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

Pull crypto updates from Herbert Xu:
 "API:
   - Enforce the setting of keys for keyed aead/hash/skcipher
     algorithms.
   - Add multibuf speed tests in tcrypt.

  Algorithms:
   - Improve performance of sha3-generic.
   - Add native sha512 support on arm64.
   - Add v8.2 Crypto Extentions version of sha3/sm3 on arm64.
   - Avoid hmac nesting by requiring underlying algorithm to be unkeyed.
   - Add cryptd_max_cpu_qlen module parameter to cryptd.

  Drivers:
   - Add support for EIP97 engine in inside-secure.
   - Add inline IPsec support to chelsio.
   - Add RevB core support to crypto4xx.
   - Fix AEAD ICV check in crypto4xx.
   - Add stm32 crypto driver.
   - Add support for BCM63xx platforms in bcm2835 and remove bcm63xx.
   - Add Derived Key Protocol (DKP) support in caam.
   - Add Samsung Exynos True RNG driver.
   - Add support for Exynos5250+ SoCs in exynos PRNG driver"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (166 commits)
  crypto: picoxcell - Fix error handling in spacc_probe()
  crypto: arm64/sha512 - fix/improve new v8.2 Crypto Extensions code
  crypto: arm64/sm3 - new v8.2 Crypto Extensions implementation
  crypto: arm64/sha3 - new v8.2 Crypto Extensions implementation
  crypto: testmgr - add new testcases for sha3
  crypto: sha3-generic - export init/update/final routines
  crypto: sha3-generic - simplify code
  crypto: sha3-generic - rewrite KECCAK transform to help the compiler optimize
  crypto: sha3-generic - fixes for alignment and big endian operation
  crypto: aesni - handle zero length dst buffer
  crypto: artpec6 - remove select on non-existing CRYPTO_SHA384
  hwrng: bcm2835 - Remove redundant dev_err call in bcm2835_rng_probe()
  crypto: stm32 - remove redundant dev_err call in stm32_cryp_probe()
  crypto: axis - remove unnecessary platform_get_resource() error check
  crypto: testmgr - test misuse of result in ahash
  crypto: inside-secure - make function safexcel_try_push_requests static
  crypto: aes-generic - fix aes-generic regression on powerpc
  crypto: chelsio - Fix indentation warning
  crypto: arm64/sha1-ce - get rid of literal pool
  crypto: arm64/sha2-ce - move the round constant table to .rodata section
  ...

1 files changed, 60 insertions, 52 deletions

diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index 1c3b7ceb36d2..e7273a606a07 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -55,29 +55,31 @@
 #define RAB1bl %bl
 #define RAB2bl %cl
 
+#define CD0 0x0(%rsp)
+#define CD1 0x8(%rsp)
+#define CD2 0x10(%rsp)
+
+# used only before/after all rounds
 #define RCD0 %r8
 #define RCD1 %r9
 #define RCD2 %r10
 
-#define RCD0d %r8d
-#define RCD1d %r9d
-#define RCD2d %r10d
-
-#define RX0 %rbp
-#define RX1 %r11
-#define RX2 %r12
+# used only during rounds
+#define RX0 %r8
+#define RX1 %r9
+#define RX2 %r10
 
-#define RX0d %ebp
-#define RX1d %r11d
-#define RX2d %r12d
+#define RX0d %r8d
+#define RX1d %r9d
+#define RX2d %r10d
 
-#define RY0 %r13
-#define RY1 %r14
-#define RY2 %r15
+#define RY0 %r11
+#define RY1 %r12
+#define RY2 %r13
 
-#define RY0d %r13d
-#define RY1d %r14d
-#define RY2d %r15d
+#define RY0d %r11d
+#define RY1d %r12d
+#define RY2d %r13d
 
 #define RT0 %rdx
 #define RT1 %rsi
@@ -85,6 +87,8 @@
 #define RT0d %edx
 #define RT1d %esi
 
+#define RT1bl %sil
+
 #define do16bit_ror(rot, op1, op2, T0, T1, tmp1, tmp2, ab, dst) \
 	movzbl ab ## bl,		tmp2 ## d; \
 	movzbl ab ## bh,		tmp1 ## d; \
@@ -92,6 +96,11 @@
 	op1##l T0(CTX, tmp2, 4),	dst ## d; \
 	op2##l T1(CTX, tmp1, 4),	dst ## d;
 
+#define swap_ab_with_cd(ab, cd, tmp)	\
+	movq cd, tmp;			\
+	movq ab, cd;			\
+	movq tmp, ab;
+
 /*
  * Combined G1 & G2 function. Reordered with help of rotates to have moves
  * at begining.
@@ -110,15 +119,15 @@
 	/* G1,2 && G2,2 */ \
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 0, x ## 0); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 0, y ## 0); \
-	xchgq cd ## 0, ab ## 0; \
+	swap_ab_with_cd(ab ## 0, cd ## 0, RT0); \
 	\
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 1, x ## 1); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 1, y ## 1); \
-	xchgq cd ## 1, ab ## 1; \
+	swap_ab_with_cd(ab ## 1, cd ## 1, RT0); \
 	\
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 2, x ## 2); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 2, y ## 2); \
-	xchgq cd ## 2, ab ## 2;
+	swap_ab_with_cd(ab ## 2, cd ## 2, RT0);
 
 #define enc_round_end(ab, x, y, n) \
 	addl y ## d,			x ## d; \
@@ -168,6 +177,16 @@
 	decrypt_round3(ba, dc, (n*2)+1); \
 	decrypt_round3(ba, dc, (n*2));
 
+#define push_cd()	\
+	pushq RCD2;	\
+	pushq RCD1;	\
+	pushq RCD0;
+
+#define pop_cd()	\
+	popq RCD0;	\
+	popq RCD1;	\
+	popq RCD2;
+
 #define inpack3(in, n, xy, m) \
 	movq 4*(n)(in),			xy ## 0; \
 	xorq w+4*m(CTX),		xy ## 0; \
@@ -223,11 +242,8 @@ ENTRY(__twofish_enc_blk_3way)
 	 *	%rdx: src, RIO
 	 *	%rcx: bool, if true: xor output
 	 */
-	pushq %r15;
-	pushq %r14;
 	pushq %r13;
 	pushq %r12;
-	pushq %rbp;
 	pushq %rbx;
 
 	pushq %rcx; /* bool xor */
@@ -235,40 +251,36 @@ ENTRY(__twofish_enc_blk_3way)
 
 	inpack_enc3();
 
-	encrypt_cycle3(RAB, RCD, 0);
-	encrypt_cycle3(RAB, RCD, 1);
-	encrypt_cycle3(RAB, RCD, 2);
-	encrypt_cycle3(RAB, RCD, 3);
-	encrypt_cycle3(RAB, RCD, 4);
-	encrypt_cycle3(RAB, RCD, 5);
-	encrypt_cycle3(RAB, RCD, 6);
-	encrypt_cycle3(RAB, RCD, 7);
+	push_cd();
+	encrypt_cycle3(RAB, CD, 0);
+	encrypt_cycle3(RAB, CD, 1);
+	encrypt_cycle3(RAB, CD, 2);
+	encrypt_cycle3(RAB, CD, 3);
+	encrypt_cycle3(RAB, CD, 4);
+	encrypt_cycle3(RAB, CD, 5);
+	encrypt_cycle3(RAB, CD, 6);
+	encrypt_cycle3(RAB, CD, 7);
+	pop_cd();
 
 	popq RIO; /* dst */
-	popq %rbp; /* bool xor */
+	popq RT1; /* bool xor */
 
-	testb %bpl, %bpl;
+	testb RT1bl, RT1bl;
 	jnz .L__enc_xor3;
 
 	outunpack_enc3(mov);
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 
 .L__enc_xor3:
 	outunpack_enc3(xor);
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 ENDPROC(__twofish_enc_blk_3way)
 
@@ -278,35 +290,31 @@ ENTRY(twofish_dec_blk_3way)
 	 *	%rsi: dst
 	 *	%rdx: src, RIO
 	 */
-	pushq %r15;
-	pushq %r14;
 	pushq %r13;
 	pushq %r12;
-	pushq %rbp;
 	pushq %rbx;
 
 	pushq %rsi; /* dst */
 
 	inpack_dec3();
 
-	decrypt_cycle3(RAB, RCD, 7);
-	decrypt_cycle3(RAB, RCD, 6);
-	decrypt_cycle3(RAB, RCD, 5);
-	decrypt_cycle3(RAB, RCD, 4);
-	decrypt_cycle3(RAB, RCD, 3);
-	decrypt_cycle3(RAB, RCD, 2);
-	decrypt_cycle3(RAB, RCD, 1);
-	decrypt_cycle3(RAB, RCD, 0);
+	push_cd();
+	decrypt_cycle3(RAB, CD, 7);
+	decrypt_cycle3(RAB, CD, 6);
+	decrypt_cycle3(RAB, CD, 5);
+	decrypt_cycle3(RAB, CD, 4);
+	decrypt_cycle3(RAB, CD, 3);
+	decrypt_cycle3(RAB, CD, 2);
+	decrypt_cycle3(RAB, CD, 1);
+	decrypt_cycle3(RAB, CD, 0);
+	pop_cd();
 
 	popq RIO; /* dst */
 
 	outunpack_dec3();
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 ENDPROC(twofish_dec_blk_3way)