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

Pull crypto updates from Herbert Xu:
 "API:

   - crypto_destroy_tfm now ignores errors as well as NULL pointers

  Algorithms:

   - Add explicit curve IDs in ECDH algorithm names

   - Add NIST P384 curve parameters

   - Add ECDSA

  Drivers:

   - Add support for Green Sardine in ccp

   - Add ecdh/curve25519 to hisilicon/hpre

   - Add support for AM64 in sa2ul"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (184 commits)
  fsverity: relax build time dependency on CRYPTO_SHA256
  fscrypt: relax Kconfig dependencies for crypto API algorithms
  crypto: camellia - drop duplicate "depends on CRYPTO"
  crypto: s5p-sss - consistently use local 'dev' variable in probe()
  crypto: s5p-sss - remove unneeded local variable initialization
  crypto: s5p-sss - simplify getting of_device_id match data
  ccp: ccp - add support for Green Sardine
  crypto: ccp - Make ccp_dev_suspend and ccp_dev_resume void functions
  crypto: octeontx2 - add support for OcteonTX2 98xx CPT block.
  crypto: chelsio/chcr - Remove useless MODULE_VERSION
  crypto: ux500/cryp - Remove duplicate argument
  crypto: chelsio - remove unused function
  crypto: sa2ul - Add support for AM64
  crypto: sa2ul - Support for per channel coherency
  dt-bindings: crypto: ti,sa2ul: Add new compatible for AM64
  crypto: hisilicon - enable new error types for QM
  crypto: hisilicon - add new error type for SEC
  crypto: hisilicon - support new error types for ZIP
  crypto: hisilicon - dynamic configuration 'err_info'
  crypto: doc - fix kernel-doc notation in chacha.c and af_alg.c
  ...

6 files changed, 48 insertions, 66 deletions

diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S
index 472e56d09eea..1da3f41359aa 100644
--- a/arch/arm/crypto/aes-cipher-core.S
+++ b/arch/arm/crypto/aes-cipher-core.S
@@ -99,28 +99,6 @@
 	__hround	\out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op, \oldcpsr
 	.endm
 
-	.macro		__rev, out, in
-	.if		__LINUX_ARM_ARCH__ < 6
-	lsl		t0, \in, #24
-	and		t1, \in, #0xff00
-	and		t2, \in, #0xff0000
-	orr		\out, t0, \in, lsr #24
-	orr		\out, \out, t1, lsl #8
-	orr		\out, \out, t2, lsr #8
-	.else
-	rev		\out, \in
-	.endif
-	.endm
-
-	.macro		__adrl, out, sym, c
-	.if		__LINUX_ARM_ARCH__ < 7
-	ldr\c		\out, =\sym
-	.else
-	movw\c		\out, #:lower16:\sym
-	movt\c		\out, #:upper16:\sym
-	.endif
-	.endm
-
 	.macro		do_crypt, round, ttab, ltab, bsz
 	push		{r3-r11, lr}
 
@@ -133,10 +111,10 @@
 	ldr		r7, [in, #12]
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	__rev		r4, r4
-	__rev		r5, r5
-	__rev		r6, r6
-	__rev		r7, r7
+	rev_l		r4, t0
+	rev_l		r5, t0
+	rev_l		r6, t0
+	rev_l		r7, t0
 #endif
 
 	eor		r4, r4, r8
@@ -144,7 +122,7 @@
 	eor		r6, r6, r10
 	eor		r7, r7, r11
 
-	__adrl		ttab, \ttab
+	mov_l		ttab, \ttab
 	/*
 	 * Disable interrupts and prefetch the 1024-byte 'ft' or 'it' table into
 	 * L1 cache, assuming cacheline size >= 32.  This is a hardening measure
@@ -180,7 +158,7 @@
 2:	.ifb		\ltab
 	add		ttab, ttab, #1
 	.else
-	__adrl		ttab, \ltab
+	mov_l		ttab, \ltab
 	// Prefetch inverse S-box for final round; see explanation above
 	.set		i, 0
 	.rept		256 / 64
@@ -194,10 +172,10 @@
 	\round		r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b, rounds
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	__rev		r4, r4
-	__rev		r5, r5
-	__rev		r6, r6
-	__rev		r7, r7
+	rev_l		r4, t0
+	rev_l		r5, t0
+	rev_l		r6, t0
+	rev_l		r7, t0
 #endif
 
 	ldr		out, [sp]
diff --git a/arch/arm/crypto/blake2b-neon-glue.c b/arch/arm/crypto/blake2b-neon-glue.c
index 34d73200e7fa..4b59d027ba4a 100644
--- a/arch/arm/crypto/blake2b-neon-glue.c
+++ b/arch/arm/crypto/blake2b-neon-glue.c
@@ -85,8 +85,8 @@ static int __init blake2b_neon_mod_init(void)
 
 static void __exit blake2b_neon_mod_exit(void)
 {
-	return crypto_unregister_shashes(blake2b_neon_algs,
-					 ARRAY_SIZE(blake2b_neon_algs));
+	crypto_unregister_shashes(blake2b_neon_algs,
+				  ARRAY_SIZE(blake2b_neon_algs));
 }
 
 module_init(blake2b_neon_mod_init);
diff --git a/arch/arm/crypto/blake2s-core.S b/arch/arm/crypto/blake2s-core.S
index bed897e9a181..86345751bbf3 100644
--- a/arch/arm/crypto/blake2s-core.S
+++ b/arch/arm/crypto/blake2s-core.S
@@ -8,6 +8,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 	// Registers used to hold message words temporarily.  There aren't
 	// enough ARM registers to hold the whole message block, so we have to
@@ -38,6 +39,23 @@
 #endif
 .endm
 
+.macro _le32_bswap	a, tmp
+#ifdef __ARMEB__
+	rev_l		\a, \tmp
+#endif
+.endm
+
+.macro _le32_bswap_8x	a, b, c, d, e, f, g, h,  tmp
+	_le32_bswap	\a, \tmp
+	_le32_bswap	\b, \tmp
+	_le32_bswap	\c, \tmp
+	_le32_bswap	\d, \tmp
+	_le32_bswap	\e, \tmp
+	_le32_bswap	\f, \tmp
+	_le32_bswap	\g, \tmp
+	_le32_bswap	\h, \tmp
+.endm
+
 // Execute a quarter-round of BLAKE2s by mixing two columns or two diagonals.
 // (a0, b0, c0, d0) and (a1, b1, c1, d1) give the registers containing the two
 // columns/diagonals.  s0-s1 are the word offsets to the message words the first
@@ -180,8 +198,10 @@ ENTRY(blake2s_compress_arch)
 	tst		r1, #3
 	bne		.Lcopy_block_misaligned
 	ldmia		r1!, {r2-r9}
+	_le32_bswap_8x	r2, r3, r4, r5, r6, r7, r8, r9,  r14
 	stmia		r12!, {r2-r9}
 	ldmia		r1!, {r2-r9}
+	_le32_bswap_8x	r2, r3, r4, r5, r6, r7, r8, r9,  r14
 	stmia		r12, {r2-r9}
 .Lcopy_block_done:
 	str		r1, [sp, #68]		// Update message pointer
@@ -268,6 +288,7 @@ ENTRY(blake2s_compress_arch)
 1:
 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 	ldr		r3, [r1], #4
+	_le32_bswap	r3, r4
 #else
 	ldrb		r3, [r1, #0]
 	ldrb		r4, [r1, #1]
diff --git a/arch/arm/crypto/chacha-scalar-core.S b/arch/arm/crypto/chacha-scalar-core.S
index 2985b80a45b5..083fe1ab96d0 100644
--- a/arch/arm/crypto/chacha-scalar-core.S
+++ b/arch/arm/crypto/chacha-scalar-core.S
@@ -41,32 +41,15 @@
 	X14	.req	r12
 	X15	.req	r14
 
-.macro __rev		out, in,  t0, t1, t2
-.if __LINUX_ARM_ARCH__ >= 6
-	rev		\out, \in
-.else
-	lsl		\t0, \in, #24
-	and		\t1, \in, #0xff00
-	and		\t2, \in, #0xff0000
-	orr		\out, \t0, \in, lsr #24
-	orr		\out, \out, \t1, lsl #8
-	orr		\out, \out, \t2, lsr #8
-.endif
-.endm
-
-.macro _le32_bswap	x,  t0, t1, t2
+.macro _le32_bswap_4x	a, b, c, d,  tmp
 #ifdef __ARMEB__
-	__rev		\x, \x,  \t0, \t1, \t2
+	rev_l		\a,  \tmp
+	rev_l		\b,  \tmp
+	rev_l		\c,  \tmp
+	rev_l		\d,  \tmp
 #endif
 .endm
 
-.macro _le32_bswap_4x	a, b, c, d,  t0, t1, t2
-	_le32_bswap	\a,  \t0, \t1, \t2
-	_le32_bswap	\b,  \t0, \t1, \t2
-	_le32_bswap	\c,  \t0, \t1, \t2
-	_le32_bswap	\d,  \t0, \t1, \t2
-.endm
-
 .macro __ldrd		a, b, src, offset
 #if __LINUX_ARM_ARCH__ >= 6
 	ldrd		\a, \b, [\src, #\offset]
@@ -200,7 +183,7 @@
 	add		X1, X1, r9
 	add		X2, X2, r10
 	add		X3, X3, r11
-	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
+	_le32_bswap_4x	X0, X1, X2, X3,  r8
 	ldmia		r12!, {r8-r11}
 	eor		X0, X0, r8
 	eor		X1, X1, r9
@@ -216,7 +199,7 @@
 	ldmia		r12!, {X0-X3}
 	add		X6, r10, X6, ror #brot
 	add		X7, r11, X7, ror #brot
-	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
+	_le32_bswap_4x	X4, X5, X6, X7,  r8
 	eor		X4, X4, X0
 	eor		X5, X5, X1
 	eor		X6, X6, X2
@@ -231,7 +214,7 @@
 	add		r1, r1, r9		// x9
 	add		r6, r6, r10		// x10
 	add		r7, r7, r11		// x11
-	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
+	_le32_bswap_4x	r0, r1, r6, r7,  r8
 	ldmia		r12!, {r8-r11}
 	eor		r0, r0, r8		// x8
 	eor		r1, r1, r9		// x9
@@ -245,7 +228,7 @@
 	add		r3, r9, r3, ror #drot	// x13
 	add		r4, r10, r4, ror #drot	// x14
 	add		r5, r11, r5, ror #drot	// x15
-	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
+	_le32_bswap_4x	r2, r3, r4, r5,  r9
 	  ldr		r9, [sp, #72]		// load LEN
 	eor		r2, r2, r0		// x12
 	eor		r3, r3, r1		// x13
@@ -301,7 +284,7 @@
 	add		X1, X1, r9
 	add		X2, X2, r10
 	add		X3, X3, r11
-	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
+	_le32_bswap_4x	X0, X1, X2, X3,  r8
 	stmia		r14!, {X0-X3}
 
 	// Save keystream for x4-x7
@@ -311,7 +294,7 @@
 	add		X5, r9, X5, ror #brot
 	add		X6, r10, X6, ror #brot
 	add		X7, r11, X7, ror #brot
-	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
+	_le32_bswap_4x	X4, X5, X6, X7,  r8
 	  add		r8, sp, #64
 	stmia		r14!, {X4-X7}
 
@@ -323,7 +306,7 @@
 	add		r1, r1, r9		// x9
 	add		r6, r6, r10		// x10
 	add		r7, r7, r11		// x11
-	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
+	_le32_bswap_4x	r0, r1, r6, r7,  r8
 	stmia		r14!, {r0,r1,r6,r7}
 	__ldrd		r8, r9, sp, 144
 	__ldrd		r10, r11, sp, 152
@@ -331,7 +314,7 @@
 	add		r3, r9, r3, ror #drot	// x13
 	add		r4, r10, r4, ror #drot	// x14
 	add		r5, r11, r5, ror #drot	// x15
-	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
+	_le32_bswap_4x	r2, r3, r4, r5,  r9
 	stmia		r14, {r2-r5}
 
 	// Stack: ks0-ks15 unused0-unused7 x0-x15 OUT IN LEN
diff --git a/arch/arm/crypto/curve25519-core.S b/arch/arm/crypto/curve25519-core.S
index be18af52e7dc..b697fa5d059a 100644
--- a/arch/arm/crypto/curve25519-core.S
+++ b/arch/arm/crypto/curve25519-core.S
@@ -10,8 +10,8 @@
 #include <linux/linkage.h>
 
 .text
-.fpu neon
 .arch armv7-a
+.fpu neon
 .align 4
 
 ENTRY(curve25519_neon)
diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c
index 3023c1acfa19..c31bd8f7c092 100644
--- a/arch/arm/crypto/poly1305-glue.c
+++ b/arch/arm/crypto/poly1305-glue.c
@@ -29,7 +29,7 @@ void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit)
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
 
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
 {
 	poly1305_init_arm(&dctx->h, key);
 	dctx->s[0] = get_unaligned_le32(key + 16);