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

Pull crypto fixes from Herbert Xu:
 - Fix compiler warnings in inside-secure
 - Fix LS1021A support in caam
 - Avoid using RBP in x86 crypto code
 - Fix bug in talitos that prevents hashing with algif
 - Fix bugs talitos hashing code that cause incorrect hash result
 - Fix memory freeing path bug in drbg
 - Fix af_alg crash when two SG lists are chained

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6:
  crypto: af_alg - update correct dst SGL entry
  crypto: caam - fix LS1021A support on ARMv7 multiplatform kernel
  crypto: inside-secure - fix gcc-4.9 warnings
  crypto: talitos - Don't provide setkey for non hmac hashing algs
  crypto: talitos - fix hashing
  crypto: talitos - fix sha224
  crypto: x86/twofish - Fix RBP usage
  crypto: sha512-avx2 - Fix RBP usage
  crypto: x86/sha256-ssse3 - Fix RBP usage
  crypto: x86/sha256-avx2 - Fix RBP usage
  crypto: x86/sha256-avx - Fix RBP usage
  crypto: x86/sha1-ssse3 - Fix RBP usage
  crypto: x86/sha1-avx2 - Fix RBP usage
  crypto: x86/des3_ede - Fix RBP usage
  crypto: x86/cast6 - Fix RBP usage
  crypto: x86/cast5 - Fix RBP usage
  crypto: x86/camellia - Fix RBP usage
  crypto: x86/blowfish - Fix RBP usage
  crypto: drbg - fix freeing of resources

12 files changed, 184 insertions, 156 deletions

diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S
index 246c67006ed0..8c1fcb6bad21 100644
--- a/arch/x86/crypto/blowfish-x86_64-asm_64.S
+++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S
@@ -33,7 +33,7 @@
 #define s3	((16 + 2 + (3 * 256)) * 4)
 
 /* register macros */
-#define CTX %rdi
+#define CTX %r12
 #define RIO %rsi
 
 #define RX0 %rax
@@ -56,12 +56,12 @@
 #define RX2bh %ch
 #define RX3bh %dh
 
-#define RT0 %rbp
+#define RT0 %rdi
 #define RT1 %rsi
 #define RT2 %r8
 #define RT3 %r9
 
-#define RT0d %ebp
+#define RT0d %edi
 #define RT1d %esi
 #define RT2d %r8d
 #define RT3d %r9d
@@ -120,13 +120,14 @@
 
 ENTRY(__blowfish_enc_blk)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 *	%rcx: bool, if true: xor output
 	 */
-	movq %rbp, %r11;
+	movq %r12, %r11;
 
+	movq %rdi, CTX;
 	movq %rsi, %r10;
 	movq %rdx, RIO;
 
@@ -142,7 +143,7 @@ ENTRY(__blowfish_enc_blk)
 	round_enc(14);
 	add_roundkey_enc(16);
 
-	movq %r11, %rbp;
+	movq %r11, %r12;
 
 	movq %r10, RIO;
 	test %cl, %cl;
@@ -157,12 +158,13 @@ ENDPROC(__blowfish_enc_blk)
 
 ENTRY(blowfish_dec_blk)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
-	movq %rbp, %r11;
+	movq %r12, %r11;
 
+	movq %rdi, CTX;
 	movq %rsi, %r10;
 	movq %rdx, RIO;
 
@@ -181,7 +183,7 @@ ENTRY(blowfish_dec_blk)
 	movq %r10, RIO;
 	write_block();
 
-	movq %r11, %rbp;
+	movq %r11, %r12;
 
 	ret;
 ENDPROC(blowfish_dec_blk)
@@ -298,20 +300,21 @@ ENDPROC(blowfish_dec_blk)
 
 ENTRY(__blowfish_enc_blk_4way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 *	%rcx: bool, if true: xor output
 	 */
-	pushq %rbp;
+	pushq %r12;
 	pushq %rbx;
 	pushq %rcx;
 
-	preload_roundkey_enc(0);
-
+	movq %rdi, CTX
 	movq %rsi, %r11;
 	movq %rdx, RIO;
 
+	preload_roundkey_enc(0);
+
 	read_block4();
 
 	round_enc4(0);
@@ -324,39 +327,40 @@ ENTRY(__blowfish_enc_blk_4way)
 	round_enc4(14);
 	add_preloaded_roundkey4();
 
-	popq %rbp;
+	popq %r12;
 	movq %r11, RIO;
 
-	test %bpl, %bpl;
+	test %r12b, %r12b;
 	jnz .L__enc_xor4;
 
 	write_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 	ret;
 
 .L__enc_xor4:
 	xor_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 	ret;
 ENDPROC(__blowfish_enc_blk_4way)
 
 ENTRY(blowfish_dec_blk_4way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
-	pushq %rbp;
+	pushq %r12;
 	pushq %rbx;
-	preload_roundkey_dec(17);
 
-	movq %rsi, %r11;
+	movq %rdi, CTX;
+	movq %rsi, %r11
 	movq %rdx, RIO;
 
+	preload_roundkey_dec(17);
 	read_block4();
 
 	round_dec4(17);
@@ -373,7 +377,7 @@ ENTRY(blowfish_dec_blk_4way)
 	write_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 
 	ret;
 ENDPROC(blowfish_dec_blk_4way)
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 310319c601ed..95ba6956a7f6 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -75,17 +75,17 @@
 #define RCD1bh %dh
 
 #define RT0 %rsi
-#define RT1 %rbp
+#define RT1 %r12
 #define RT2 %r8
 
 #define RT0d %esi
-#define RT1d %ebp
+#define RT1d %r12d
 #define RT2d %r8d
 
 #define RT2bl %r8b
 
 #define RXOR %r9
-#define RRBP %r10
+#define RR12 %r10
 #define RDST %r11
 
 #define RXORd %r9d
@@ -197,7 +197,7 @@ ENTRY(__camellia_enc_blk)
 	 *	%rdx: src
 	 *	%rcx: bool xor
 	 */
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 
 	movq %rcx, RXOR;
 	movq %rsi, RDST;
@@ -227,13 +227,13 @@ ENTRY(__camellia_enc_blk)
 
 	enc_outunpack(mov, RT1);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	ret;
 
 .L__enc_xor:
 	enc_outunpack(xor, RT1);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	ret;
 ENDPROC(__camellia_enc_blk)
 
@@ -248,7 +248,7 @@ ENTRY(camellia_dec_blk)
 	movl $24, RXORd;
 	cmovel RXORd, RT2d; /* max */
 
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 	movq %rsi, RDST;
 	movq %rdx, RIO;
 
@@ -271,7 +271,7 @@ ENTRY(camellia_dec_blk)
 
 	dec_outunpack();
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	ret;
 ENDPROC(camellia_dec_blk)
 
@@ -433,7 +433,7 @@ ENTRY(__camellia_enc_blk_2way)
 	 */
 	pushq %rbx;
 
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 	movq %rcx, RXOR;
 	movq %rsi, RDST;
 	movq %rdx, RIO;
@@ -461,14 +461,14 @@ ENTRY(__camellia_enc_blk_2way)
 
 	enc_outunpack2(mov, RT2);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	popq %rbx;
 	ret;
 
 .L__enc2_xor:
 	enc_outunpack2(xor, RT2);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	popq %rbx;
 	ret;
 ENDPROC(__camellia_enc_blk_2way)
@@ -485,7 +485,7 @@ ENTRY(camellia_dec_blk_2way)
 	cmovel RXORd, RT2d; /* max */
 
 	movq %rbx, RXOR;
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 	movq %rsi, RDST;
 	movq %rdx, RIO;
 
@@ -508,7 +508,7 @@ ENTRY(camellia_dec_blk_2way)
 
 	dec_outunpack2();
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	movq RXOR, %rbx;
 	ret;
 ENDPROC(camellia_dec_blk_2way)
diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
index b4a8806234ea..86107c961bb4 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -47,7 +47,7 @@
 /**********************************************************************
   16-way AVX cast5
  **********************************************************************/
-#define CTX %rdi
+#define CTX %r15
 
 #define RL1 %xmm0
 #define RR1 %xmm1
@@ -70,8 +70,8 @@
 
 #define RTMP %xmm15
 
-#define RID1  %rbp
-#define RID1d %ebp
+#define RID1  %rdi
+#define RID1d %edi
 #define RID2  %rsi
 #define RID2d %esi
 
@@ -226,7 +226,7 @@
 .align 16
 __cast5_enc_blk16:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RL1: blocks 1 and 2
 	 *	RR1: blocks 3 and 4
 	 *	RL2: blocks 5 and 6
@@ -246,9 +246,11 @@ __cast5_enc_blk16:
 	 *	RR4: encrypted blocks 15 and 16
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -283,7 +285,7 @@ __cast5_enc_blk16:
 
 .L__skip_enc:
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	vmovdqa .Lbswap_mask, RKM;
 
@@ -298,7 +300,7 @@ ENDPROC(__cast5_enc_blk16)
 .align 16
 __cast5_dec_blk16:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RL1: encrypted blocks 1 and 2
 	 *	RR1: encrypted blocks 3 and 4
 	 *	RL2: encrypted blocks 5 and 6
@@ -318,9 +320,11 @@ __cast5_dec_blk16:
 	 *	RR4: decrypted blocks 15 and 16
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -356,7 +360,7 @@ __cast5_dec_blk16:
 
 	vmovdqa .Lbswap_mask, RKM;
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	outunpack_blocks(RR1, RL1, RTMP, RX, RKM);
 	outunpack_blocks(RR2, RL2, RTMP, RX, RKM);
@@ -372,12 +376,14 @@ ENDPROC(__cast5_dec_blk16)
 
 ENTRY(cast5_ecb_enc_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	vmovdqu (0*4*4)(%rdx), RL1;
@@ -400,18 +406,22 @@ ENTRY(cast5_ecb_enc_16way)
 	vmovdqu RR4, (6*4*4)(%r11);
 	vmovdqu RL4, (7*4*4)(%r11);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast5_ecb_enc_16way)
 
 ENTRY(cast5_ecb_dec_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 
 	FRAME_BEGIN
+	pushq %r15;
+
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	vmovdqu (0*4*4)(%rdx), RL1;
@@ -434,20 +444,22 @@ ENTRY(cast5_ecb_dec_16way)
 	vmovdqu RR4, (6*4*4)(%r11);
 	vmovdqu RL4, (7*4*4)(%r11);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast5_ecb_dec_16way)
 
 ENTRY(cast5_cbc_dec_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -483,23 +495,24 @@ ENTRY(cast5_cbc_dec_16way)
 	vmovdqu RR4, (6*16)(%r11);
 	vmovdqu RL4, (7*16)(%r11);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast5_cbc_dec_16way)
 
 ENTRY(cast5_ctr_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 *	%rcx: iv (big endian, 64bit)
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -558,8 +571,8 @@ ENTRY(cast5_ctr_16way)
 	vmovdqu RR4, (6*16)(%r11);
 	vmovdqu RL4, (7*16)(%r11);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast5_ctr_16way)
diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
index 952d3156a933..7f30b6f0d72c 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -47,7 +47,7 @@
 /**********************************************************************
   8-way AVX cast6
  **********************************************************************/
-#define CTX %rdi
+#define CTX %r15
 
 #define RA1 %xmm0
 #define RB1 %xmm1
@@ -70,8 +70,8 @@
 
 #define RTMP %xmm15
 
-#define RID1  %rbp
-#define RID1d %ebp
+#define RID1  %rdi
+#define RID1d %edi
 #define RID2  %rsi
 #define RID2d %esi
 
@@ -264,15 +264,17 @@
 .align 8
 __cast6_enc_blk8:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
 	 * output:
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -297,7 +299,7 @@ __cast6_enc_blk8:
 	QBAR(11);
 
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	vmovdqa .Lbswap_mask, RKM;
 
@@ -310,15 +312,17 @@ ENDPROC(__cast6_enc_blk8)
 .align 8
 __cast6_dec_blk8:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
 	 * output:
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: decrypted blocks
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -343,7 +347,7 @@ __cast6_dec_blk8:
 	QBAR(0);
 
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	vmovdqa .Lbswap_mask, RKM;
 	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
@@ -354,12 +358,14 @@ ENDPROC(__cast6_dec_blk8)
 
 ENTRY(cast6_ecb_enc_8way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
@@ -368,18 +374,21 @@ ENTRY(cast6_ecb_enc_8way)
 
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_ecb_enc_8way)
 
 ENTRY(cast6_ecb_dec_8way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
@@ -388,20 +397,22 @@ ENTRY(cast6_ecb_dec_8way)
 
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_ecb_dec_8way)
 
 ENTRY(cast6_cbc_dec_8way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -411,8 +422,8 @@ ENTRY(cast6_cbc_dec_8way)
 
 	store_cbc_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast6_cbc_dec_8way)
@@ -425,9 +436,10 @@ ENTRY(cast6_ctr_8way)
 	 *	%rcx: iv (little endian, 128bit)
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -438,8 +450,8 @@ ENTRY(cast6_ctr_8way)
 
 	store_ctr_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast6_ctr_8way)
@@ -452,7 +464,9 @@ ENTRY(cast6_xts_enc_8way)
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX
 	movq %rsi, %r11;
 
 	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
@@ -464,6 +478,7 @@ ENTRY(cast6_xts_enc_8way)
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_xts_enc_8way)
@@ -476,7 +491,9 @@ ENTRY(cast6_xts_dec_8way)
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX
 	movq %rsi, %r11;
 
 	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
@@ -488,6 +505,7 @@ ENTRY(cast6_xts_dec_8way)
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_xts_dec_8way)
diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S
index f3e91647ca27..8e49ce117494 100644
--- a/arch/x86/crypto/des3_ede-asm_64.S
+++ b/arch/x86/crypto/des3_ede-asm_64.S
@@ -64,12 +64,12 @@
 #define RW2bh %ch
 
 #define RT0 %r15
-#define RT1 %rbp
+#define RT1 %rsi
 #define RT2 %r14
 #define RT3 %rdx
 
 #define RT0d %r15d
-#define RT1d %ebp
+#define RT1d %esi
 #define RT2d %r14d
 #define RT3d %edx
 
@@ -177,13 +177,14 @@ ENTRY(des3_ede_x86_64_crypt_blk)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
-	pushq %rbp;
 	pushq %rbx;
 	pushq %r12;
 	pushq %r13;
 	pushq %r14;
 	pushq %r15;
 
+	pushq %rsi; /* dst */
+
 	read_block(%rdx, RL0, RR0);
 	initial_permutation(RL0, RR0);
 
@@ -241,6 +242,8 @@ ENTRY(des3_ede_x86_64_crypt_blk)
 	round1(32+15, RL0, RR0, dummy2);
 
 	final_permutation(RR0, RL0);
+
+	popq %rsi /* dst */
 	write_block(%rsi, RR0, RL0);
 
 	popq %r15;
@@ -248,7 +251,6 @@ ENTRY(des3_ede_x86_64_crypt_blk)
 	popq %r13;
 	popq %r12;
 	popq %rbx;
-	popq %rbp;
 
 	ret;
 ENDPROC(des3_ede_x86_64_crypt_blk)
@@ -432,13 +434,14 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way)
 	 *	%rdx: src (3 blocks)
 	 */
 
-	pushq %rbp;
 	pushq %rbx;
 	pushq %r12;
 	pushq %r13;
 	pushq %r14;
 	pushq %r15;
 
+	pushq %rsi /* dst */
+
 	/* load input */
 	movl 0 * 4(%rdx), RL0d;
 	movl 1 * 4(%rdx), RR0d;
@@ -520,6 +523,7 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way)
 	bswapl RR2d;
 	bswapl RL2d;
 
+	popq %rsi /* dst */
 	movl RR0d, 0 * 4(%rsi);
 	movl RL0d, 1 * 4(%rsi);
 	movl RR1d, 2 * 4(%rsi);
@@ -532,7 +536,6 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way)
 	popq %r13;
 	popq %r12;
 	popq %rbx;
-	popq %rbp;
 
 	ret;
 ENDPROC(des3_ede_x86_64_crypt_blk_3way)
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index 1eab79c9ac48..9f712a7dfd79 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -89,7 +89,7 @@
 #define	REG_RE	%rdx
 #define	REG_RTA	%r12
 #define	REG_RTB	%rbx
-#define	REG_T1	%ebp
+#define	REG_T1	%r11d
 #define	xmm_mov	vmovups
 #define	avx2_zeroupper	vzeroupper
 #define	RND_F1	1
@@ -637,7 +637,6 @@ _loop3:
 	ENTRY(\name)
 
 	push	%rbx
-	push	%rbp
 	push	%r12
 	push	%r13
 	push	%r14
@@ -673,7 +672,6 @@ _loop3:
 	pop	%r14
 	pop	%r13
 	pop	%r12
-	pop	%rbp
 	pop	%rbx
 
 	ret
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index a4109506a5e8..6204bd53528c 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -37,7 +37,7 @@
 #define REG_A	%ecx
 #define REG_B	%esi
 #define REG_C	%edi
-#define REG_D	%ebp
+#define REG_D	%r12d
 #define REG_E	%edx
 
 #define REG_T1	%eax
@@ -74,10 +74,10 @@
 	ENTRY(\name)
 
 	push	%rbx
-	push	%rbp
 	push	%r12
+	push	%rbp
+	mov	%rsp, %rbp
 
-	mov	%rsp, %r12
 	sub	$64, %rsp		# allocate workspace
 	and	$~15, %rsp		# align stack
 
@@ -99,10 +99,9 @@
 	xor	%rax, %rax
 	rep stosq
 
-	mov	%r12, %rsp		# deallocate workspace
-
-	pop	%r12
+	mov	%rbp, %rsp		# deallocate workspace
 	pop	%rbp
+	pop	%r12
 	pop	%rbx
 	ret
 
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
index e08888a1a5f2..001bbcf93c79 100644
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ b/arch/x86/crypto/sha256-avx-asm.S
@@ -103,7 +103,7 @@ SRND = %rsi       # clobbers INP
 c = %ecx
 d = %r8d
 e = %edx
-TBL = %rbp
+TBL = %r12
 a = %eax
 b = %ebx
 
@@ -350,13 +350,13 @@ a = TMP_
 ENTRY(sha256_transform_avx)
 .align 32
 	pushq   %rbx
-	pushq   %rbp
+	pushq   %r12
 	pushq   %r13
 	pushq   %r14
 	pushq   %r15
-	pushq   %r12
+	pushq	%rbp
+	movq	%rsp, %rbp
 
-	mov	%rsp, %r12
 	subq    $STACK_SIZE, %rsp	# allocate stack space
 	and	$~15, %rsp		# align stack pointer
 
@@ -452,13 +452,12 @@ loop2:
 
 done_hash:
 
-	mov	%r12, %rsp
-
-	popq	%r12
+	mov	%rbp, %rsp
+	popq	%rbp
 	popq    %r15
 	popq    %r14
 	popq    %r13
-	popq    %rbp
+	popq	%r12
 	popq    %rbx
 	ret
 ENDPROC(sha256_transform_avx)
diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
index 89c8f09787d2..1420db15dcdd 100644
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ b/arch/x86/crypto/sha256-avx2-asm.S
@@ -98,8 +98,6 @@ d	= %r8d
 e       = %edx	# clobbers NUM_BLKS
 y3	= %esi	# clobbers INP
 
-
-TBL	= %rbp
 SRND	= CTX	# SRND is same register as CTX
 
 a = %eax
@@ -531,7 +529,6 @@ STACK_SIZE	= _RSP      + _RSP_SIZE
 ENTRY(sha256_transform_rorx)
 .align 32
 	pushq	%rbx
-	pushq	%rbp
 	pushq	%r12
 	pushq	%r13
 	pushq	%r14
@@ -568,8 +565,6 @@ ENTRY(sha256_transform_rorx)
 	mov	CTX, _CTX(%rsp)
 
 loop0:
-	lea     K256(%rip), TBL
-
 	## Load first 16 dwords from two blocks
 	VMOVDQ	0*32(INP),XTMP0
 	VMOVDQ	1*32(INP),XTMP1
@@ -597,19 +592,19 @@ last_block_enter:
 
 .align 16
 loop1:
-	vpaddd	0*32(TBL, SRND), X0, XFER
+	vpaddd	K256+0*32(SRND), X0, XFER
 	vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 0*32
 
-	vpaddd	1*32(TBL, SRND), X0, XFER
+	vpaddd	K256+1*32(SRND), X0, XFER
 	vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 1*32
 
-	vpaddd	2*32(TBL, SRND), X0, XFER
+	vpaddd	K256+2*32(SRND), X0, XFER
 	vmovdqa XFER, 2*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 2*32
 
-	vpaddd	3*32(TBL, SRND), X0, XFER
+	vpaddd	K256+3*32(SRND), X0, XFER
 	vmovdqa XFER, 3*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 3*32
 
@@ -619,10 +614,11 @@ loop1:
 
 loop2:
 	## Do last 16 rounds with no scheduling
-	vpaddd	0*32(TBL, SRND), X0, XFER
+	vpaddd	K256+0*32(SRND), X0, XFER
 	vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
 	DO_4ROUNDS	_XFER + 0*32
-	vpaddd	1*32(TBL, SRND), X1, XFER
+
+	vpaddd	K256+1*32(SRND), X1, XFER
 	vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
 	DO_4ROUNDS	_XFER + 1*32
 	add	$2*32, SRND
@@ -676,9 +672,6 @@ loop3:
 	ja	done_hash
 
 do_last_block:
-	#### do last block
-	lea	K256(%rip), TBL
-
 	VMOVDQ	0*16(INP),XWORD0
 	VMOVDQ	1*16(INP),XWORD1
 	VMOVDQ	2*16(INP),XWORD2
@@ -718,7 +711,6 @@ done_hash:
 	popq	%r14
 	popq	%r13
 	popq	%r12
-	popq	%rbp
 	popq	%rbx
 	ret
 ENDPROC(sha256_transform_rorx)
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
index 39b83c93e7fd..c6c05ed2c16a 100644
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ b/arch/x86/crypto/sha256-ssse3-asm.S
@@ -95,7 +95,7 @@ SRND = %rsi       # clobbers INP
 c = %ecx
 d = %r8d
 e = %edx
-TBL = %rbp
+TBL = %r12
 a = %eax
 b = %ebx
 
@@ -356,13 +356,13 @@ a = TMP_
 ENTRY(sha256_transform_ssse3)
 .align 32
 	pushq   %rbx
-	pushq   %rbp
+	pushq   %r12
 	pushq   %r13
 	pushq   %r14
 	pushq   %r15
-	pushq   %r12
+	pushq   %rbp
+	mov	%rsp, %rbp
 
-	mov	%rsp, %r12
 	subq    $STACK_SIZE, %rsp
 	and	$~15, %rsp
 
@@ -462,13 +462,12 @@ loop2:
 
 done_hash:
 
-	mov	%r12, %rsp
-
-	popq    %r12
+	mov	%rbp, %rsp
+	popq	%rbp
 	popq    %r15
 	popq    %r14
 	popq    %r13
-	popq    %rbp
+	popq    %r12
 	popq    %rbx
 
 	ret
diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S
index 7f5f6c6ec72e..b16d56005162 100644
--- a/arch/x86/crypto/sha512-avx2-asm.S
+++ b/arch/x86/crypto/sha512-avx2-asm.S
@@ -69,8 +69,9 @@ XFER  = YTMP0
 
 BYTE_FLIP_MASK  = %ymm9
 
-# 1st arg
-CTX         = %rdi
+# 1st arg is %rdi, which is saved to the stack and accessed later via %r12
+CTX1        = %rdi
+CTX2        = %r12
 # 2nd arg
 INP         = %rsi
 # 3rd arg
@@ -81,7 +82,7 @@ d           = %r8
 e           = %rdx
 y3          = %rsi
 
-TBL   = %rbp
+TBL   = %rdi # clobbers CTX1
 
 a     = %rax
 b     = %rbx
@@ -91,26 +92,26 @@ g     = %r10
 h     = %r11
 old_h = %r11
 
-T1    = %r12
+T1    = %r12 # clobbers CTX2
 y0    = %r13
 y1    = %r14
 y2    = %r15
 
-y4    = %r12
-
 # Local variables (stack frame)
 XFER_SIZE = 4*8
 SRND_SIZE = 1*8
 INP_SIZE = 1*8
 INPEND_SIZE = 1*8
+CTX_SIZE = 1*8
 RSPSAVE_SIZE = 1*8
-GPRSAVE_SIZE = 6*8
+GPRSAVE_SIZE = 5*8
 
 frame_XFER = 0
 frame_SRND = frame_XFER + XFER_SIZE
 frame_INP = frame_SRND + SRND_SIZE
 frame_INPEND = frame_INP + INP_SIZE
-frame_RSPSAVE = frame_INPEND + INPEND_SIZE
+frame_CTX = frame_INPEND + INPEND_SIZE
+frame_RSPSAVE = frame_CTX + CTX_SIZE
 frame_GPRSAVE = frame_RSPSAVE + RSPSAVE_SIZE
 frame_size = frame_GPRSAVE + GPRSAVE_SIZE
 
@@ -576,12 +577,11 @@ ENTRY(sha512_transform_rorx)
 	mov	%rax, frame_RSPSAVE(%rsp)
 
 	# Save GPRs
-	mov	%rbp, frame_GPRSAVE(%rsp)
-	mov	%rbx, 8*1+frame_GPRSAVE(%rsp)
-	mov	%r12, 8*2+frame_GPRSAVE(%rsp)
-	mov	%r13, 8*3+frame_GPRSAVE(%rsp)
-	mov	%r14, 8*4+frame_GPRSAVE(%rsp)
-	mov	%r15, 8*5+frame_GPRSAVE(%rsp)
+	mov	%rbx, 8*0+frame_GPRSAVE(%rsp)
+	mov	%r12, 8*1+frame_GPRSAVE(%rsp)
+	mov	%r13, 8*2+frame_GPRSAVE(%rsp)
+	mov	%r14, 8*3+frame_GPRSAVE(%rsp)
+	mov	%r15, 8*4+frame_GPRSAVE(%rsp)
 
 	shl	$7, NUM_BLKS	# convert to bytes
 	jz	done_hash
@@ -589,14 +589,17 @@ ENTRY(sha512_transform_rorx)
 	mov	NUM_BLKS, frame_INPEND(%rsp)
 
 	## load initial digest
-	mov	8*0(CTX),a
-	mov	8*1(CTX),b
-	mov	8*2(CTX),c
-	mov	8*3(CTX),d
-	mov	8*4(CTX),e
-	mov	8*5(CTX),f
-	mov	8*6(CTX),g
-	mov	8*7(CTX),h
+	mov	8*0(CTX1), a
+	mov	8*1(CTX1), b
+	mov	8*2(CTX1), c
+	mov	8*3(CTX1), d
+	mov	8*4(CTX1), e
+	mov	8*5(CTX1), f
+	mov	8*6(CTX1), g
+	mov	8*7(CTX1), h
+
+	# save %rdi (CTX) before it gets clobbered
+	mov	%rdi, frame_CTX(%rsp)
 
 	vmovdqa	PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK
 
@@ -652,14 +655,15 @@ loop2:
 	subq	$1, frame_SRND(%rsp)
 	jne	loop2
 
-	addm	8*0(CTX),a
-	addm	8*1(CTX),b
-	addm	8*2(CTX),c
-	addm	8*3(CTX),d
-	addm	8*4(CTX),e
-	addm	8*5(CTX),f
-	addm	8*6(CTX),g
-	addm	8*7(CTX),h
+	mov	frame_CTX(%rsp), CTX2
+	addm	8*0(CTX2), a
+	addm	8*1(CTX2), b
+	addm	8*2(CTX2), c
+	addm	8*3(CTX2), d
+	addm	8*4(CTX2), e
+	addm	8*5(CTX2), f
+	addm	8*6(CTX2), g
+	addm	8*7(CTX2), h
 
 	mov	frame_INP(%rsp), INP
 	add	$128, INP
@@ -669,12 +673,11 @@ loop2:
 done_hash:
 
 # Restore GPRs
-	mov	frame_GPRSAVE(%rsp)     ,%rbp
-	mov	8*1+frame_GPRSAVE(%rsp) ,%rbx
-	mov	8*2+frame_GPRSAVE(%rsp) ,%r12
-	mov	8*3+frame_GPRSAVE(%rsp) ,%r13
-	mov	8*4+frame_GPRSAVE(%rsp) ,%r14
-	mov	8*5+frame_GPRSAVE(%rsp) ,%r15
+	mov	8*0+frame_GPRSAVE(%rsp), %rbx
+	mov	8*1+frame_GPRSAVE(%rsp), %r12
+	mov	8*2+frame_GPRSAVE(%rsp), %r13
+	mov	8*3+frame_GPRSAVE(%rsp), %r14
+	mov	8*4+frame_GPRSAVE(%rsp), %r15
 
 	# Restore Stack Pointer
 	mov	frame_RSPSAVE(%rsp), %rsp
diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
index b3f49d286348..73b471da3622 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -76,8 +76,8 @@
 #define RT %xmm14
 #define RR %xmm15
 
-#define RID1  %rbp
-#define RID1d %ebp
+#define RID1  %r13
+#define RID1d %r13d
 #define RID2  %rsi
 #define RID2d %esi
 
@@ -259,7 +259,7 @@ __twofish_enc_blk8:
 
 	vmovdqu w(CTX), RK1;
 
-	pushq %rbp;
+	pushq %r13;
 	pushq %rbx;
 	pushq %rcx;
 
@@ -282,7 +282,7 @@ __twofish_enc_blk8:
 
 	popq %rcx;
 	popq %rbx;
-	popq %rbp;
+	popq %r13;
 
 	outunpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
 	outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
@@ -301,7 +301,7 @@ __twofish_dec_blk8:
 
 	vmovdqu (w+4*4)(CTX), RK1;
 
-	pushq %rbp;
+	pushq %r13;
 	pushq %rbx;
 
 	inpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
@@ -322,7 +322,7 @@ __twofish_dec_blk8:
 	vmovdqu (w)(CTX), RK1;
 
 	popq %rbx;
-	popq %rbp;
+	popq %r13;
 
 	outunpack_blocks(RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);