Merge branch 'linux-linaro-lsk' into linux-linaro-lsk-rt

19 files changed, 543 insertions, 69 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index bb6571607c6f..8b0c1829be89 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -118,6 +118,9 @@ config IOMMU_HELPER
 config FIX_EARLYCON_MEM
 	def_bool y
 
+config KERNEL_MODE_NEON
+	def_bool y
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index c43b4ac13008..50f559f574fe 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -37,8 +37,21 @@ struct fpsimd_state {
 			u32 fpcr;
 		};
 	};
+	/* the id of the last cpu to have restored this state */
+	unsigned int cpu;
 };
 
+/*
+ * Struct for stacking the bottom 'n' FP/SIMD registers.
+ */
+struct fpsimd_partial_state {
+	u32		fpsr;
+	u32		fpcr;
+	u32		num_regs;
+	__uint128_t	vregs[32];
+};
+
+
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /* Masks for extracting the FPSR and FPCR from the FPSCR */
 #define VFP_FPSCR_STAT_MASK	0xf800009f
@@ -58,6 +71,16 @@ extern void fpsimd_load_state(struct fpsimd_state *state);
 extern void fpsimd_thread_switch(struct task_struct *next);
 extern void fpsimd_flush_thread(void);
 
+extern void fpsimd_preserve_current_state(void);
+extern void fpsimd_restore_current_state(void);
+extern void fpsimd_update_current_state(struct fpsimd_state *state);
+
+extern void fpsimd_flush_task_state(struct task_struct *target);
+
+extern void fpsimd_save_partial_state(struct fpsimd_partial_state *state,
+				      u32 num_regs);
+extern void fpsimd_load_partial_state(struct fpsimd_partial_state *state);
+
 #endif
 
 #endif
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index bbec599c96bd..768414d55e64 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -62,3 +62,38 @@
 	ldr	w\tmpnr, [\state, #16 * 2 + 4]
 	msr	fpcr, x\tmpnr
 .endm
+
+.altmacro
+.macro fpsimd_save_partial state, numnr, tmpnr1, tmpnr2
+	mrs	x\tmpnr1, fpsr
+	str	w\numnr, [\state, #8]
+	mrs	x\tmpnr2, fpcr
+	stp	w\tmpnr1, w\tmpnr2, [\state]
+	adr	x\tmpnr1, 0f
+	add	\state, \state, x\numnr, lsl #4
+	sub	x\tmpnr1, x\tmpnr1, x\numnr, lsl #1
+	br	x\tmpnr1
+	.irp	qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0
+	.irp	qb, %(qa + 1)
+	stp	q\qa, q\qb, [\state, # -16 * \qa - 16]
+	.endr
+	.endr
+0:
+.endm
+
+.macro fpsimd_restore_partial state, tmpnr1, tmpnr2
+	ldp	w\tmpnr1, w\tmpnr2, [\state]
+	msr	fpsr, x\tmpnr1
+	msr	fpcr, x\tmpnr2
+	adr	x\tmpnr1, 0f
+	ldr	w\tmpnr2, [\state, #8]
+	add	\state, \state, x\tmpnr2, lsl #4
+	sub	x\tmpnr1, x\tmpnr1, x\tmpnr2, lsl #1
+	br	x\tmpnr1
+	.irp	qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0
+	.irp	qb, %(qa + 1)
+	ldp	q\qa, q\qb, [\state, # -16 * \qa - 16]
+	.endr
+	.endr
+0:
+.endm
diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h
new file mode 100644
index 000000000000..13ce4cc18e26
--- /dev/null
+++ b/arch/arm64/include/asm/neon.h
@@ -0,0 +1,18 @@
+/*
+ * linux/arch/arm64/include/asm/neon.h
+ *
+ * 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 <linux/types.h>
+
+#define cpu_has_neon()		(1)
+
+#define kernel_neon_begin()	kernel_neon_begin_partial(32)
+
+void kernel_neon_begin_partial(u32 num_regs);
+void kernel_neon_end(void);
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 59f151f8241d..c09cbf6ce34a 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -109,6 +109,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SIGPENDING		0
 #define TIF_NEED_RESCHED	1
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
+#define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
 #define TIF_SYSCALL_TRACE	8
 #define TIF_SYSCALL_AUDIT	9
 #define TIF_SYSCALL_TRACEPOINT	10
@@ -124,6 +125,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_FOREIGN_FPSTATE	(1 << TIF_FOREIGN_FPSTATE)
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
@@ -131,7 +133,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-				 _TIF_NOTIFY_RESUME)
+				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE)
 
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP)
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 6a27cd6dbfa6..d358ccacfc00 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -41,3 +41,27 @@ ENTRY(fpsimd_load_state)
 	fpsimd_restore x0, 8
 	ret
 ENDPROC(fpsimd_load_state)
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Save the bottom n FP registers.
+ *
+ * x0 - pointer to struct fpsimd_partial_state
+ */
+ENTRY(fpsimd_save_partial_state)
+	fpsimd_save_partial x0, 1, 8, 9
+	ret
+ENDPROC(fpsimd_load_partial_state)
+
+/*
+ * Load the bottom n FP registers.
+ *
+ * x0 - pointer to struct fpsimd_partial_state
+ */
+ENTRY(fpsimd_load_partial_state)
+	fpsimd_restore_partial x0, 8, 9
+	ret
+ENDPROC(fpsimd_load_partial_state)
+
+#endif
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index fa789169f98b..1fe70fa6160c 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -591,7 +591,7 @@ fast_work_pending:
 	str	x0, [sp, #S_X0]			// returned x0
 work_pending:
 	tbnz	x1, #TIF_NEED_RESCHED, work_resched
-	/* TIF_SIGPENDING or TIF_NOTIFY_RESUME case */
+	/* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
 	ldr	x2, [sp, #S_PSTATE]
 	mov	x0, sp				// 'regs'
 	tst	x2, #PSR_MODE_MASK		// user mode regs?
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 522df9c7f3a4..ad8aebb1cdef 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/signal.h>
+#include <linux/hardirq.h>
 
 #include <asm/fpsimd.h>
 #include <asm/cputype.h>
@@ -34,6 +35,60 @@
 #define FPEXC_IDF	(1 << 7)
 
 /*
+ * In order to reduce the number of times the FPSIMD state is needlessly saved
+ * and restored, we need to keep track of two things:
+ * (a) for each task, we need to remember which CPU was the last one to have
+ *     the task's FPSIMD state loaded into its FPSIMD registers;
+ * (b) for each CPU, we need to remember which task's userland FPSIMD state has
+ *     been loaded into its FPSIMD registers most recently, or whether it has
+ *     been used to perform kernel mode NEON in the meantime.
+ *
+ * For (a), we add a 'cpu' field to struct fpsimd_state, which gets updated to
+ * the id of the current CPU everytime the state is loaded onto a CPU. For (b),
+ * we add the per-cpu variable 'fpsimd_last_state' (below), which contains the
+ * address of the userland FPSIMD state of the task that was loaded onto the CPU
+ * the most recently, or NULL if kernel mode NEON has been performed after that.
+ *
+ * With this in place, we no longer have to restore the next FPSIMD state right
+ * when switching between tasks. Instead, we can defer this check to userland
+ * resume, at which time we verify whether the CPU's fpsimd_last_state and the
+ * task's fpsimd_state.cpu are still mutually in sync. If this is the case, we
+ * can omit the FPSIMD restore.
+ *
+ * As an optimization, we use the thread_info flag TIF_FOREIGN_FPSTATE to
+ * indicate whether or not the userland FPSIMD state of the current task is
+ * present in the registers. The flag is set unless the FPSIMD registers of this
+ * CPU currently contain the most recent userland FPSIMD state of the current
+ * task.
+ *
+ * For a certain task, the sequence may look something like this:
+ * - the task gets scheduled in; if both the task's fpsimd_state.cpu field
+ *   contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu
+ *   variable points to the task's fpsimd_state, the TIF_FOREIGN_FPSTATE flag is
+ *   cleared, otherwise it is set;
+ *
+ * - the task returns to userland; if TIF_FOREIGN_FPSTATE is set, the task's
+ *   userland FPSIMD state is copied from memory to the registers, the task's
+ *   fpsimd_state.cpu field is set to the id of the current CPU, the current
+ *   CPU's fpsimd_last_state pointer is set to this task's fpsimd_state and the
+ *   TIF_FOREIGN_FPSTATE flag is cleared;
+ *
+ * - the task executes an ordinary syscall; upon return to userland, the
+ *   TIF_FOREIGN_FPSTATE flag will still be cleared, so no FPSIMD state is
+ *   restored;
+ *
+ * - the task executes a syscall which executes some NEON instructions; this is
+ *   preceded by a call to kernel_neon_begin(), which copies the task's FPSIMD
+ *   register contents to memory, clears the fpsimd_last_state per-cpu variable
+ *   and sets the TIF_FOREIGN_FPSTATE flag;
+ *
+ * - the task gets preempted after kernel_neon_end() is called; as we have not
+ *   returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
+ *   whatever is in the FPSIMD registers is not saved to memory, but discarded.
+ */
+static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state);
+
+/*
  * Trapped FP/ASIMD access.
  */
 void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
@@ -71,43 +126,137 @@ void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 
 void fpsimd_thread_switch(struct task_struct *next)
 {
-	/* check if not kernel threads */
-	if (current->mm)
+	/*
+	 * Save the current FPSIMD state to memory, but only if whatever is in
+	 * the registers is in fact the most recent userland FPSIMD state of
+	 * 'current'.
+	 */
+	if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
 		fpsimd_save_state(&current->thread.fpsimd_state);
-	if (next->mm)
-		fpsimd_load_state(&next->thread.fpsimd_state);
+
+	if (next->mm) {
+		/*
+		 * If we are switching to a task whose most recent userland
+		 * FPSIMD state is already in the registers of *this* cpu,
+		 * we can skip loading the state from memory. Otherwise, set
+		 * the TIF_FOREIGN_FPSTATE flag so the state will be loaded
+		 * upon the next return to userland.
+		 */
+		struct fpsimd_state *st = &next->thread.fpsimd_state;
+
+		if (__this_cpu_read(fpsimd_last_state) == st
+		    && st->cpu == smp_processor_id())
+			clear_ti_thread_flag(task_thread_info(next),
+					     TIF_FOREIGN_FPSTATE);
+		else
+			set_ti_thread_flag(task_thread_info(next),
+					   TIF_FOREIGN_FPSTATE);
+	}
 }
 
 void fpsimd_flush_thread(void)
 {
-	preempt_disable();
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
-	fpsimd_load_state(&current->thread.fpsimd_state);
+	set_thread_flag(TIF_FOREIGN_FPSTATE);
+}
+
+/*
+ * Save the userland FPSIMD state of 'current' to memory, but only if the state
+ * currently held in the registers does in fact belong to 'current'
+ */
+void fpsimd_preserve_current_state(void)
+{
+	preempt_disable();
+	if (!test_thread_flag(TIF_FOREIGN_FPSTATE))
+		fpsimd_save_state(&current->thread.fpsimd_state);
+	preempt_enable();
+}
+
+/*
+ * Load the userland FPSIMD state of 'current' from memory, but only if the
+ * FPSIMD state already held in the registers is /not/ the most recent FPSIMD
+ * state of 'current'
+ */
+void fpsimd_restore_current_state(void)
+{
+	preempt_disable();
+	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		struct fpsimd_state *st = &current->thread.fpsimd_state;
+
+		fpsimd_load_state(st);
+		this_cpu_write(fpsimd_last_state, st);
+		st->cpu = smp_processor_id();
+	}
+	preempt_enable();
+}
+
+/*
+ * Load an updated userland FPSIMD state for 'current' from memory and set the
+ * flag that indicates that the FPSIMD register contents are the most recent
+ * FPSIMD state of 'current'
+ */
+void fpsimd_update_current_state(struct fpsimd_state *state)
+{
+	preempt_disable();
+	fpsimd_load_state(state);
+	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		struct fpsimd_state *st = &current->thread.fpsimd_state;
+
+		this_cpu_write(fpsimd_last_state, st);
+		st->cpu = smp_processor_id();
+	}
 	preempt_enable();
 }
 
+/*
+ * Invalidate live CPU copies of task t's FPSIMD state
+ */
+void fpsimd_flush_task_state(struct task_struct *t)
+{
+	t->thread.fpsimd_state.cpu = NR_CPUS;
+}
+
 #ifdef CONFIG_KERNEL_MODE_NEON
 
+static DEFINE_PER_CPU(struct fpsimd_partial_state, hardirq_fpsimdstate);
+static DEFINE_PER_CPU(struct fpsimd_partial_state, softirq_fpsimdstate);
+
 /*
  * Kernel-side NEON support functions
  */
-void kernel_neon_begin(void)
+void kernel_neon_begin_partial(u32 num_regs)
 {
-	/* Avoid using the NEON in interrupt context */
-	BUG_ON(in_interrupt());
-	preempt_disable();
+	if (in_interrupt()) {
+		struct fpsimd_partial_state *s = this_cpu_ptr(
+			in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
 
-	if (current->mm)
-		fpsimd_save_state(&current->thread.fpsimd_state);
+		BUG_ON(num_regs > 32);
+		fpsimd_save_partial_state(s, roundup(num_regs, 2));
+	} else {
+		/*
+		 * Save the userland FPSIMD state if we have one and if we
+		 * haven't done so already. Clear fpsimd_last_state to indicate
+		 * that there is no longer userland FPSIMD state in the
+		 * registers.
+		 */
+		preempt_disable();
+		if (current->mm &&
+		    !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE))
+			fpsimd_save_state(&current->thread.fpsimd_state);
+		this_cpu_write(fpsimd_last_state, NULL);
+	}
 }
-EXPORT_SYMBOL(kernel_neon_begin);
+EXPORT_SYMBOL(kernel_neon_begin_partial);
 
 void kernel_neon_end(void)
 {
-	if (current->mm)
-		fpsimd_load_state(&current->thread.fpsimd_state);
-
-	preempt_enable();
+	if (in_interrupt()) {
+		struct fpsimd_partial_state *s = this_cpu_ptr(
+			in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
+		fpsimd_load_partial_state(s);
+	} else {
+		preempt_enable();
+	}
 }
 EXPORT_SYMBOL(kernel_neon_end);
 
@@ -119,12 +268,12 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
 {
 	switch (cmd) {
 	case CPU_PM_ENTER:
-		if (current->mm)
+		if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
 			fpsimd_save_state(&current->thread.fpsimd_state);
 		break;
 	case CPU_PM_EXIT:
 		if (current->mm)
-			fpsimd_load_state(&current->thread.fpsimd_state);
+			set_thread_flag(TIF_FOREIGN_FPSTATE);
 		break;
 	case CPU_PM_ENTER_FAILED:
 	default:
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 3193bf35dbc8..15c91e25d045 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -215,7 +215,7 @@ void release_thread(struct task_struct *dead_task)
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	fpsimd_save_state(&current->thread.fpsimd_state);
+	fpsimd_preserve_current_state();
 	*dst = *src;
 	return 0;
 }
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 0bf195533088..3e926b9c0641 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -521,6 +521,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 		return ret;
 
 	target->thread.fpsimd_state.user_fpsimd = newstate;
+	fpsimd_flush_task_state(target);
 	return ret;
 }
 
@@ -768,6 +769,7 @@ static int compat_vfp_set(struct task_struct *target,
 		uregs->fpcr = fpscr & VFP_FPSCR_CTRL_MASK;
 	}
 
+	fpsimd_flush_task_state(target);
 	return ret;
 }
 
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index e3cf09626245..bbc1aad21ce6 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -51,7 +51,7 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 	int err;
 
 	/* dump the hardware registers to the fpsimd_state structure */
-	fpsimd_save_state(fpsimd);
+	fpsimd_preserve_current_state();
 
 	/* copy the FP and status/control registers */
 	err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs));
@@ -86,11 +86,8 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
 
 	/* load the hardware registers from the fpsimd_state structure */
-	if (!err) {
-		preempt_disable();
-		fpsimd_load_state(&fpsimd);
-		preempt_enable();
-	}
+	if (!err)
+		fpsimd_update_current_state(&fpsimd);
 
 	return err ? -EFAULT : 0;
 }
@@ -423,4 +420,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 	}
+
+	if (thread_flags & _TIF_FOREIGN_FPSTATE)
+		fpsimd_restore_current_state();
+
 }
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index e51bbe79f5b5..02de43260332 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -219,7 +219,7 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
 	 * Note that this also saves V16-31, which aren't visible
 	 * in AArch32.
 	 */
-	fpsimd_save_state(fpsimd);
+	fpsimd_preserve_current_state();
 
 	/* Place structure header on the stack */
 	__put_user_error(magic, &frame->magic, err);
@@ -282,11 +282,8 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame)
 	 * We don't need to touch the exception register, so
 	 * reload the hardware state.
 	 */
-	if (!err) {
-		preempt_disable();
-		fpsimd_load_state(&fpsimd);
-		preempt_enable();
-	}
+	if (!err)
+		fpsimd_update_current_state(&fpsimd);
 
 	return err ? -EFAULT : 0;
 }
diff --git a/crypto/Kconfig b/crypto/Kconfig
index bf8148e74e73..a1eba1845367 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -179,6 +179,10 @@ config CRYPTO_ABLK_HELPER_X86
 	depends on X86
 	select CRYPTO_CRYPTD
 
+config CRYPTO_ABLK_HELPER
+	tristate
+	select CRYPTO_CRYPTD
+
 config CRYPTO_GLUE_HELPER_X86
 	tristate
 	depends on X86
diff --git a/crypto/Makefile b/crypto/Makefile
index a8e9b0fefbe9..5d0b869b173f 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -101,3 +101,4 @@ obj-$(CONFIG_CRYPTO_USER_API_SKCIPHER) += algif_skcipher.o
 obj-$(CONFIG_XOR_BLOCKS) += xor.o
 obj-$(CONFIG_ASYNC_CORE) += async_tx/
 obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += asymmetric_keys/
+obj-$(CONFIG_CRYPTO_ABLK_HELPER) += ablk_helper.o
diff --git a/crypto/ablk_helper.c b/crypto/ablk_helper.c
new file mode 100644
index 000000000000..62568b1fc885
--- /dev/null
+++ b/crypto/ablk_helper.c
@@ -0,0 +1,150 @@
+/*
+ * Shared async block cipher helpers
+ *
+ * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * Based on aesni-intel_glue.c by:
+ *  Copyright (C) 2008, Intel Corp.
+ *    Author: Huang Ying <ying.huang@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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <crypto/algapi.h>
+#include <crypto/cryptd.h>
+#include <crypto/ablk_helper.h>
+#include <asm/simd.h>
+
+int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+		 unsigned int key_len)
+{
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct crypto_ablkcipher *child = &ctx->cryptd_tfm->base;
+	int err;
+
+	crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(tfm)
+				    & CRYPTO_TFM_REQ_MASK);
+	err = crypto_ablkcipher_setkey(child, key, key_len);
+	crypto_ablkcipher_set_flags(tfm, crypto_ablkcipher_get_flags(child)
+				    & CRYPTO_TFM_RES_MASK);
+	return err;
+}
+EXPORT_SYMBOL_GPL(ablk_set_key);
+
+int __ablk_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct blkcipher_desc desc;
+
+	desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+	desc.info = req->info;
+	desc.flags = 0;
+
+	return crypto_blkcipher_crt(desc.tfm)->encrypt(
+		&desc, req->dst, req->src, req->nbytes);
+}
+EXPORT_SYMBOL_GPL(__ablk_encrypt);
+
+int ablk_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+	if (!may_use_simd()) {
+		struct ablkcipher_request *cryptd_req =
+			ablkcipher_request_ctx(req);
+
+		memcpy(cryptd_req, req, sizeof(*req));
+		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+		return crypto_ablkcipher_encrypt(cryptd_req);
+	} else {
+		return __ablk_encrypt(req);
+	}
+}
+EXPORT_SYMBOL_GPL(ablk_encrypt);
+
+int ablk_decrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+	if (!may_use_simd()) {
+		struct ablkcipher_request *cryptd_req =
+			ablkcipher_request_ctx(req);
+
+		memcpy(cryptd_req, req, sizeof(*req));
+		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+		return crypto_ablkcipher_decrypt(cryptd_req);
+	} else {
+		struct blkcipher_desc desc;
+
+		desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+		desc.info = req->info;
+		desc.flags = 0;
+
+		return crypto_blkcipher_crt(desc.tfm)->decrypt(
+			&desc, req->dst, req->src, req->nbytes);
+	}
+}
+EXPORT_SYMBOL_GPL(ablk_decrypt);
+
+void ablk_exit(struct crypto_tfm *tfm)
+{
+	struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	cryptd_free_ablkcipher(ctx->cryptd_tfm);
+}
+EXPORT_SYMBOL_GPL(ablk_exit);
+
+int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name)
+{
+	struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct cryptd_ablkcipher *cryptd_tfm;
+
+	cryptd_tfm = cryptd_alloc_ablkcipher(drv_name, 0, 0);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+
+	ctx->cryptd_tfm = cryptd_tfm;
+	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
+		crypto_ablkcipher_reqsize(&cryptd_tfm->base);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ablk_init_common);
+
+int ablk_init(struct crypto_tfm *tfm)
+{
+	char drv_name[CRYPTO_MAX_ALG_NAME];
+
+	snprintf(drv_name, sizeof(drv_name), "__driver-%s",
+					crypto_tfm_alg_driver_name(tfm));
+
+	return ablk_init_common(tfm, drv_name);
+}
+EXPORT_SYMBOL_GPL(ablk_init);
+
+MODULE_LICENSE("GPL");
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index a79e7e9ab86e..0122bec38564 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -70,14 +70,12 @@ static inline u8 *blkcipher_get_spot(u8 *start, unsigned int len)
 	return max(start, end_page);
 }
 
-static inline unsigned int blkcipher_done_slow(struct crypto_blkcipher *tfm,
-					       struct blkcipher_walk *walk,
+static inline unsigned int blkcipher_done_slow(struct blkcipher_walk *walk,
 					       unsigned int bsize)
 {
 	u8 *addr;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
 
-	addr = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+	addr = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
 	addr = blkcipher_get_spot(addr, bsize);
 	scatterwalk_copychunks(addr, &walk->out, bsize, 1);
 	return bsize;
@@ -105,7 +103,6 @@ static inline unsigned int blkcipher_done_fast(struct blkcipher_walk *walk,
 int blkcipher_walk_done(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk, int err)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
 	unsigned int nbytes = 0;
 
 	if (likely(err >= 0)) {
@@ -117,7 +114,7 @@ int blkcipher_walk_done(struct blkcipher_desc *desc,
 			err = -EINVAL;
 			goto err;
 		} else
-			n = blkcipher_done_slow(tfm, walk, n);
+			n = blkcipher_done_slow(walk, n);
 
 		nbytes = walk->total - n;
 		err = 0;
@@ -136,7 +133,7 @@ err:
 	}
 
 	if (walk->iv != desc->info)
-		memcpy(desc->info, walk->iv, crypto_blkcipher_ivsize(tfm));
+		memcpy(desc->info, walk->iv, walk->ivsize);
 	if (walk->buffer != walk->page)
 		kfree(walk->buffer);
 	if (walk->page)
@@ -226,22 +223,20 @@ static inline int blkcipher_next_fast(struct blkcipher_desc *desc,
 static int blkcipher_walk_next(struct blkcipher_desc *desc,
 			       struct blkcipher_walk *walk)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
 	unsigned int bsize;
 	unsigned int n;
 	int err;
 
 	n = walk->total;
-	if (unlikely(n < crypto_blkcipher_blocksize(tfm))) {
+	if (unlikely(n < walk->cipher_blocksize)) {
 		desc->flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
 		return blkcipher_walk_done(desc, walk, -EINVAL);
 	}
 
 	walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
 			 BLKCIPHER_WALK_DIFF);
-	if (!scatterwalk_aligned(&walk->in, alignmask) ||
-	    !scatterwalk_aligned(&walk->out, alignmask)) {
+	if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
+	    !scatterwalk_aligned(&walk->out, walk->alignmask)) {
 		walk->flags |= BLKCIPHER_WALK_COPY;
 		if (!walk->page) {
 			walk->page = (void *)__get_free_page(GFP_ATOMIC);
@@ -250,12 +245,12 @@ static int blkcipher_walk_next(struct blkcipher_desc *desc,
 		}
 	}
 
-	bsize = min(walk->blocksize, n);
+	bsize = min(walk->walk_blocksize, n);
 	n = scatterwalk_clamp(&walk->in, n);
 	n = scatterwalk_clamp(&walk->out, n);
 
 	if (unlikely(n < bsize)) {
-		err = blkcipher_next_slow(desc, walk, bsize, alignmask);
+		err = blkcipher_next_slow(desc, walk, bsize, walk->alignmask);
 		goto set_phys_lowmem;
 	}
 
@@ -277,28 +272,26 @@ set_phys_lowmem:
 	return err;
 }
 
-static inline int blkcipher_copy_iv(struct blkcipher_walk *walk,
-				    struct crypto_blkcipher *tfm,
-				    unsigned int alignmask)
+static inline int blkcipher_copy_iv(struct blkcipher_walk *walk)
 {
-	unsigned bs = walk->blocksize;
-	unsigned int ivsize = crypto_blkcipher_ivsize(tfm);
-	unsigned aligned_bs = ALIGN(bs, alignmask + 1);
-	unsigned int size = aligned_bs * 2 + ivsize + max(aligned_bs, ivsize) -
-			    (alignmask + 1);
+	unsigned bs = walk->walk_blocksize;
+	unsigned aligned_bs = ALIGN(bs, walk->alignmask + 1);
+	unsigned int size = aligned_bs * 2 +
+			    walk->ivsize + max(aligned_bs, walk->ivsize) -
+			    (walk->alignmask + 1);
 	u8 *iv;
 
-	size += alignmask & ~(crypto_tfm_ctx_alignment() - 1);
+	size += walk->alignmask & ~(crypto_tfm_ctx_alignment() - 1);
 	walk->buffer = kmalloc(size, GFP_ATOMIC);
 	if (!walk->buffer)
 		return -ENOMEM;
 
-	iv = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+	iv = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
 	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
 	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
-	iv = blkcipher_get_spot(iv, ivsize);
+	iv = blkcipher_get_spot(iv, walk->ivsize);
 
-	walk->iv = memcpy(iv, walk->iv, ivsize);
+	walk->iv = memcpy(iv, walk->iv, walk->ivsize);
 	return 0;
 }
 
@@ -306,7 +299,10 @@ int blkcipher_walk_virt(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk)
 {
 	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->cipher_blocksize = walk->walk_blocksize;
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_virt);
@@ -315,7 +311,10 @@ int blkcipher_walk_phys(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk)
 {
 	walk->flags |= BLKCIPHER_WALK_PHYS;
-	walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->cipher_blocksize = walk->walk_blocksize;
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
@@ -323,9 +322,6 @@ EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
 static int blkcipher_walk_first(struct blkcipher_desc *desc,
 				struct blkcipher_walk *walk)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
-
 	if (WARN_ON_ONCE(in_irq()))
 		return -EDEADLK;
 
@@ -335,8 +331,8 @@ static int blkcipher_walk_first(struct blkcipher_desc *desc,
 
 	walk->buffer = NULL;
 	walk->iv = desc->info;
-	if (unlikely(((unsigned long)walk->iv & alignmask))) {
-		int err = blkcipher_copy_iv(walk, tfm, alignmask);
+	if (unlikely(((unsigned long)walk->iv & walk->alignmask))) {
+		int err = blkcipher_copy_iv(walk);
 		if (err)
 			return err;
 	}
@@ -353,11 +349,28 @@ int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
 			      unsigned int blocksize)
 {
 	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->blocksize = blocksize;
+	walk->walk_blocksize = blocksize;
+	walk->cipher_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_virt_block);
 
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+				   struct blkcipher_walk *walk,
+				   struct crypto_aead *tfm,
+				   unsigned int blocksize)
+{
+	walk->flags &= ~BLKCIPHER_WALK_PHYS;
+	walk->walk_blocksize = blocksize;
+	walk->cipher_blocksize = crypto_aead_blocksize(tfm);
+	walk->ivsize = crypto_aead_ivsize(tfm);
+	walk->alignmask = crypto_aead_alignmask(tfm);
+	return blkcipher_walk_first(desc, walk);
+}
+EXPORT_SYMBOL_GPL(blkcipher_aead_walk_virt_block);
+
 static int setkey_unaligned(struct crypto_tfm *tfm, const u8 *key,
 			    unsigned int keylen)
 {
diff --git a/include/asm-generic/simd.h b/include/asm-generic/simd.h
new file mode 100644
index 000000000000..f57eb7b5c23b
--- /dev/null
+++ b/include/asm-generic/simd.h
@@ -0,0 +1,14 @@
+
+#include <linux/hardirq.h>
+
+/*
+ * may_use_simd - whether it is allowable at this time to issue SIMD
+ *                instructions or access the SIMD register file
+ *
+ * As architectures typically don't preserve the SIMD register file when
+ * taking an interrupt, !in_interrupt() should be a reasonable default.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+	return !in_interrupt();
+}
diff --git a/include/crypto/ablk_helper.h b/include/crypto/ablk_helper.h
new file mode 100644
index 000000000000..4f93df50c23e
--- /dev/null
+++ b/include/crypto/ablk_helper.h
@@ -0,0 +1,31 @@
+/*
+ * Shared async block cipher helpers
+ */
+
+#ifndef _CRYPTO_ABLK_HELPER_H
+#define _CRYPTO_ABLK_HELPER_H
+
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <crypto/cryptd.h>
+
+struct async_helper_ctx {
+	struct cryptd_ablkcipher *cryptd_tfm;
+};
+
+extern int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+			unsigned int key_len);
+
+extern int __ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_decrypt(struct ablkcipher_request *req);
+
+extern void ablk_exit(struct crypto_tfm *tfm);
+
+extern int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name);
+
+extern int ablk_init(struct crypto_tfm *tfm);
+
+#endif /* _CRYPTO_ABLK_HELPER_H */
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 418d270e1806..063f8ef49301 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -100,9 +100,12 @@ struct blkcipher_walk {
 	void *page;
 	u8 *buffer;
 	u8 *iv;
+	unsigned int ivsize;
 
 	int flags;
-	unsigned int blocksize;
+	unsigned int walk_blocksize;
+	unsigned int cipher_blocksize;
+	unsigned int alignmask;
 };
 
 struct ablkcipher_walk {
@@ -192,6 +195,10 @@ int blkcipher_walk_phys(struct blkcipher_desc *desc,
 int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
 			      struct blkcipher_walk *walk,
 			      unsigned int blocksize);
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+				   struct blkcipher_walk *walk,
+				   struct crypto_aead *tfm,
+				   unsigned int blocksize);
 
 int ablkcipher_walk_done(struct ablkcipher_request *req,
 			 struct ablkcipher_walk *walk, int err);