Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM updates from Russell King:
 "Included in this series are:

   1. BE8 (modern big endian) changes for ARM from Ben Dooks
   2. big.Little support from Nicolas Pitre and Dave Martin
   3. support for LPAE systems with all system memory above 4GB
   4. Perf updates from Will Deacon
   5. Additional prefetching and other performance improvements from Will.
   6. Neon-optimised AES implementation fro Ard.
   7. A number of smaller fixes scattered around the place.

  There is a rather horrid merge conflict in tools/perf - I was never
  notified of the conflict because it originally occurred between Will's
  tree and other stuff.  Consequently I have a resolution which Will
  forwarded me, which I'll forward on immediately after sending this
  mail.

  The other notable thing is I'm expecting some build breakage in the
  crypto stuff on ARM only with Ard's AES patches.  These were merged
  into a stable git branch which others had already pulled, so there's
  little I can do about this.  The problem is caused because these
  patches have a dependency on some code in the crypto git tree - I
  tried requesting a branch I can pull to resolve these, and all I got
  each time from the crypto people was "we'll revert our patches then"
  which would only make things worse since I still don't have the
  dependent patches.  I've no idea what's going on there or how to
  resolve that, and since I can't split these patches from the rest of
  this pull request, I'm rather stuck with pushing this as-is or
  reverting Ard's patches.

  Since it should "come out in the wash" I've left them in - the only
  build problems they seem to cause at the moment are with randconfigs,
  and since it's a new feature anyway.  However, if by -rc1 the
  dependencies aren't in, I think it'd be best to revert Ard's patches"

I resolved the perf conflict roughly as per the patch sent by Russell,
but there may be some differences.  Any errors are likely mine.  Let's
see how the crypto issues work out..

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (110 commits)
  ARM: 7868/1: arm/arm64: remove atomic_clear_mask() in "include/asm/atomic.h"
  ARM: 7867/1: include: asm: use 'int' instead of 'unsigned long' for 'oldval' in atomic_cmpxchg().
  ARM: 7866/1: include: asm: use 'long long' instead of 'u64' within atomic.h
  ARM: 7871/1: amba: Extend number of IRQS
  ARM: 7887/1: Don't smp_cross_call() on UP devices in arch_irq_work_raise()
  ARM: 7872/1: Support arch_irq_work_raise() via self IPIs
  ARM: 7880/1: Clear the IT state independent of the Thumb-2 mode
  ARM: 7878/1: nommu: Implement dummy early_paging_init()
  ARM: 7876/1: clear Thumb-2 IT state on exception handling
  ARM: 7874/2: bL_switcher: Remove cpu_hotplug_driver_{lock,unlock}()
  ARM: footbridge: fix build warnings for netwinder
  ARM: 7873/1: vfp: clear vfp_current_hw_state for dying cpu
  ARM: fix misplaced arch_virt_to_idmap()
  ARM: 7848/1: mcpm: Implement cpu_kill() to synchronise on powerdown
  ARM: 7847/1: mcpm: Factor out logical-to-physical CPU translation
  ARM: 7869/1: remove unused XSCALE_PMU Kconfig param
  ARM: 7864/1: Handle 64-bit memory in case of 32-bit phys_addr_t
  ARM: 7863/1: Let arm_add_memory() always use 64-bit arguments
  ARM: 7862/1: pcpu: replace __get_cpu_var_uses
  ARM: 7861/1: cacheflush: consolidate single-CPU ARMv7 cache disabling code
  ...

arch/arm/Kconfig

@@ -5,6 +5,7 @@ config ARM
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
+	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT if MMU
 	select CLONE_BACKWARDS
@@ -51,6 +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
@@ -481,6 +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
@@ -688,7 +692,6 @@ config ARCH_SA1100
 	select GENERIC_CLOCKEVENTS
 	select HAVE_IDE
 	select ISA
-	select NEED_MACH_GPIO_H
 	select NEED_MACH_MEMORY_H
 	select SPARSE_IRQ
 	help
@@ -1064,11 +1067,6 @@ config IWMMXT
 	  Enable support for iWMMXt context switching at run time if
 	  running on a CPU that supports it.
 
-config XSCALE_PMU
-	bool
-	depends on CPU_XSCALE
-	default y
-
 config MULTI_IRQ_HANDLER
 	bool
 	help
@@ -1516,6 +1514,32 @@ 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/Kconfig.debug

@@ -318,6 +318,7 @@ choice
 	config DEBUG_MSM_UART1
 		bool "Kernel low-level debugging messages via MSM UART1"
 		depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
+		select DEBUG_MSM_UART
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the first serial port on MSM devices.
@@ -325,6 +326,7 @@ choice
 	config DEBUG_MSM_UART2
 		bool "Kernel low-level debugging messages via MSM UART2"
 		depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
+		select DEBUG_MSM_UART
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the second serial port on MSM devices.
@@ -332,6 +334,7 @@ choice
 	config DEBUG_MSM_UART3
 		bool "Kernel low-level debugging messages via MSM UART3"
 		depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
+		select DEBUG_MSM_UART
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the third serial port on MSM devices.
@@ -340,6 +343,7 @@ choice
 		bool "Kernel low-level debugging messages via MSM 8660 UART"
 		depends on ARCH_MSM8X60
 		select MSM_HAS_DEBUG_UART_HS
+		select DEBUG_MSM_UART
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the serial port on MSM 8660 devices.
@@ -348,10 +352,20 @@ choice
 		bool "Kernel low-level debugging messages via MSM 8960 UART"
 		depends on ARCH_MSM8960
 		select MSM_HAS_DEBUG_UART_HS
+		select DEBUG_MSM_UART
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the serial port on MSM 8960 devices.
 
+	config DEBUG_MSM8974_UART
+		bool "Kernel low-level debugging messages via MSM 8974 UART"
+		depends on ARCH_MSM8974
+		select MSM_HAS_DEBUG_UART_HS
+		select DEBUG_MSM_UART
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the serial port on MSM 8974 devices.
+
 	config DEBUG_MVEBU_UART
 		bool "Kernel low-level debugging messages via MVEBU UART (old bootloaders)"
 		depends on ARCH_MVEBU
@@ -841,6 +855,20 @@ choice
 		  options; the platform specific options are deprecated
 		  and will be soon removed.
 
+	config DEBUG_LL_UART_EFM32
+		bool "Kernel low-level debugging via efm32 UART"
+		depends on ARCH_EFM32
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to an UART or USART port on efm32 based
+		  machines. Use the following addresses for DEBUG_UART_PHYS:
+
+		    0x4000c000 | USART0
+		    0x4000c400 | USART1
+		    0x4000c800 | USART2
+		    0x4000e000 | UART0
+		    0x4000e400 | UART1
+
 	config DEBUG_LL_UART_PL01X
 		bool "Kernel low-level debugging via ARM Ltd PL01x Primecell UART"
 		help
@@ -887,11 +915,16 @@ config DEBUG_STI_UART
 	bool
 	depends on ARCH_STI
 
+config DEBUG_MSM_UART
+	bool
+	depends on ARCH_MSM
+
 config DEBUG_LL_INCLUDE
 	string
 	default "debug/8250.S" if DEBUG_LL_UART_8250 || DEBUG_UART_8250
 	default "debug/pl01x.S" if DEBUG_LL_UART_PL01X || DEBUG_UART_PL01X
 	default "debug/exynos.S" if DEBUG_EXYNOS_UART
+	default "debug/efm32.S" if DEBUG_LL_UART_EFM32
 	default "debug/icedcc.S" if DEBUG_ICEDCC
 	default "debug/imx.S" if DEBUG_IMX1_UART || \
 				 DEBUG_IMX25_UART || \
@@ -902,11 +935,7 @@ config DEBUG_LL_INCLUDE
 				 DEBUG_IMX53_UART ||\
 				 DEBUG_IMX6Q_UART || \
 				 DEBUG_IMX6SL_UART
-	default "debug/msm.S" if DEBUG_MSM_UART1 || \
+	default "debug/msm.S" if DEBUG_MSM_UART
-				 DEBUG_MSM_UART2 || \
-				 DEBUG_MSM_UART3 || \
-				 DEBUG_MSM8660_UART || \
-				 DEBUG_MSM8960_UART
 	default "debug/omap2plus.S" if DEBUG_OMAP2PLUS_UART
 	default "debug/sirf.S" if DEBUG_SIRFPRIMA2_UART1 || DEBUG_SIRFMARCO_UART1
 	default "debug/sti.S" if DEBUG_STI_UART
@@ -959,6 +988,7 @@ config DEBUG_UART_PHYS
 	default 0x20064000 if DEBUG_RK29_UART1 || DEBUG_RK3X_UART2
 	default 0x20068000 if DEBUG_RK29_UART2 || DEBUG_RK3X_UART3
 	default 0x20201000 if DEBUG_BCM2835
+	default 0x4000e400 if DEBUG_LL_UART_EFM32
 	default 0x40090000 if ARCH_LPC32XX
 	default 0x40100000 if DEBUG_PXA_UART1
 	default 0x42000000 if ARCH_GEMINI
@@ -989,6 +1019,7 @@ config DEBUG_UART_PHYS
 	default 0xfff36000 if DEBUG_HIGHBANK_UART
 	default 0xfffff700 if ARCH_IOP33X
 	depends on DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \
+		DEBUG_LL_UART_EFM32 || \
 		DEBUG_UART_8250 || DEBUG_UART_PL01X
 
 config DEBUG_UART_VIRT

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
+ ARM_BE8(	orr	r0, r0, #1 << 25 )	@ big-endian page tables
-		orr	r0, r0, #1 << 25	@ big-endian page tables
-#endif
 		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
+ ARM_BE8(	orr	r0, r0, #1 << 25 )	@ big-endian page tables
-		orr	r0, r0, #1 << 25	@ big-endian page tables
-#endif
 		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

@@ -16,3 +16,5 @@ 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

@@ -0,0 +1,71 @@
+/*
+ * 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)
@@ -90,6 +102,21 @@ void mcpm_cpu_power_down(void)
 	BUG();
 }
 
+int mcpm_cpu_power_down_finish(unsigned int cpu, unsigned int cluster)
+{
+	int ret;
+
+	if (WARN_ON_ONCE(!platform_ops || !platform_ops->power_down_finish))
+		return -EUNATCH;
+
+	ret = platform_ops->power_down_finish(cpu, cluster);
+	if (ret)
+		pr_warn("%s: cpu %u, cluster %u failed to power down (%d)\n",
+			__func__, cpu, cluster, ret);
+
+	return ret;
+}
+
 void mcpm_cpu_suspend(u64 expected_residency)
 {
 	phys_reset_t phys_reset;

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/common/mcpm_platsmp.c

@@ -19,14 +19,23 @@
 #include <asm/smp.h>
 #include <asm/smp_plat.h>
 
-static int mcpm_boot_secondary(unsigned int cpu, struct task_struct *idle)
+static void cpu_to_pcpu(unsigned int cpu,
+			unsigned int *pcpu, unsigned int *pcluster)
 {
-	unsigned int mpidr, pcpu, pcluster, ret;
+	unsigned int mpidr;
-	extern void secondary_startup(void);
 
 	mpidr = cpu_logical_map(cpu);
-	pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	*pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-	pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	*pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+}
+
+static int mcpm_boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+	unsigned int pcpu, pcluster, ret;
+	extern void secondary_startup(void);
+
+	cpu_to_pcpu(cpu, &pcpu, &pcluster);
+
 	pr_debug("%s: logical CPU %d is physical CPU %d cluster %d\n",
 		 __func__, cpu, pcpu, pcluster);
 
@@ -47,6 +56,15 @@ static void mcpm_secondary_init(unsigned int cpu)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
+static int mcpm_cpu_kill(unsigned int cpu)
+{
+	unsigned int pcpu, pcluster;
+
+	cpu_to_pcpu(cpu, &pcpu, &pcluster);
+
+	return !mcpm_cpu_power_down_finish(pcpu, pcluster);
+}
+
 static int mcpm_cpu_disable(unsigned int cpu)
 {
 	/*
@@ -73,6 +91,7 @@ static struct smp_operations __initdata mcpm_smp_ops = {
 	.smp_boot_secondary	= mcpm_boot_secondary,
 	.smp_secondary_init	= mcpm_secondary_init,
 #ifdef CONFIG_HOTPLUG_CPU
+	.cpu_kill		= mcpm_cpu_kill,
 	.cpu_disable		= mcpm_cpu_disable,
 	.cpu_die		= mcpm_cpu_die,
 #endif

arch/arm/common/timer-sp.c

@@ -175,7 +175,7 @@ static struct clock_event_device sp804_clockevent = {
 
 static struct irqaction sp804_timer_irq = {
 	.name		= "timer",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= sp804_timer_interrupt,
 	.dev_id		= &sp804_clockevent,
 };

arch/arm/configs/h3600_defconfig

@@ -1,5 +1,6 @@
-CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_MODULES=y
@@ -11,11 +12,11 @@ CONFIG_ARCH_SA1100=y
 CONFIG_SA1100_H3600=y
 CONFIG_PCCARD=y
 CONFIG_PCMCIA_SA1100=y
+CONFIG_PREEMPT=y
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 # CONFIG_CPU_FREQ_STAT is not set
 CONFIG_FPE_NWFPE=y
-CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
@@ -24,13 +25,10 @@ CONFIG_IRDA=m
 CONFIG_IRLAN=m
 CONFIG_IRNET=m
 CONFIG_IRCOMM=m
-CONFIG_SA1100_FIR=m
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_REDBOOT_PARTS=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_ADV_OPTIONS=y
@@ -41,19 +39,15 @@ CONFIG_MTD_SA1100=y
 CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
-# CONFIG_MISC_DEVICES is not set
 CONFIG_IDE=y
 CONFIG_BLK_DEV_IDECS=y
 CONFIG_NETDEVICES=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
-# CONFIG_WLAN is not set
-CONFIG_NET_PCMCIA=y
 CONFIG_PCMCIA_PCNET=y
 CONFIG_PPP=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_DEFLATE=m
 CONFIG_PPP_BSDCOMP=m
+CONFIG_PPP_DEFLATE=m
+CONFIG_PPP_ASYNC=m
+# CONFIG_WLAN is not set
 # CONFIG_KEYBOARD_ATKBD is not set
 CONFIG_KEYBOARD_GPIO=y
 # CONFIG_INPUT_MOUSE is not set
@@ -64,8 +58,6 @@ CONFIG_SERIAL_SA1100_CONSOLE=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
 CONFIG_FB_SA1100=y
-# CONFIG_VGA_CONSOLE is not set
-# CONFIG_HID_SUPPORT is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
 CONFIG_MSDOS_FS=m
@@ -74,6 +66,4 @@ CONFIG_JFFS2_FS=y
 CONFIG_CRAMFS=m
 CONFIG_NFS_FS=y
 CONFIG_NFSD=m
-CONFIG_SMB_FS=m
 CONFIG_NLS=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set

arch/arm/crypto/.gitignore

@@ -0,0 +1 @@
+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
+aes-arm-y	:= aes-armv4.o aes_glue.o
-sha1-arm-y := sha1-armv4-large.o sha1_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 {
+EXPORT_SYMBOL(AES_encrypt);
-	unsigned int rd_key[4 *(AES_MAXNR + 1)];
+EXPORT_SYMBOL(AES_decrypt);
-	int rounds;
+EXPORT_SYMBOL(private_AES_set_encrypt_key);
-} AES_KEY;
+EXPORT_SYMBOL(private_AES_set_decrypt_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);
 
 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

@@ -0,0 +1,19 @@
+
+#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

@@ -0,0 +1,434 @@
+/*
+ * 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