDIAN_BE8
-		orr	r0, r0, #1 << 25	@ big-endian page tables
-#endif
+ ARM_BE8(	orr	r0, r0, #1 << 25 )	@ big-endian page tables
 		mrcne   p15, 0, r6, c2, c0, 2   @ read ttb control reg
 		orrne	r0, r0, #1		@ MMU enabled
 		movne	r1, #0xfffffffd		@ domain 0 = client

arch/arm/common/Makefile

@@ -17,3 +17,5 @@ obj-$(CONFIG_MCPM)		+= mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
 AFLAGS_mcpm_head.o		:= -march=armv7-a
 AFLAGS_vlock.o			:= -march=armv7-a
 obj-$(CONFIG_TI_PRIV_EDMA)	+= edma.o
+obj-$(CONFIG_BL_SWITCHER)	+= bL_switcher.o
+obj-$(CONFIG_BL_SWITCHER_DUMMY_IF) += bL_switcher_dummy_if.o

arch/arm/common/bL_switcher_dummy_if.c

+/*
+ * arch/arm/common/bL_switcher_dummy_if.c -- b.L switcher dummy interface
+ *
+ * Created by:	Nicolas Pitre, November 2012
+ * Copyright:	(C) 2012-2013  Linaro Limited
+ *
+ * Dummy interface to user space for debugging purpose only.
+ *
+ * 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.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <asm/uaccess.h>
+#include <asm/bL_switcher.h>
+
+static ssize_t bL_switcher_write(struct file *file, const char __user *buf,
+			size_t len, loff_t *pos)
+{
+	unsigned char val[3];
+	unsigned int cpu, cluster;
+	int ret;
+
+	pr_debug("%s\n", __func__);
+
+	if (len < 3)
+		return -EINVAL;
+
+	if (copy_from_user(val, buf, 3))
+		return -EFAULT;
+
+	/* format: <cpu#>,<cluster#> */
+	if (val[0] < '0' || val[0] > '9' ||
+	    val[1] != ',' ||
+	    val[2] < '0' || val[2] > '1')
+		return -EINVAL;
+
+	cpu = val[0] - '0';
+	cluster = val[2] - '0';
+	ret = bL_switch_request(cpu, cluster);
+
+	return ret ? : len;
+}
+
+static const struct file_operations bL_switcher_fops = {
+	.write		= bL_switcher_write,
+	.owner	= THIS_MODULE,
+};
+
+static struct miscdevice bL_switcher_device = {
+	MISC_DYNAMIC_MINOR,
+	"b.L_switcher",
+	&bL_switcher_fops
+};
+
+static int __init bL_switcher_dummy_if_init(void)
+{
+	return misc_register(&bL_switcher_device);
+}
+
+static void __exit bL_switcher_dummy_if_exit(void)
+{
+	misc_deregister(&bL_switcher_device);
+}
+
+module_init(bL_switcher_dummy_if_init);
+module_exit(bL_switcher_dummy_if_exit);

arch/arm/common/mcpm_entry.c

@@ -27,6 +27,18 @@ void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr)
 	sync_cache_w(&mcpm_entry_vectors[cluster][cpu]);
 }
 
+extern unsigned long mcpm_entry_early_pokes[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER][2];
+
+void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
+			 unsigned long poke_phys_addr, unsigned long poke_val)
+{
+	unsigned long *poke = &mcpm_entry_early_pokes[cluster][cpu][0];
+	poke[0] = poke_phys_addr;
+	poke[1] = poke_val;
+	__cpuc_flush_dcache_area((void *)poke, 8);
+	outer_clean_range(__pa(poke), __pa(poke + 2));
+}
+
 static const struct mcpm_platform_ops *platform_ops;
 
 int __init mcpm_platform_register(const struct mcpm_platform_ops *ops)

arch/arm/common/mcpm_head.S

@@ -15,6 +15,7 @@
 
 #include <linux/linkage.h>
 #include <asm/mcpm.h>
+#include <asm/assembler.h>
 
 #include "vlock.h"
 
@@ -47,6 +48,7 @@
 
 ENTRY(mcpm_entry_point)
 
+ ARM_BE8(setend        be)
  THUMB(	adr	r12, BSYM(1f)	)
  THUMB(	bx	r12		)
  THUMB(	.thumb			)
@@ -71,12 +73,19 @@ ENTRY(mcpm_entry_point)
 	 * position independent way.
 	 */
 	adr	r5, 3f
-	ldmia	r5, {r6, r7, r8, r11}
+	ldmia	r5, {r0, r6, r7, r8, r11}
+	add	r0, r5, r0			@ r0 = mcpm_entry_early_pokes
 	add	r6, r5, r6			@ r6 = mcpm_entry_vectors
 	ldr	r7, [r5, r7]			@ r7 = mcpm_power_up_setup_phys
 	add	r8, r5, r8			@ r8 = mcpm_sync
 	add	r11, r5, r11			@ r11 = first_man_locks
 
+	@ Perform an early poke, if any
+	add	r0, r0, r4, lsl #3
+	ldmia	r0, {r0, r1}
+	teq	r0, #0
+	strne	r1, [r0]
+
 	mov	r0, #MCPM_SYNC_CLUSTER_SIZE
 	mla	r8, r0, r10, r8			@ r8 = sync cluster base
 
@@ -195,7 +204,8 @@ mcpm_entry_gated:
 
 	.align	2
 
-3:	.word	mcpm_entry_vectors - .
+3:	.word	mcpm_entry_early_pokes - .
+	.word	mcpm_entry_vectors - 3b
 	.word	mcpm_power_up_setup_phys - 3b
 	.word	mcpm_sync - 3b
 	.word	first_man_locks - 3b
@@ -214,6 +224,10 @@ first_man_locks:
 ENTRY(mcpm_entry_vectors)
 	.space	4 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
 
+	.type	mcpm_entry_early_pokes, #object
+ENTRY(mcpm_entry_early_pokes)
+	.space	8 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
+
 	.type	mcpm_power_up_setup_phys, #object
 ENTRY(mcpm_power_up_setup_phys)
 	.space  4		@ set by mcpm_sync_init()

arch/arm/crypto/.gitignore

+aesbs-core.S

arch/arm/crypto/Makefile

@@ -3,7 +3,17 @@
 #
 
 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
 
-aes-arm-y  := aes-armv4.o aes_glue.o
-sha1-arm-y := sha1-armv4-large.o sha1_glue.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
+
+quiet_cmd_perl = PERL    $@
+      cmd_perl = $(PERL) $(<) > $(@)
+
+$(src)/aesbs-core.S_shipped: $(src)/bsaes-armv7.pl
+	$(call cmd,perl)
+
+.PRECIOUS: $(obj)/aesbs-core.S

arch/arm/crypto/aes_glue.c

@@ -6,22 +6,12 @@
 #include <linux/crypto.h>
 #include <crypto/aes.h>
 
-#define AES_MAXNR 14
+#include "aes_glue.h"
 
-typedef struct {
-	unsigned int rd_key[4 *(AES_MAXNR + 1)];
-	int rounds;
-} AES_KEY;
-
-struct AES_CTX {
-	AES_KEY enc_key;
-	AES_KEY dec_key;
-};
-
-asmlinkage void AES_encrypt(const u8 *in, u8 *out, AES_KEY *ctx);
-asmlinkage void AES_decrypt(const u8 *in, u8 *out, AES_KEY *ctx);
-asmlinkage int private_AES_set_decrypt_key(const unsigned char *userKey, const int bits, AES_KEY *key);
-asmlinkage int private_AES_set_encrypt_key(const unsigned char *userKey, const int bits, AES_KEY *key);
+EXPORT_SYMBOL(AES_encrypt);
+EXPORT_SYMBOL(AES_decrypt);
+EXPORT_SYMBOL(private_AES_set_encrypt_key);
+EXPORT_SYMBOL(private_AES_set_decrypt_key);
 
 static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
@@ -81,7 +71,7 @@ static struct crypto_alg aes_alg = {
 		.cipher	= {
 			.cia_min_keysize	= AES_MIN_KEY_SIZE,
 			.cia_max_keysize	= AES_MAX_KEY_SIZE,
-			.cia_setkey			= aes_set_key,
+			.cia_setkey		= aes_set_key,
 			.cia_encrypt		= aes_encrypt,
 			.cia_decrypt		= aes_decrypt
 		}

arch/arm/crypto/aes_glue.h

+
+#define AES_MAXNR 14
+
+struct AES_KEY {
+	unsigned int rd_key[4 * (AES_MAXNR + 1)];
+	int rounds;
+};
+
+struct AES_CTX {
+	struct AES_KEY enc_key;
+	struct AES_KEY dec_key;
+};
+
+asmlinkage void AES_encrypt(const u8 *in, u8 *out, struct AES_KEY *ctx);
+asmlinkage void AES_decrypt(const u8 *in, u8 *out, struct AES_KEY *ctx);
+asmlinkage int private_AES_set_decrypt_key(const unsigned char *userKey,
+					   const int bits, struct AES_KEY *key);
+asmlinkage int private_AES_set_encrypt_key(const unsigned char *userKey,
+					   const int bits, struct AES_KEY *key);

arch/arm/crypto/aesbs-glue.c

+/*
+ * linux/arch/arm/crypto/aesbs-glue.c - glue code for NEON bit sliced AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <asm/neon.h>
+#include <crypto/aes.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <linux/module.h>
+
+#include "aes_glue.h"
+
+#define BIT_SLICED_KEY_MAXSIZE	(128 * (AES_MAXNR - 1) + 2 * AES_BLOCK_SIZE)
+
+struct BS_KEY {
+	struct AES_KEY	rk;
+	int		converted;
+	u8 __aligned(8)	bs[BIT_SLICED_KEY_MAXSIZE];
+} __aligned(8);
+
+asmlinkage void bsaes_enc_key_convert(u8 out[], struct AES_KEY const *in);
+asmlinkage void bsaes_dec_key_convert(u8 out[], struct AES_KEY const *in);
+
+asmlinkage void bsaes_cbc_encrypt(u8 const in[], u8 out[], u32 bytes,
+				  struct BS_KEY *key, u8 iv[]);
+
+asmlinkage void bsaes_ctr32_encrypt_blocks(u8 const in[], u8 out[], u32 blocks,
+					   struct BS_KEY *key, u8 const iv[]);
+
+asmlinkage void bsaes_xts_encrypt(u8 const in[], u8 out[], u32 bytes,
+				  struct BS_KEY *key, u8 tweak[]);
+
+asmlinkage void bsaes_xts_decrypt(u8 const in[], u8 out[], u32 bytes,
+				  struct BS_KEY *key, u8 tweak[]);
+
+struct aesbs_cbc_ctx {
+	struct AES_KEY	enc;
+	struct BS_KEY	dec;
+};
+
+struct aesbs_ctr_ctx {
+	struct BS_KEY	enc;
+};
+
+struct aesbs_xts_ctx {
+	struct BS_KEY	enc;
+	struct BS_KEY	dec;
+	struct AES_KEY	twkey;
+};
+
+static int aesbs_cbc_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+			     unsigned int key_len)
+{
+	struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+	int bits = key_len * 8;
+
+	if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+	ctx->dec.rk = ctx->enc;
+	private_AES_set_decrypt_key(in_key, bits, &ctx->dec.rk);
+	ctx->dec.converted = 0;
+	return 0;
+}
+
+static int aesbs_ctr_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+			     unsigned int key_len)
+{
+	struct aesbs_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
+	int bits = key_len * 8;
+
+	if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc.rk)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+	ctx->enc.converted = 0;
+	return 0;
+}
+
+static int aesbs_xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+			     unsigned int key_len)
+{
+	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	int bits = key_len * 4;
+
+	if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc.rk)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+	ctx->dec.rk = ctx->enc.rk;
+	private_AES_set_decrypt_key(in_key, bits, &ctx->dec.rk);
+	private_AES_set_encrypt_key(in_key + key_len / 2, bits, &ctx->twkey);
+	ctx->enc.converted = ctx->dec.converted = 0;
+	return 0;
+}
+
+static int aesbs_cbc_encrypt(struct blkcipher_desc *desc,
+			     struct scatterlist *dst,
+			     struct scatterlist *src, unsigned int nbytes)
+{
+	struct aesbs_cbc_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	while (walk.nbytes) {
+		u32 blocks = walk.nbytes / AES_BLOCK_SIZE;
+		u8 *src = walk.src.virt.addr;
+
+		if (walk.dst.virt.addr == walk.src.virt.addr) {
+			u8 *iv = walk.iv;
+
+			do {
+				crypto_xor(src, iv, AES_BLOCK_SIZE);
+				AES_encrypt(src, src, &ctx->enc);
+				iv = src;
+				src += AES_BLOCK_SIZE;
+			} while (--blocks);
+			memcpy(walk.iv, iv, AES_BLOCK_SIZE);
+		} else {
+			u8 *dst = walk.dst.virt.addr;
+
+			do {
+				crypto_xor(walk.iv, src, AES_BLOCK_SIZE);
+				AES_encrypt(walk.iv, dst, &ctx->enc);
+				memcpy(walk.iv, dst, AES_BLOCK_SIZE);
+				src += AES_BLOCK_SIZE;
+				dst += AES_BLOCK_SIZE;
+			} while (--blocks);
+		}
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	return err;
+}
+
+static int aesbs_cbc_decrypt(struct blkcipher_desc *desc,
+			     struct scatterlist *dst,
+			     struct scatterlist *src, unsigned int nbytes)
+{
+	struct aesbs_cbc_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
+
+	while ((walk.nbytes / AES_BLOCK_SIZE) >= 8) {
+		kernel_neon_begin();
+		bsaes_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
+				  walk.nbytes, &ctx->dec, walk.iv);
+		kernel_neon_end();
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	while (walk.nbytes) {
+		u32 blocks = walk.nbytes / AES_BLOCK_SIZE;
+		u8 *dst = walk.dst.virt.addr;
+		u8 *src = walk.src.virt.addr;
+		u8 bk[2][AES_BLOCK_SIZE];
+		u8 *iv = walk.iv;
+
+		do {
+			if (walk.dst.virt.addr == walk.src.virt.addr)
+				memcpy(bk[blocks & 1], src, AES_BLOCK_SIZE);
+
+			AES_decrypt(src, dst, &ctx->dec.rk);
+			crypto_xor(dst, iv, AES_BLOCK_SIZE);
+
+			if (walk.dst.virt.addr == walk.src.virt.addr)
+				iv = bk[blocks & 1];
+			else
+				iv = src;
+
+			dst += AES_BLOCK_SIZE;
+			src += AES_BLOCK_SIZE;
+		} while (--blocks);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	return err;
+}
+
+static void inc_be128_ctr(__be32 ctr[], u32 addend)
+{
+	int i;
+
+	for (i = 3; i >= 0; i--, addend = 1) {
+		u32 n = be32_to_cpu(ctr[i]) + addend;
+
+		ctr[i] = cpu_to_be32(n);
+		if (n >= addend)
+			break;
+	}
+}
+
+static int aesbs_ctr_encrypt(struct blkcipher_desc *desc,
+			     struct scatterlist *dst, struct scatterlist *src,
+			     unsigned int nbytes)
+{
+	struct aesbs_ctr_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+	u32 blocks;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
+
+	while ((blocks = walk.nbytes / AES_BLOCK_SIZE)) {
+		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+		__be32 *ctr = (__be32 *)walk.iv;
+		u32 headroom = UINT_MAX - be32_to_cpu(ctr[3]);
+
+		/* avoid 32 bit counter overflow in the NEON code */
+		if (unlikely(headroom < blocks)) {
+			blocks = headroom + 1;
+			tail = walk.nbytes - blocks * AES_BLOCK_SIZE;
+		}
+		kernel_neon_begin();
+		bsaes_ctr32_encrypt_blocks(walk.src.virt.addr,
+					   walk.dst.virt.addr, blocks,
+					   &ctx->enc, walk.iv);
+		kernel_neon_end();
+		inc_be128_ctr(ctr, blocks);
+
+		nbytes -= blocks * AES_BLOCK_SIZE;
+		if (nbytes && nbytes == tail && nbytes <= AES_BLOCK_SIZE)
+			break;
+
+		err = blkcipher_walk_done(desc, &walk, tail);
+	}
+	if (walk.nbytes) {
+		u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
+		u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
+		u8 ks[AES_BLOCK_SIZE];
+
+		AES_encrypt(walk.iv, ks, &ctx->enc.rk);
+		if (tdst != tsrc)
+			memcpy(tdst, tsrc, nbytes);
+		crypto_xor(tdst, ks, nbytes);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	return err;
+}
+
+static int aesbs_xts_encrypt(struct blkcipher_desc *desc,
+			     struct scatterlist *dst,
+			     struct scatterlist *src, unsigned int nbytes)
+{
+	struct aesbs_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
+
+	/* generate the initial tweak */
+	AES_encrypt(walk.iv, walk.iv, &ctx->twkey);
+
+	while (walk.nbytes) {
+		kernel_neon_begin();
+		bsaes_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
+				  walk.nbytes, &ctx->enc, walk.iv);
+		kernel_neon_end();
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	return err;
+}
+
+static int aesbs_xts_decrypt(struct blkcipher_desc *desc,
+			     struct scatterlist *dst,
+			     struct scatterlist *src, unsigned int nbytes)
+{
+	struct aesbs_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
+
+	/* generate the initial tweak */
+	AES_encrypt(walk.iv, walk.iv, &ctx->twkey);
+
+	while (walk.nbytes) {
+		kernel_neon_begin();
+		bsaes_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr,
+				  walk.nbytes, &ctx->dec, walk.iv);
+		kernel_neon_end();
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	return err;
+}
+
+static struct crypto_alg aesbs_algs[] = { {
+	.cra_name		= "__cbc-aes-neonbs",
+	.cra_driver_name	= "__driver-cbc-aes-neonbs",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct aesbs_cbc_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= aesbs_cbc_set_key,
+		.encrypt	= aesbs_cbc_encrypt,
+		.decrypt	= aesbs_cbc_decrypt,
+	},
+}, {
+	.cra_name		= "__ctr-aes-neonbs",
+	.cra_driver_name	= "__driver-ctr-aes-neonbs",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct aesbs_ctr_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= aesbs_ctr_set_key,
+		.encrypt	= aesbs_ctr_encrypt,
+		.decrypt	= aesbs_ctr_encrypt,
+	},
+}, {
+	.cra_name		= "__xts-aes-neonbs",
+	.cra_driver_name	= "__driver-xts-aes-neonbs",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct aesbs_xts_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
+		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= aesbs_xts_set_key,
+		.encrypt	= aesbs_xts_encrypt,
+		.decrypt	= aesbs_xts_decrypt,
+	},
+}, {
+	.cra_name		= "cbc(aes)",
+	.cra_driver_name	= "cbc-aes-neonbs",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= __ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "ctr(aes)",
+	.cra_driver_name	= "ctr-aes-neonbs",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "xts(aes)",
+	.cra_driver_name	= "xts-aes-neonbs",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
+		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+} };
+
+static int __init aesbs_mod_init(void)
+{
+	if (!cpu_has_neon())
+		return -ENODEV;
+
+	return crypto_register_algs(aesbs_algs, ARRAY_SIZE(aesbs_algs));
+}
+
+static void __exit aesbs_mod_exit(void)
+{
+	crypto_unregister_algs(aesbs_algs, ARRAY_SIZE(aesbs_algs));
+}
+
+module_init(aesbs_mod_init);
+module_exit(aesbs_mod_exit);
+
+MODULE_DESCRIPTION("Bit sliced AES in CBC/CTR/XTS modes using NEON");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL");

arch/arm/include/asm/Kbuild

@@ -24,6 +24,7 @@ generic-y += sembuf.h
 generic-y += serial.h
 generic-y += shmbuf.h
 generic-y += siginfo.h
+generic-y += simd.h
 generic-y += sizes.h
 generic-y += socket.h
 generic-y += sockios.h

arch/arm/include/asm/assembler.h

@@ -53,6 +53,13 @@
 #define put_byte_3      lsl #0
 #endif
 
+/* Select code for any configuration running in BE8 mode */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define ARM_BE8(code...) code
+#else
+#define ARM_BE8(code...)
+#endif
+
 /*
  * Data preload for architectures that support it
  */

arch/arm/include/asm/atomic.h

@@ -12,6 +12,7 @@
 #define __ASM_ARM_ATOMIC_H
 
 #include <linux/compiler.h>
+#include <linux/prefetch.h>
 #include <linux/types.h>
 #include <linux/irqflags.h>
 #include <asm/barrier.h>
@@ -41,6 +42,7 @@ static inline void atomic_add(int i, atomic_t *v)
 	unsigned long tmp;
 	int result;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic_add\n"
 "1:	ldrex	%0, [%3]\n"
 "	add	%0, %0, %4\n"
@@ -79,6 +81,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 	unsigned long tmp;
 	int result;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic_sub\n"
 "1:	ldrex	%0, [%3]\n"
 "	sub	%0, %0, %4\n"
@@ -260,6 +263,7 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 {
 	long long tmp;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic64_set\n"
 "1:	ldrexd	%0, %H0, [%2]\n"
 "	strexd	%0, %3, %H3, [%2]\n"
@@ -276,10 +280,11 @@ static inline void atomic64_add(long long i, atomic64_t *v)
 	long long result;
 	unsigned long tmp;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic64_add\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%0, %0, %4\n"
-"	adc	%H0, %H0, %H4\n"
+"	adds	%Q0, %Q0, %Q4\n"
+"	adc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -297,8 +302,8 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v)
 
 	__asm__ __volatile__("@ atomic64_add_return\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%0, %0, %4\n"
-"	adc	%H0, %H0, %H4\n"
+"	adds	%Q0, %Q0, %Q4\n"
+"	adc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -316,10 +321,11 @@ static inline void atomic64_sub(long long i, atomic64_t *v)
 	long long result;
 	unsigned long tmp;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic64_sub\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, %4\n"
-"	sbc	%H0, %H0, %H4\n"
+"	subs	%Q0, %Q0, %Q4\n"
+"	sbc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -337,8 +343,8 @@ static inline long long atomic64_sub_return(long long i, atomic64_t *v)
 
 	__asm__ __volatile__("@ atomic64_sub_return\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, %4\n"
-"	sbc	%H0, %H0, %H4\n"
+"	subs	%Q0, %Q0, %Q4\n"
+"	sbc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -406,9 +412,9 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 
 	__asm__ __volatile__("@ atomic64_dec_if_positive\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, #1\n"
-"	sbc	%H0, %H0, #0\n"
-"	teq	%H0, #0\n"
+"	subs	%Q0, %Q0, #1\n"
+"	sbc	%R0, %R0, #0\n"
+"	teq	%R0, #0\n"
 "	bmi	2f\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
@@ -437,8 +443,8 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 "	teqeq	%H0, %H5\n"
 "	moveq	%1, #0\n"
 "	beq	2f\n"
-"	adds	%0, %0, %6\n"
-"	adc	%H0, %H0, %H6\n"
+"	adds	%Q0, %Q0, %Q6\n"
+"	adc	%R0, %R0, %R6\n"
 "	strexd	%2, %0, %H0, [%4]\n"
 "	teq	%2, #0\n"
 "	bne	1b\n"

arch/arm/include/asm/bL_switcher.h

+/*
+ * arch/arm/include/asm/bL_switcher.h
+ *
+ * Created by:  Nicolas Pitre, April 2012
+ * Copyright:   (C) 2012-2013  Linaro Limited
+ *
+ * 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.
+ */
+
+#ifndef ASM_BL_SWITCHER_H
+#define ASM_BL_SWITCHER_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+typedef void (*bL_switch_completion_handler)(void *cookie);
+
+int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
+			 bL_switch_completion_handler completer,
+			 void *completer_cookie);
+static inline int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
+{
+	return bL_switch_request_cb(cpu, new_cluster_id, NULL, NULL);
+}
+
+/*
+ * Register here to be notified about runtime enabling/disabling of
+ * the switcher.
+ *
+ * The notifier chain is called with the switcher activation lock held:
+ * the switcher will not be enabled or disabled during callbacks.
+ * Callbacks must not call bL_switcher_{get,put}_enabled().
+ */
+#define BL_NOTIFY_PRE_ENABLE	0
+#define BL_NOTIFY_POST_ENABLE	1
+#define BL_NOTIFY_PRE_DISABLE	2
+#define BL_NOTIFY_POST_DISABLE	3
+
+#ifdef CONFIG_BL_SWITCHER
+
+int bL_switcher_register_notifier(struct notifier_block *nb);
+int bL_switcher_unregister_notifier(struct notifier_block *nb);
+
+/*
+ * Use these functions to temporarily prevent enabling/disabling of
+ * the switcher.
+ * bL_switcher_get_enabled() returns true if the switcher is currently
+ * enabled.  Each call to bL_switcher_get_enabled() must be followed
+ * by a call to bL_switcher_put_enabled().  These functions are not
+ * recursive.
+ */
+bool bL_switcher_get_enabled(void);
+void bL_switcher_put_enabled(void);
+
+int bL_switcher_trace_trigger(void);
+int bL_switcher_get_logical_index(u32 mpidr);
+
+#else
+static inline int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline bool bL_switcher_get_enabled(void) { return false; }
+static inline void bL_switcher_put_enabled(void) { }
+static inline int bL_switcher_trace_trigger(void) { return 0; }
+static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; }
+#endif /* CONFIG_BL_SWITCHER */
+
+#endif

arch/arm/include/asm/bug.h

@@ -2,6 +2,8 @@
 #define _ASMARM_BUG_H
 
 #include <linux/linkage.h>
+#include <linux/types.h>
+#include <asm/opcodes.h>
 
 #ifdef CONFIG_BUG
 
@@ -12,10 +14,10 @@
  */
 #ifdef CONFIG_THUMB2_KERNEL
 #define BUG_INSTR_VALUE 0xde02
-#define BUG_INSTR_TYPE ".hword "
+#define BUG_INSTR(__value) __inst_thumb16(__value)
 #else
 #define BUG_INSTR_VALUE 0xe7f001f2
-#define BUG_INSTR_TYPE ".word "
+#define BUG_INSTR(__value) __inst_arm(__value)
 #endif
 
 
@@ -33,7 +35,7 @@
 
 #define __BUG(__file, __line, __value)				\
 do {								\
-	asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n"	\
+	asm volatile("1:\t" BUG_INSTR(__value) "\n"  \
 		".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \
 		"2:\t.asciz " #__file "\n" 			\
 		".popsection\n" 				\
@@ -48,7 +50,7 @@ do {								\
 
 #define __BUG(__file, __line, __value)				\
 do {								\
-	asm volatile(BUG_INSTR_TYPE #__value);			\
+	asm volatile(BUG_INSTR(__value) "\n");			\
 	unreachable();						\
 } while (0)
 #endif  /* CONFIG_DEBUG_BUGVERBOSE */

arch/arm/include/asm/hardirq.h

@@ -5,7 +5,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	7
+#define NR_IPI	8
 
 typedef struct {
 	unsigned int __softirq_pending;

arch/arm/include/asm/hardware/coresight.h

@@ -24,8 +24,8 @@
 #define TRACER_TIMEOUT 10000
 
 #define etm_writel(t, v, x) \
-	(__raw_writel((v), (t)->etm_regs + (x)))
-#define etm_readl(t, x) (__raw_readl((t)->etm_regs + (x)))
+	(writel_relaxed((v), (t)->etm_regs + (x)))
+#define etm_readl(t, x) (readl_relaxed((t)->etm_regs + (x)))
 
 /* CoreSight Management Registers */
 #define CSMR_LOCKACCESS 0xfb0
@@ -142,8 +142,8 @@
 #define ETBFF_TRIGFL		BIT(10)
 
 #define etb_writel(t, v, x) \
-	(__raw_writel((v), (t)->etb_regs + (x)))
-#define etb_readl(t, x) (__raw_readl((t)->etb_regs + (x)))
+	(writel_relaxed((v), (t)->etb_regs + (x)))
+#define etb_readl(t, x) (readl_relaxed((t)->etb_regs + (x)))
 
 #define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0)
 #define etm_unlock(t) \

arch/arm/include/asm/kgdb.h

@@ -11,6 +11,7 @@
 #define __ARM_KGDB_H__
 
 #include <linux/ptrace.h>
+#include <asm/opcodes.h>
 
 /*
  * GDB assumes that we're a user process being debugged, so
@@ -41,7 +42,7 @@
 
 static inline void arch_kgdb_breakpoint(void)
 {
-	asm(".word 0xe7ffdeff");
+	asm(__inst_arm(0xe7ffdeff));
 }
 
 extern void kgdb_handle_bus_error(void);

arch/arm/include/asm/mach/arch.h

@@ -49,6 +49,7 @@ struct machine_desc {
 	bool			(*smp_init)(void);
 	void			(*fixup)(struct tag *, char **,
 					 struct meminfo *);
+	void			(*init_meminfo)(void);
 	void			(*reserve)(void);/* reserve mem blocks	*/
 	void			(*map_io)(void);/* IO mapping function	*/
 	void			(*init_early)(void);

arch/arm/include/asm/mcpm.h

@@ -41,6 +41,14 @@ extern void mcpm_entry_point(void);
  */
 void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr);
 
+/*
+ * This sets an early poke i.e a value to be poked into some address
+ * from very early assembly code before the CPU is ungated.  The
+ * address must be physical, and if 0 then nothing will happen.
+ */
+void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
+			 unsigned long poke_phys_addr, unsigned long poke_val);
+
 /*
  * CPU/cluster power operations API for higher subsystems to use.
  */

arch/arm/include/asm/memory.h

@@ -172,8 +172,13 @@
  * so that all we need to do is modify the 8-bit constant field.
  */
 #define __PV_BITS_31_24	0x81000000
+#define __PV_BITS_7_0	0x81
+
+extern u64 __pv_phys_offset;
+extern u64 __pv_offset;
+extern void fixup_pv_table(const void *, unsigned long);
+extern const void *__pv_table_begin, *__pv_table_end;
 
-extern unsigned long __pv_phys_offset;
 #define PHYS_OFFSET __pv_phys_offset
 
 #define __pv_stub(from,to,instr,type)			\
@@ -185,22 +190,58 @@ extern unsigned long __pv_phys_offset;
 	: "=r" (to)					\
 	: "r" (from), "I" (type))
 
-static inline unsigned long __virt_to_phys(unsigned long x)
+#define __pv_stub_mov_hi(t)				\
+	__asm__ volatile("@ __pv_stub_mov\n"		\
+	"1:	mov	%R0, %1\n"			\
+	"	.pushsection .pv_table,\"a\"\n"		\
+	"	.long	1b\n"				\
+	"	.popsection\n"				\
+	: "=r" (t)					\
+	: "I" (__PV_BITS_7_0))
+
+#define __pv_add_carry_stub(x, y)			\
+	__asm__ volatile("@ __pv_add_carry_stub\n"	\
+	"1:	adds	%Q0, %1, %2\n"			\
+	"	adc	%R0, %R0, #0\n"			\
+	"	.pushsection .pv_table,\"a\"\n"		\
+	"	.long	1b\n"				\
+	"	.popsection\n"				\
+	: "+r" (y)					\
+	: "r" (x), "I" (__PV_BITS_31_24)		\
+	: "cc")
+
+static inline phys_addr_t __virt_to_phys(unsigned long x)
 {
-	unsigned long t;
-	__pv_stub(x, t, "add", __PV_BITS_31_24);
+	phys_addr_t t;
+
+	if (sizeof(phys_addr_t) == 4) {
+		__pv_stub(x, t, "add", __PV_BITS_31_24);
+	} else {
+		__pv_stub_mov_hi(t);
+		__pv_add_carry_stub(x, t);
+	}
 	return t;
 }
 
-static inline unsigned long __phys_to_virt(unsigned long x)
+static inline unsigned long __phys_to_virt(phys_addr_t x)
 {
 	unsigned long t;
 	__pv_stub(x, t, "sub", __PV_BITS_31_24);
 	return t;
 }
+
 #else
-#define __virt_to_phys(x)	((x) - PAGE_OFFSET + PHYS_OFFSET)
-#define __phys_to_virt(x)	((x) - PHYS_OFFSET + PAGE_OFFSET)
+
+static inline phys_addr_t __virt_to_phys(unsigned long x)
+{
+	return (phys_addr_t)x - PAGE_OFFSET + PHYS_OFFSET;
+}
+
+static inline unsigned long __phys_to_virt(phys_addr_t x)
+{
+	return x - PHYS_OFFSET + PAGE_OFFSET;
+}
+
 #endif
 #endif
 #endif /* __ASSEMBLY__ */
@@ -238,16 +279,33 @@ static inline phys_addr_t virt_to_phys(const volatile void *x)
 
 static inline void *phys_to_virt(phys_addr_t x)
 {
-	return (void *)(__phys_to_virt((unsigned long)(x)));
+	return (void *)__phys_to_virt(x);
 }
 
 /*
  * Drivers should NOT use these either.
  */
 #define __pa(x)			__virt_to_phys((unsigned long)(x))
-#define __va(x)			((void *)__phys_to_virt((unsigned long)(x)))
+#define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
 
+extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
+
+/*
+ * These are for systems that have a hardware interconnect supported alias of
+ * physical memory for idmap purposes.  Most cases should leave these
+ * untouched.
+ */
+static inline phys_addr_t __virt_to_idmap(unsigned long x)
+{
+	if (arch_virt_to_idmap)
+		return arch_virt_to_idmap(x);
+	else
+		return __virt_to_phys(x);
+}
+
+#define virt_to_idmap(x)	__virt_to_idmap((unsigned long)(x))
+
 /*
  * Virtual <-> DMA view memory address translations
  * Again, these are *only* valid on the kernel direct mapped RAM

arch/arm/include/asm/mmu.h

@@ -16,7 +16,7 @@ typedef struct {
 #ifdef CONFIG_CPU_HAS_ASID
 #define ASID_BITS	8
 #define ASID_MASK	((~0ULL) << ASID_BITS)
-#define ASID(mm)	((mm)->context.id.counter & ~ASID_MASK)
+#define ASID(mm)	((unsigned int)((mm)->context.id.counter & ~ASID_MASK))
 #else
 #define ASID(mm)	(0)
 #endif

arch/arm/include/asm/processor.h

@@ -22,6 +22,7 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/ptrace.h>
 #include <asm/types.h>
+#include <asm/unified.h>
 
 #ifdef __KERNEL__
 #define STACK_TOP	((current->personality & ADDR_LIMIT_32BIT) ? \
@@ -87,6 +88,17 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_EIP(tsk)	task_pt_regs(tsk)->ARM_pc
 #define KSTK_ESP(tsk)	task_pt_regs(tsk)->ARM_sp
 
+#ifdef CONFIG_SMP
+#define __ALT_SMP_ASM(smp, up)						\
+	"9998:	" smp "\n"						\
+	"	.pushsection \".alt.smp.init\", \"a\"\n"		\
+	"	.long	9998b\n"					\
+	"	" up "\n"						\
+	"	.popsection\n"
+#else
+#define __ALT_SMP_ASM(smp, up)	up
+#endif
+
 /*
  * Prefetching support - only ARMv5.
  */
@@ -97,17 +109,22 @@ static inline void prefetch(const void *ptr)
 {
 	__asm__ __volatile__(
 		"pld\t%a0"
-		:
-		: "p" (ptr)
-		: "cc");
+		:: "p" (ptr));
 }
 
+#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
 #define ARCH_HAS_PREFETCHW
-#define prefetchw(ptr)	prefetch(ptr)
-
-#define ARCH_HAS_SPINLOCK_PREFETCH
-#define spin_lock_prefetch(x) do { } while (0)
-
+static inline void prefetchw(const void *ptr)
+{
+	__asm__ __volatile__(
+		".arch_extension	mp\n"
+		__ALT_SMP_ASM(
+			WASM(pldw)		"\t%a0",
+			WASM(pld)		"\t%a0"
+		)
+		:: "p" (ptr));
+}
+#endif
 #endif
 
 #define HAVE_ARCH_PICK_MMAP_LAYOUT

arch/arm/include/asm/smp.h

@@ -84,6 +84,8 @@ extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
 
+extern int register_ipi_completion(struct completion *completion, int cpu);
+
 struct smp_operations {
 #ifdef CONFIG_SMP
 	/*

arch/arm/include/asm/spinlock.h

@@ -5,21 +5,13 @@
 #error SMP not supported on pre-ARMv6 CPUs
 #endif
 
-#include <asm/processor.h>
+#include <linux/prefetch.h>
 
 /*
  * sev and wfe are ARMv6K extensions.  Uniprocessor ARMv6 may not have the K
  * extensions, so when running on UP, we have to patch these instructions away.
  */
-#define ALT_SMP(smp, up)					\
-	"9998:	" smp "\n"					\
-	"	.pushsection \".alt.smp.init\", \"a\"\n"	\
-	"	.long	9998b\n"				\
-	"	" up "\n"					\
-	"	.popsection\n"
-
 #ifdef CONFIG_THUMB2_KERNEL
-#define SEV		ALT_SMP("sev.w", "nop.w")
 /*
  * For Thumb-2, special care is needed to ensure that the conditional WFE
  * instruction really does assemble to exactly 4 bytes (as required by
@@ -31,17 +23,18 @@
  * the assembler won't change IT instructions which are explicitly present
  * in the input.
  */
-#define WFE(cond)	ALT_SMP(		\
+#define WFE(cond)	__ALT_SMP_ASM(		\
 	"it " cond "\n\t"			\
 	"wfe" cond ".n",			\
 						\
 	"nop.w"					\
 )
 #else
-#define SEV		ALT_SMP("sev", "nop")
-#define WFE(cond)	ALT_SMP("wfe" cond, "nop")
+#define WFE(cond)	__ALT_SMP_ASM("wfe" cond, "nop")
 #endif
 
+#define SEV		__ALT_SMP_ASM(WASM(sev), WASM(nop))
+
 static inline void dsb_sev(void)
 {
 #if __LINUX_ARM_ARCH__ >= 7
@@ -77,6 +70,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	u32 newval;
 	arch_spinlock_t lockval;
 
+	prefetchw(&lock->slock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%3]\n"
 "	add	%1, %0, %4\n"
@@ -100,6 +94,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 	unsigned long contended, res;
 	u32 slock;
 
+	prefetchw(&lock->slock);
 	do {
 		__asm__ __volatile__(
 		"	ldrex	%0, [%3]\n"
@@ -156,6 +151,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
 
+	prefetchw(&rw->lock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%1]\n"
 "	teq	%0, #0\n"
@@ -174,6 +170,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	unsigned long contended, res;
 
+	prefetchw(&rw->lock);
 	do {
 		__asm__ __volatile__(
 		"	ldrex	%0, [%2]\n"
@@ -207,7 +204,7 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 }
 
 /* write_can_lock - would write_trylock() succeed? */
-#define arch_write_can_lock(x)		((x)->lock == 0)
+#define arch_write_can_lock(x)		(ACCESS_ONCE((x)->lock) == 0)
 
 /*
  * Read locks are a bit more hairy:
@@ -225,6 +222,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp, tmp2;
 
+	prefetchw(&rw->lock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%2]\n"
 "	adds	%0, %0, #1\n"
@@ -245,6 +243,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 	smp_mb();
 
+	prefetchw(&rw->lock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%2]\n"
 "	sub	%0, %0, #1\n"
@@ -263,6 +262,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
 	unsigned long contended, res;
 
+	prefetchw(&rw->lock);
 	do {
 		__asm__ __volatile__(
 		"	ldrex	%0, [%2]\n"
@@ -284,7 +284,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 }
 
 /* read_can_lock - would read_trylock() succeed? */
-#define arch_read_can_lock(x)		((x)->lock < 0x80000000)
+#define arch_read_can_lock(x)		(ACCESS_ONCE((x)->lock) < 0x80000000)
 
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags) arch_write_lock(lock)

arch/arm/include/asm/spinlock_types.h

@@ -25,7 +25,7 @@ typedef struct {
 #define __ARCH_SPIN_LOCK_UNLOCKED	{ { 0 } }
 
 typedef struct {
-	volatile unsigned int lock;
+	u32 lock;
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED		{ 0 }

arch/arm/include/asm/unified.h

@@ -38,6 +38,8 @@
 #ifdef __ASSEMBLY__
 #define W(instr)	instr.w
 #define BSYM(sym)	sym + 1
+#else
+#define WASM(instr)	#instr ".w"
 #endif
 
 #else	/* !CONFIG_THUMB2_KERNEL */
@@ -50,6 +52,8 @@
 #ifdef __ASSEMBLY__
 #define W(instr)	instr
 #define BSYM(sym)	sym
+#else
+#define WASM(instr)	#instr
 #endif
 
 #endif	/* CONFIG_THUMB2_KERNEL */

arch/arm/include/debug/pl01x.S

@@ -25,12 +25,14 @@
 
 		.macro	waituart,rd,rx
 1001:		ldr	\rd, [\rx, #UART01x_FR]
+ ARM_BE8(	rev	\rd, \rd )
 		tst	\rd, #UART01x_FR_TXFF
 		bne	1001b
 		.endm
 
 		.macro	busyuart,rd,rx
 1001:		ldr	\rd, [\rx, #UART01x_FR]
+ ARM_BE8(	rev	\rd, \rd )
 		tst	\rd, #UART01x_FR_BUSY
 		bne	1001b
 		.endm

arch/arm/include/uapi/asm/Kbuild

@@ -7,6 +7,7 @@ header-y += hwcap.h
 header-y += ioctls.h
 header-y += kvm_para.h
 header-y += mman.h
+header-y += perf_regs.h
 header-y += posix_types.h
 header-y += ptrace.h
 header-y += setup.h

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

+#ifndef _ASM_ARM_PERF_REGS_H
+#define _ASM_ARM_PERF_REGS_H
+
+enum perf_event_arm_regs {
+	PERF_REG_ARM_R0,
+	PERF_REG_ARM_R1,
+	PERF_REG_ARM_R2,
+	PERF_REG_ARM_R3,
+	PERF_REG_ARM_R4,
+	PERF_REG_ARM_R5,
+	PERF_REG_ARM_R6,
+	PERF_REG_ARM_R7,
+	PERF_REG_ARM_R8,
+	PERF_REG_ARM_R9,
+	PERF_REG_ARM_R10,
+	PERF_REG_ARM_FP,
+	PERF_REG_ARM_IP,
+	PERF_REG_ARM_SP,
+	PERF_REG_ARM_LR,
+	PERF_REG_ARM_PC,
+	PERF_REG_ARM_MAX,
+};
+#endif /* _ASM_ARM_PERF_REGS_H */

arch/arm/kernel/Makefile

@@ -17,7 +17,8 @@ CFLAGS_REMOVE_return_address.o = -pg
 
 obj-y		:= elf.o entry-common.o irq.o opcodes.o \
 		   process.o ptrace.o return_address.o \
-		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
+		   setup.o signal.o sigreturn_codes.o \
+		   stacktrace.o sys_arm.o time.o traps.o
 
 obj-$(CONFIG_ATAGS)		+= atags_parse.o
 obj-$(CONFIG_ATAGS_PROC)	+= atags_proc.o
@@ -78,6 +79,7 @@ obj-$(CONFIG_CPU_XSC3)		+= xscale-cp0.o
 obj-$(CONFIG_CPU_MOHAWK)	+= xscale-cp0.o
 obj-$(CONFIG_CPU_PJ4)		+= pj4-cp0.o
 obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_regs.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o perf_event_cpu.o
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o

arch/arm/kernel/armksyms.c

@@ -155,4 +155,5 @@ EXPORT_SYMBOL(__gnu_mcount_nc);
 
 #ifdef CONFIG_ARM_PATCH_PHYS_VIRT
 EXPORT_SYMBOL(__pv_phys_offset);
+EXPORT_SYMBOL(__pv_offset);
 #endif

arch/arm/kernel/entry-armv.S

@@ -416,9 +416,8 @@ __und_usr:
 	bne	__und_usr_thumb
 	sub	r4, r2, #4			@ ARM instr at LR - 4
 1:	ldrt	r0, [r4]
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	rev	r0, r0				@ little endian instruction
-#endif
+ ARM_BE8(rev	r0, r0)				@ little endian instruction
+
 	@ r0 = 32-bit ARM instruction which caused the exception
 	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
 	@ r4 = PC value for the faulting instruction

arch/arm/kernel/entry-common.S

@@ -393,9 +393,7 @@ ENTRY(vector_swi)
 #else
  USER(	ldr	r10, [lr, #-4]		)	@ get SWI instruction
 #endif
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	rev	r10, r10			@ little endian instruction
-#endif
+ ARM_BE8(rev	r10, r10)			@ little endian instruction
 
 #elif defined(CONFIG_AEABI)
 

arch/arm/kernel/head.S

@@ -77,6 +77,7 @@
 
 	__HEAD
 ENTRY(stext)
+ ARM_BE8(setend	be )			@ ensure we are in BE8 mode
 
  THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
  THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
@@ -352,6 +353,9 @@ ENTRY(secondary_startup)
 	 * the processor type - there is no need to check the machine type
 	 * as it has already been validated by the primary processor.
 	 */
+
+ ARM_BE8(setend	be)				@ ensure we are in BE8 mode
+
 #ifdef CONFIG_ARM_VIRT_EXT
 	bl	__hyp_stub_install_secondary
 #endif
@@ -555,6 +559,14 @@ ENTRY(fixup_smp)
 	ldmfd	sp!, {r4 - r6, pc}
 ENDPROC(fixup_smp)
 
+#ifdef __ARMEB__
+#define LOW_OFFSET	0x4
+#define HIGH_OFFSET	0x0
+#else
+#define LOW_OFFSET	0x0
+#define HIGH_OFFSET	0x4
+#endif
+
 #ifdef CONFIG_ARM_PATCH_PHYS_VIRT
 
 /* __fixup_pv_table - patch the stub instructions with the delta between
@@ -565,17 +577,20 @@ ENDPROC(fixup_smp)
 	__HEAD
 __fixup_pv_table:
 	adr	r0, 1f
-	ldmia	r0, {r3-r5, r7}
-	sub	r3, r0, r3	@ PHYS_OFFSET - PAGE_OFFSET
+	ldmia	r0, {r3-r7}
+	mvn	ip, #0
+	subs	r3, r0, r3	@ PHYS_OFFSET - PAGE_OFFSET
 	add	r4, r4, r3	@ adjust table start address
 	add	r5, r5, r3	@ adjust table end address
-	add	r7, r7, r3	@ adjust __pv_phys_offset address
-	str	r8, [r7]	@ save computed PHYS_OFFSET to __pv_phys_offset
+	add	r6, r6, r3	@ adjust __pv_phys_offset address
+	add	r7, r7, r3	@ adjust __pv_offset address
+	str	r8, [r6, #LOW_OFFSET]	@ save computed PHYS_OFFSET to __pv_phys_offset
+	strcc	ip, [r7, #HIGH_OFFSET]	@ save to __pv_offset high bits
 	mov	r6, r3, lsr #24	@ constant for add/sub instructions
 	teq	r3, r6, lsl #24 @ must be 16MiB aligned
 THUMB(	it	ne		@ cross section branch )
 	bne	__error
-	str	r6, [r7, #4]	@ save to __pv_offset
+	str	r3, [r7, #LOW_OFFSET]	@ save to __pv_offset low bits
 	b	__fixup_a_pv_table
 ENDPROC(__fixup_pv_table)
 
@@ -584,10 +599,19 @@ ENDPROC(__fixup_pv_table)
 	.long	__pv_table_begin
 	.long	__pv_table_end
 2:	.long	__pv_phys_offset
+	.long	__pv_offset
 
 	.text
 __fixup_a_pv_table:
+	adr	r0, 3f
+	ldr	r6, [r0]
+	add	r6, r6, r3
+	ldr	r0, [r6, #HIGH_OFFSET]	@ pv_offset high word
+	ldr	r6, [r6, #LOW_OFFSET]	@ pv_offset low word
+	mov	r6, r6, lsr #24
+	cmn	r0, #1
 #ifdef CONFIG_THUMB2_KERNEL
+	moveq	r0, #0x200000	@ set bit 21, mov to mvn instruction
 	lsls	r6, #24
 	beq	2f
 	clz	r7, r6
@@ -601,18 +625,42 @@ __fixup_a_pv_table:
 	b	2f
 1:	add     r7, r3
 	ldrh	ip, [r7, #2]
-	and	ip, 0x8f00
-	orr	ip, r6	@ mask in offset bits 31-24
+ARM_BE8(rev16	ip, ip)
+	tst	ip, #0x4000
+	and	ip, #0x8f00
+	orrne	ip, r6	@ mask in offset bits 31-24
+	orreq	ip, r0	@ mask in offset bits 7-0
+ARM_BE8(rev16	ip, ip)
 	strh	ip, [r7, #2]
+	bne	2f
+	ldrh	ip, [r7]
+ARM_BE8(rev16	ip, ip)
+	bic	ip, #0x20
+	orr	ip, ip, r0, lsr #16
+ARM_BE8(rev16	ip, ip)
+	strh	ip, [r7]
 2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
 	bcc	1b
 	bx	lr
 #else
+	moveq	r0, #0x400000	@ set bit 22, mov to mvn instruction
 	b	2f
 1:	ldr	ip, [r7, r3]
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	@ in BE8, we load data in BE, but instructions still in LE
+	bic	ip, ip, #0xff000000
+	tst	ip, #0x000f0000	@ check the rotation field
+	orrne	ip, ip, r6, lsl #24 @ mask in offset bits 31-24
+	biceq	ip, ip, #0x00004000 @ clear bit 22
+	orreq	ip, ip, r0, lsl #24 @ mask in offset bits 7-0
+#else
 	bic	ip, ip, #0x000000ff
-	orr	ip, ip, r6	@ mask in offset bits 31-24
+	tst	ip, #0xf00	@ check the rotation field
+	orrne	ip, ip, r6	@ mask in offset bits 31-24
+	biceq	ip, ip, #0x400000	@ clear bit 22
+	orreq	ip, ip, r0	@ mask in offset bits 7-0
+#endif
 	str	ip, [r7, r3]
 2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
@@ -621,28 +669,30 @@ __fixup_a_pv_table:
 #endif
 ENDPROC(__fixup_a_pv_table)
 
+	.align
+3:	.long __pv_offset
+
 ENTRY(fixup_pv_table)
 	stmfd	sp!, {r4 - r7, lr}
-	ldr	r2, 2f			@ get address of __pv_phys_offset
 	mov	r3, #0			@ no offset
 	mov	r4, r0			@ r0 = table start
 	add	r5, r0, r1		@ r1 = table size
-	ldr	r6, [r2, #4]		@ get __pv_offset
 	bl	__fixup_a_pv_table
 	ldmfd	sp!, {r4 - r7, pc}
 ENDPROC(fixup_pv_table)
 
-	.align
-2:	.long	__pv_phys_offset
-
 	.data
 	.globl	__pv_phys_offset
 	.type	__pv_phys_offset, %object
 __pv_phys_offset:
-	.long	0
-	.size	__pv_phys_offset, . - __pv_phys_offset
+	.quad	0
+	.size	__pv_phys_offset, . -__pv_phys_offset
+
+	.globl	__pv_offset
+	.type	__pv_offset, %object
 __pv_offset:
-	.long	0
+	.quad	0
+	.size	__pv_offset, . -__pv_offset
 #endif
 
 #include "head-common.S"

arch/arm/kernel/perf_event.c

@@ -256,12 +256,11 @@ validate_event(struct pmu_hw_events *hw_events,
 	       struct perf_event *event)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	struct pmu *leader_pmu = event->group_leader->pmu;
 
 	if (is_software_event(event))
 		return 1;
 
-	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+	if (event->state < PERF_EVENT_STATE_OFF)
 		return 1;
 
 	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)

arch/arm/kernel/perf_regs.c

+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM_MAX))
+		return 0;
+
+	return regs->uregs[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_ARM_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+	return PERF_SAMPLE_REGS_ABI_32;
+}