Merge tag 'for-3.16' of git://git.linaro.org/people/ard.biesheuvel/linux-arm into upstream

FPSIMD register bank context switching and crypto algorithms
optimisations for arm64 from Ard Biesheuvel.

* tag 'for-3.16' of git://git.linaro.org/people/ard.biesheuvel/linux-arm:
  arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions
  arm64: pull in <asm/simd.h> from asm-generic
  arm64/crypto: AES in CCM mode using ARMv8 Crypto Extensions
  arm64/crypto: AES using ARMv8 Crypto Extensions
  arm64/crypto: GHASH secure hash using ARMv8 Crypto Extensions
  arm64/crypto: SHA-224/SHA-256 using ARMv8 Crypto Extensions
  arm64/crypto: SHA-1 using ARMv8 Crypto Extensions
  arm64: add support for kernel mode NEON in interrupt context
  arm64: defer reloading a task's FPSIMD state to userland resume
  arm64: add abstractions for FPSIMD state manipulation
  asm-generic: allow generic unaligned access if the arch supports it

Conflicts:
	arch/arm64/include/asm/thread_info.h

5 files changed, 67 insertions, 2 deletions

diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 83f71b3004a8..42c7eecd2bb6 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -40,6 +40,7 @@ generic-y += segment.h
 generic-y += sembuf.h
 generic-y += serial.h
 generic-y += shmbuf.h
+generic-y += simd.h
 generic-y += sizes.h
 generic-y += socket.h
 generic-y += sockios.h
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
index b0cc58a97780..13ce4cc18e26 100644
--- a/arch/arm64/include/asm/neon.h
+++ b/arch/arm64/include/asm/neon.h
@@ -8,7 +8,11 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/types.h>
+
 #define cpu_has_neon()		(1)
 
-void kernel_neon_begin(void);
+#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 0a8b2a97a32e..9c086c63f911 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -103,6 +103,7 @@ 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
@@ -118,6 +119,7 @@ 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)
@@ -125,7 +127,7 @@ 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)