Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "API:
   - hwrng core now credits for low-quality RNG devices.

  Algorithms:
   - Optimisations for neon aes on arm/arm64.
   - Add accelerated crc32_be on arm64.
   - Add ffdheXYZ(dh) templates.
   - Disallow hmac keys < 112 bits in FIPS mode.
   - Add AVX assembly implementation for sm3 on x86.

  Drivers:
   - Add missing local_bh_disable calls for crypto_engine callback.
   - Ensure BH is disabled in crypto_engine callback path.
   - Fix zero length DMA mappings in ccree.
   - Add synchronization between mailbox accesses in octeontx2.
   - Add Xilinx SHA3 driver.
   - Add support for the TDES IP available on sama7g5 SoC in atmel"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (137 commits)
  crypto: xilinx - Turn SHA into a tristate and allow COMPILE_TEST
  MAINTAINERS: update HPRE/SEC2/TRNG driver maintainers list
  crypto: dh - Remove the unused function dh_safe_prime_dh_alg()
  hwrng: nomadik - Change clk_disable to clk_disable_unprepare
  crypto: arm64 - cleanup comments
  crypto: qat - fix initialization of pfvf rts_map_msg structures
  crypto: qat - fix initialization of pfvf cap_msg structures
  crypto: qat - remove unneeded assignment
  crypto: qat - disable registration of algorithms
  crypto: hisilicon/qm - fix memset during queues clearing
  crypto: xilinx: prevent probing on non-xilinx hardware
  crypto: marvell/octeontx - Use swap() instead of open coding it
  crypto: ccree - Fix use after free in cc_cipher_exit()
  crypto: ccp - ccp_dmaengine_unregister release dma channels
  crypto: octeontx2 - fix missing unlock
  hwrng: cavium - fix NULL but dereferenced coccicheck error
  crypto: cavium/nitrox - don't cast parameter in bit operations
  crypto: vmx - add missing dependencies
  MAINTAINERS: Add maintainer for Xilinx ZynqMP SHA3 driver
  crypto: xilinx - Add Xilinx SHA3 driver
  ...

2 files changed, 102 insertions, 31 deletions

diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32.S
index 0f9e10ecda23..8340dccff46f 100644
--- a/arch/arm64/lib/crc32.S
+++ b/arch/arm64/lib/crc32.S
@@ -11,7 +11,44 @@
 
 	.arch		armv8-a+crc
 
-	.macro		__crc32, c
+	.macro		byteorder, reg, be
+	.if		\be
+CPU_LE( rev		\reg, \reg	)
+	.else
+CPU_BE( rev		\reg, \reg	)
+	.endif
+	.endm
+
+	.macro		byteorder16, reg, be
+	.if		\be
+CPU_LE( rev16		\reg, \reg	)
+	.else
+CPU_BE( rev16		\reg, \reg	)
+	.endif
+	.endm
+
+	.macro		bitorder, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	.endif
+	.endm
+
+	.macro		bitorder16, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	lsr		\reg, \reg, #16
+	.endif
+	.endm
+
+	.macro		bitorder8, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	lsr		\reg, \reg, #24
+	.endif
+	.endm
+
+	.macro		__crc32, c, be=0
+	bitorder	w0, \be
 	cmp		x2, #16
 	b.lt		8f			// less than 16 bytes
 
@@ -24,10 +61,14 @@
 	add		x8, x8, x1
 	add		x1, x1, x7
 	ldp		x5, x6, [x8]
-CPU_BE(	rev		x3, x3		)
-CPU_BE(	rev		x4, x4		)
-CPU_BE(	rev		x5, x5		)
-CPU_BE(	rev		x6, x6		)
+	byteorder	x3, \be
+	byteorder	x4, \be
+	byteorder	x5, \be
+	byteorder	x6, \be
+	bitorder	x3, \be
+	bitorder	x4, \be
+	bitorder	x5, \be
+	bitorder	x6, \be
 
 	tst		x7, #8
 	crc32\c\()x	w8, w0, x3
@@ -55,33 +96,43 @@ CPU_BE(	rev		x6, x6		)
 32:	ldp		x3, x4, [x1], #32
 	sub		x2, x2, #32
 	ldp		x5, x6, [x1, #-16]
-CPU_BE(	rev		x3, x3		)
-CPU_BE(	rev		x4, x4		)
-CPU_BE(	rev		x5, x5		)
-CPU_BE(	rev		x6, x6		)
+	byteorder	x3, \be
+	byteorder	x4, \be
+	byteorder	x5, \be
+	byteorder	x6, \be
+	bitorder	x3, \be
+	bitorder	x4, \be
+	bitorder	x5, \be
+	bitorder	x6, \be
 	crc32\c\()x	w0, w0, x3
 	crc32\c\()x	w0, w0, x4
 	crc32\c\()x	w0, w0, x5
 	crc32\c\()x	w0, w0, x6
 	cbnz		x2, 32b
-0:	ret
+0:	bitorder	w0, \be
+	ret
 
 8:	tbz		x2, #3, 4f
 	ldr		x3, [x1], #8
-CPU_BE(	rev		x3, x3		)
+	byteorder	x3, \be
+	bitorder	x3, \be
 	crc32\c\()x	w0, w0, x3
 4:	tbz		x2, #2, 2f
 	ldr		w3, [x1], #4
-CPU_BE(	rev		w3, w3		)
+	byteorder	w3, \be
+	bitorder	w3, \be
 	crc32\c\()w	w0, w0, w3
 2:	tbz		x2, #1, 1f
 	ldrh		w3, [x1], #2
-CPU_BE(	rev16		w3, w3		)
+	byteorder16	w3, \be
+	bitorder16	w3, \be
 	crc32\c\()h	w0, w0, w3
 1:	tbz		x2, #0, 0f
 	ldrb		w3, [x1]
+	bitorder8	w3, \be
 	crc32\c\()b	w0, w0, w3
-0:	ret
+0:	bitorder	w0, \be
+	ret
 	.endm
 
 	.align		5
@@ -99,3 +150,11 @@ alternative_if_not ARM64_HAS_CRC32
 alternative_else_nop_endif
 	__crc32		c
 SYM_FUNC_END(__crc32c_le)
+
+	.align		5
+SYM_FUNC_START(crc32_be)
+alternative_if_not ARM64_HAS_CRC32
+	b		crc32_be_base
+alternative_else_nop_endif
+	__crc32		be=1
+SYM_FUNC_END(crc32_be)
diff --git a/arch/arm64/lib/xor-neon.c b/arch/arm64/lib/xor-neon.c
index d189cf4e70ea..96b171995d19 100644
--- a/arch/arm64/lib/xor-neon.c
+++ b/arch/arm64/lib/xor-neon.c
@@ -10,8 +10,8 @@
 #include <linux/module.h>
 #include <asm/neon-intrinsics.h>
 
-void xor_arm64_neon_2(unsigned long bytes, unsigned long *p1,
-	unsigned long *p2)
+void xor_arm64_neon_2(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -37,8 +37,9 @@ void xor_arm64_neon_2(unsigned long bytes, unsigned long *p1,
 	} while (--lines > 0);
 }
 
-void xor_arm64_neon_3(unsigned long bytes, unsigned long *p1,
-	unsigned long *p2, unsigned long *p3)
+void xor_arm64_neon_3(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -72,8 +73,10 @@ void xor_arm64_neon_3(unsigned long bytes, unsigned long *p1,
 	} while (--lines > 0);
 }
 
-void xor_arm64_neon_4(unsigned long bytes, unsigned long *p1,
-	unsigned long *p2, unsigned long *p3, unsigned long *p4)
+void xor_arm64_neon_4(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -115,9 +118,11 @@ void xor_arm64_neon_4(unsigned long bytes, unsigned long *p1,
 	} while (--lines > 0);
 }
 
-void xor_arm64_neon_5(unsigned long bytes, unsigned long *p1,
-	unsigned long *p2, unsigned long *p3,
-	unsigned long *p4, unsigned long *p5)
+void xor_arm64_neon_5(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4,
+	const unsigned long * __restrict p5)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -186,8 +191,10 @@ static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r)
 	return res;
 }
 
-static void xor_arm64_eor3_3(unsigned long bytes, unsigned long *p1,
-			     unsigned long *p2, unsigned long *p3)
+static void xor_arm64_eor3_3(unsigned long bytes,
+	unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -219,9 +226,11 @@ static void xor_arm64_eor3_3(unsigned long bytes, unsigned long *p1,
 	} while (--lines > 0);
 }
 
-static void xor_arm64_eor3_4(unsigned long bytes, unsigned long *p1,
-			     unsigned long *p2, unsigned long *p3,
-			     unsigned long *p4)
+static void xor_arm64_eor3_4(unsigned long bytes,
+	unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -261,9 +270,12 @@ static void xor_arm64_eor3_4(unsigned long bytes, unsigned long *p1,
 	} while (--lines > 0);
 }
 
-static void xor_arm64_eor3_5(unsigned long bytes, unsigned long *p1,
-			     unsigned long *p2, unsigned long *p3,
-			     unsigned long *p4, unsigned long *p5)
+static void xor_arm64_eor3_5(unsigned long bytes,
+	unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4,
+	const unsigned long * __restrict p5)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;