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

Pull crypto updates from Herbert Xu:
 "API:
   - Allow DRBG testing through user-space af_alg
   - Add tcrypt speed testing support for keyed hashes
   - Add type-safe init/exit hooks for ahash

  Algorithms:
   - Mark arc4 as obsolete and pending for future removal
   - Mark anubis, khazad, sead and tea as obsolete
   - Improve boot-time xor benchmark
   - Add OSCCA SM2 asymmetric cipher algorithm and use it for integrity

  Drivers:
   - Fixes and enhancement for XTS in caam
   - Add support for XIP8001B hwrng in xiphera-trng
   - Add RNG and hash support in sun8i-ce/sun8i-ss
   - Allow imx-rngc to be used by kernel entropy pool
   - Use crypto engine in omap-sham
   - Add support for Ingenic X1830 with ingenic"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (205 commits)
  X.509: Fix modular build of public_key_sm2
  crypto: xor - Remove unused variable count in do_xor_speed
  X.509: fix error return value on the failed path
  crypto: bcm - Verify GCM/CCM key length in setkey
  crypto: qat - drop input parameter from adf_enable_aer()
  crypto: qat - fix function parameters descriptions
  crypto: atmel-tdes - use semicolons rather than commas to separate statements
  crypto: drivers - use semicolons rather than commas to separate statements
  hwrng: mxc-rnga - use semicolons rather than commas to separate statements
  hwrng: iproc-rng200 - use semicolons rather than commas to separate statements
  hwrng: stm32 - use semicolons rather than commas to separate statements
  crypto: xor - use ktime for template benchmarking
  crypto: xor - defer load time benchmark to a later time
  crypto: hisilicon/zip - fix the uninitalized 'curr_qm_qp_num'
  crypto: hisilicon/zip - fix the return value when device is busy
  crypto: hisilicon/zip - fix zero length input in GZIP decompress
  crypto: hisilicon/zip - fix the uncleared debug registers
  lib/mpi: Fix unused variable warnings
  crypto: x86/poly1305 - Remove assignments with no effect
  hwrng: npcm - modify readl to readb
  ...

20 files changed, 131 insertions, 118 deletions

diff --git a/arch/arm/crypto/aes-neonbs-core.S b/arch/arm/crypto/aes-neonbs-core.S
index cfaed4e67535..7d0cc7f226a5 100644
--- a/arch/arm/crypto/aes-neonbs-core.S
+++ b/arch/arm/crypto/aes-neonbs-core.S
@@ -77,11 +77,6 @@
 	vldr		\out\()h, \sym + 8
 	.endm
 
-	.macro		__adr, reg, lbl
-	adr		\reg, \lbl
-THUMB(	orr		\reg, \reg, #1		)
-	.endm
-
 	.macro		in_bs_ch, b0, b1, b2, b3, b4, b5, b6, b7
 	veor		\b2, \b2, \b1
 	veor		\b5, \b5, \b6
@@ -629,11 +624,11 @@ ENDPROC(aesbs_decrypt8)
 	push		{r4-r6, lr}
 	ldr		r5, [sp, #16]		// number of blocks
 
-99:	__adr		ip, 0f
+99:	adr		ip, 0f
 	and		lr, r5, #7
 	cmp		r5, #8
 	sub		ip, ip, lr, lsl #2
-	bxlt		ip			// computed goto if blocks < 8
+	movlt		pc, ip			// computed goto if blocks < 8
 
 	vld1.8		{q0}, [r1]!
 	vld1.8		{q1}, [r1]!
@@ -648,11 +643,11 @@ ENDPROC(aesbs_decrypt8)
 	mov		rounds, r3
 	bl		\do8
 
-	__adr		ip, 1f
+	adr		ip, 1f
 	and		lr, r5, #7
 	cmp		r5, #8
 	sub		ip, ip, lr, lsl #2
-	bxlt		ip			// computed goto if blocks < 8
+	movlt		pc, ip			// computed goto if blocks < 8
 
 	vst1.8		{\o0}, [r0]!
 	vst1.8		{\o1}, [r0]!
@@ -689,12 +684,12 @@ ENTRY(aesbs_cbc_decrypt)
 	push		{r4-r6, lr}
 	ldm		ip, {r5-r6}		// load args 4-5
 
-99:	__adr		ip, 0f
+99:	adr		ip, 0f
 	and		lr, r5, #7
 	cmp		r5, #8
 	sub		ip, ip, lr, lsl #2
 	mov		lr, r1
-	bxlt		ip			// computed goto if blocks < 8
+	movlt		pc, ip			// computed goto if blocks < 8
 
 	vld1.8		{q0}, [lr]!
 	vld1.8		{q1}, [lr]!
@@ -718,11 +713,11 @@ ENTRY(aesbs_cbc_decrypt)
 	vmov		q14, q8
 	vmov		q15, q8
 
-	__adr		ip, 1f
+	adr		ip, 1f
 	and		lr, r5, #7
 	cmp		r5, #8
 	sub		ip, ip, lr, lsl #2
-	bxlt		ip			// computed goto if blocks < 8
+	movlt		pc, ip			// computed goto if blocks < 8
 
 	vld1.8		{q9}, [r1]!
 	vld1.8		{q10}, [r1]!
@@ -733,9 +728,9 @@ ENTRY(aesbs_cbc_decrypt)
 	vld1.8		{q15}, [r1]!
 	W(nop)
 
-1:	__adr		ip, 2f
+1:	adr		ip, 2f
 	sub		ip, ip, lr, lsl #3
-	bxlt		ip			// computed goto if blocks < 8
+	movlt		pc, ip			// computed goto if blocks < 8
 
 	veor		q0, q0, q8
 	vst1.8		{q0}, [r0]!
@@ -804,13 +799,13 @@ ENTRY(aesbs_ctr_encrypt)
 	vmov		q6, q0
 	vmov		q7, q0
 
-	__adr		ip, 0f
+	adr		ip, 0f
 	sub		lr, r5, #1
 	and		lr, lr, #7
 	cmp		r5, #8
 	sub		ip, ip, lr, lsl #5
 	sub		ip, ip, lr, lsl #2
-	bxlt		ip			// computed goto if blocks < 8
+	movlt		pc, ip			// computed goto if blocks < 8
 
 	next_ctr	q1
 	next_ctr	q2
@@ -824,13 +819,13 @@ ENTRY(aesbs_ctr_encrypt)
 	mov		rounds, r3
 	bl		aesbs_encrypt8
 
-	__adr		ip, 1f
+	adr		ip, 1f
 	and		lr, r5, #7
 	cmp		r5, #8
 	movgt		r4, #0
 	ldrle		r4, [sp, #40]		// load final in the last round
 	sub		ip, ip, lr, lsl #2
-	bxlt		ip			// computed goto if blocks < 8
+	movlt		pc, ip			// computed goto if blocks < 8
 
 	vld1.8		{q8}, [r1]!
 	vld1.8		{q9}, [r1]!
@@ -843,10 +838,10 @@ ENTRY(aesbs_ctr_encrypt)
 1:	bne		2f
 	vld1.8		{q15}, [r1]!
 
-2:	__adr		ip, 3f
+2:	adr		ip, 3f
 	cmp		r5, #8
 	sub		ip, ip, lr, lsl #3
-	bxlt		ip			// computed goto if blocks < 8
+	movlt		pc, ip			// computed goto if blocks < 8
 
 	veor		q0, q0, q8
 	vst1.8		{q0}, [r0]!
@@ -900,12 +895,12 @@ __xts_prepare8:
 	vshr.u64	d30, d31, #7
 	vmov		q12, q14
 
-	__adr		ip, 0f
+	adr		ip, 0f
 	and		r4, r6, #7
 	cmp		r6, #8
 	sub		ip, ip, r4, lsl #5
 	mov		r4, sp
-	bxlt		ip			// computed goto if blocks < 8
+	movlt		pc, ip			// computed goto if blocks < 8
 
 	vld1.8		{q0}, [r1]!
 	next_tweak	q12, q14, q15, q13
@@ -961,8 +956,7 @@ ENDPROC(__xts_prepare8)
 	push		{r4-r8, lr}
 	mov		r5, sp			// preserve sp
 	ldrd		r6, r7, [sp, #24]	// get blocks and iv args
-	ldr		r8, [sp, #32]		// reorder final tweak?
-	rsb		r8, r8, #1
+	rsb		r8, ip, #1
 	sub		ip, sp, #128		// make room for 8x tweak
 	bic		ip, ip, #0xf		// align sp to 16 bytes
 	mov		sp, ip
@@ -973,12 +967,12 @@ ENDPROC(__xts_prepare8)
 	mov		rounds, r3
 	bl		\do8
 
-	__adr		ip, 0f
+	adr		ip, 0f
 	and		lr, r6, #7
 	cmp		r6, #8
 	sub		ip, ip, lr, lsl #2
 	mov		r4, sp
-	bxlt		ip			// computed goto if blocks < 8
+	movlt		pc, ip			// computed goto if blocks < 8
 
 	vld1.8		{q8}, [r4, :128]!
 	vld1.8		{q9}, [r4, :128]!
@@ -989,9 +983,9 @@ ENDPROC(__xts_prepare8)
 	vld1.8		{q14}, [r4, :128]!
 	vld1.8		{q15}, [r4, :128]
 
-0:	__adr		ip, 1f
+0:	adr		ip, 1f
 	sub		ip, ip, lr, lsl #3
-	bxlt		ip			// computed goto if blocks < 8
+	movlt		pc, ip			// computed goto if blocks < 8
 
 	veor		\o0, \o0, q8
 	vst1.8		{\o0}, [r0]!
@@ -1018,9 +1012,11 @@ ENDPROC(__xts_prepare8)
 	.endm
 
 ENTRY(aesbs_xts_encrypt)
+	mov		ip, #0			// never reorder final tweak
 	__xts_crypt	aesbs_encrypt8, q0, q1, q4, q6, q3, q7, q2, q5
 ENDPROC(aesbs_xts_encrypt)
 
 ENTRY(aesbs_xts_decrypt)
+	ldr		ip, [sp, #8]		// reorder final tweak?
 	__xts_crypt	aesbs_decrypt8, q0, q1, q6, q4, q2, q7, q3, q5
 ENDPROC(aesbs_xts_decrypt)
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index e6fd32919c81..bda8bf17631e 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -8,7 +8,6 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 #include <crypto/aes.h>
-#include <crypto/cbc.h>
 #include <crypto/ctr.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
@@ -49,7 +48,7 @@ struct aesbs_ctx {
 
 struct aesbs_cbc_ctx {
 	struct aesbs_ctx	key;
-	struct crypto_cipher	*enc_tfm;
+	struct crypto_skcipher	*enc_tfm;
 };
 
 struct aesbs_xts_ctx {
@@ -140,19 +139,23 @@ static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 	kernel_neon_end();
 	memzero_explicit(&rk, sizeof(rk));
 
-	return crypto_cipher_setkey(ctx->enc_tfm, in_key, key_len);
+	return crypto_skcipher_setkey(ctx->enc_tfm, in_key, key_len);
 }
 
-static void cbc_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
+static int cbc_encrypt(struct skcipher_request *req)
 {
+	struct skcipher_request *subreq = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	crypto_cipher_encrypt_one(ctx->enc_tfm, dst, src);
-}
+	skcipher_request_set_tfm(subreq, ctx->enc_tfm);
+	skcipher_request_set_callback(subreq,
+				      skcipher_request_flags(req),
+				      NULL, NULL);
+	skcipher_request_set_crypt(subreq, req->src, req->dst,
+				   req->cryptlen, req->iv);
 
-static int cbc_encrypt(struct skcipher_request *req)
-{
-	return crypto_cbc_encrypt_walk(req, cbc_encrypt_one);
+	return crypto_skcipher_encrypt(subreq);
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
@@ -183,20 +186,27 @@ static int cbc_decrypt(struct skcipher_request *req)
 	return err;
 }
 
-static int cbc_init(struct crypto_tfm *tfm)
+static int cbc_init(struct crypto_skcipher *tfm)
 {
-	struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	unsigned int reqsize;
 
-	ctx->enc_tfm = crypto_alloc_cipher("aes", 0, 0);
+	ctx->enc_tfm = crypto_alloc_skcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(ctx->enc_tfm))
+		return PTR_ERR(ctx->enc_tfm);
 
-	return PTR_ERR_OR_ZERO(ctx->enc_tfm);
+	reqsize = sizeof(struct skcipher_request);
+	reqsize += crypto_skcipher_reqsize(ctx->enc_tfm);
+	crypto_skcipher_set_reqsize(tfm, reqsize);
+
+	return 0;
 }
 
-static void cbc_exit(struct crypto_tfm *tfm)
+static void cbc_exit(struct crypto_skcipher *tfm)
 {
-	struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	crypto_free_cipher(ctx->enc_tfm);
+	crypto_free_skcipher(ctx->enc_tfm);
 }
 
 static int aesbs_ctr_setkey_sync(struct crypto_skcipher *tfm, const u8 *in_key,
@@ -304,9 +314,9 @@ static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 	return aesbs_setkey(tfm, in_key, key_len);
 }
 
-static int xts_init(struct crypto_tfm *tfm)
+static int xts_init(struct crypto_skcipher *tfm)
 {
-	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->cts_tfm = crypto_alloc_cipher("aes", 0, 0);
 	if (IS_ERR(ctx->cts_tfm))
@@ -319,9 +329,9 @@ static int xts_init(struct crypto_tfm *tfm)
 	return PTR_ERR_OR_ZERO(ctx->tweak_tfm);
 }
 
-static void xts_exit(struct crypto_tfm *tfm)
+static void xts_exit(struct crypto_skcipher *tfm)
 {
-	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	crypto_free_cipher(ctx->tweak_tfm);
 	crypto_free_cipher(ctx->cts_tfm);
@@ -432,8 +442,6 @@ static struct skcipher_alg aes_algs[] = { {
 	.base.cra_ctxsize	= sizeof(struct aesbs_cbc_ctx),
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
-	.base.cra_init		= cbc_init,
-	.base.cra_exit		= cbc_exit,
 
 	.min_keysize		= AES_MIN_KEY_SIZE,
 	.max_keysize		= AES_MAX_KEY_SIZE,
@@ -442,6 +450,8 @@ static struct skcipher_alg aes_algs[] = { {
 	.setkey			= aesbs_cbc_setkey,
 	.encrypt		= cbc_encrypt,
 	.decrypt		= cbc_decrypt,
+	.init			= cbc_init,
+	.exit			= cbc_exit,
 }, {
 	.base.cra_name		= "__ctr(aes)",
 	.base.cra_driver_name	= "__ctr-aes-neonbs",
@@ -483,8 +493,6 @@ static struct skcipher_alg aes_algs[] = { {
 	.base.cra_ctxsize	= sizeof(struct aesbs_xts_ctx),
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
-	.base.cra_init		= xts_init,
-	.base.cra_exit		= xts_exit,
 
 	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
 	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
@@ -493,6 +501,8 @@ static struct skcipher_alg aes_algs[] = { {
 	.setkey			= aesbs_xts_setkey,
 	.encrypt		= xts_encrypt,
 	.decrypt		= xts_decrypt,
+	.init			= xts_init,
+	.exit			= xts_exit,
 } };
 
 static struct simd_skcipher_alg *aes_simd_algs[ARRAY_SIZE(aes_algs)];
diff --git a/arch/arm/crypto/curve25519-glue.c b/arch/arm/crypto/curve25519-glue.c
index 776ae07e0469..31eb75b6002f 100644
--- a/arch/arm/crypto/curve25519-glue.c
+++ b/arch/arm/crypto/curve25519-glue.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/jump_label.h>
+#include <linux/scatterlist.h>
 #include <crypto/curve25519.h>
 
 asmlinkage void curve25519_neon(u8 mypublic[CURVE25519_KEY_SIZE],
diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c
index 13cfef4ae22e..3023c1acfa19 100644
--- a/arch/arm/crypto/poly1305-glue.c
+++ b/arch/arm/crypto/poly1305-glue.c
@@ -20,6 +20,7 @@
 
 void poly1305_init_arm(void *state, const u8 *key);
 void poly1305_blocks_arm(void *state, const u8 *src, u32 len, u32 hibit);
+void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit);
 void poly1305_emit_arm(void *state, u8 *digest, const u32 *nonce);
 
 void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit)
diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl
index 9f96ff48e4a8..f3a2b54efd4e 100644
--- a/arch/arm/crypto/sha256-armv4.pl
+++ b/arch/arm/crypto/sha256-armv4.pl
@@ -175,7 +175,6 @@ $code=<<___;
 #else
 .syntax unified
 # ifdef __thumb2__
-#  define adrl adr
 .thumb
 # else
 .code   32
@@ -471,7 +470,8 @@ sha256_block_data_order_neon:
 	stmdb	sp!,{r4-r12,lr}
 
 	sub	$H,sp,#16*4+16
-	adrl	$Ktbl,K256
+	adr	$Ktbl,.Lsha256_block_data_order
+	sub	$Ktbl,$Ktbl,#.Lsha256_block_data_order-K256
 	bic	$H,$H,#15		@ align for 128-bit stores
 	mov	$t2,sp
 	mov	sp,$H			@ alloca
diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped
index ea04b2ab0c33..6363014a50d7 100644
--- a/arch/arm/crypto/sha256-core.S_shipped
+++ b/arch/arm/crypto/sha256-core.S_shipped
@@ -56,7 +56,6 @@
 #else
 .syntax unified
 # ifdef __thumb2__
-#  define adrl adr
 .thumb
 # else
 .code   32
@@ -1885,7 +1884,8 @@ sha256_block_data_order_neon:
 	stmdb	sp!,{r4-r12,lr}
 
 	sub	r11,sp,#16*4+16
-	adrl	r14,K256
+	adr	r14,.Lsha256_block_data_order
+	sub	r14,r14,#.Lsha256_block_data_order-K256
 	bic	r11,r11,#15		@ align for 128-bit stores
 	mov	r12,sp
 	mov	sp,r11			@ alloca
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
index 69df68981acd..2fc3516912fa 100644
--- a/arch/arm/crypto/sha512-armv4.pl
+++ b/arch/arm/crypto/sha512-armv4.pl
@@ -212,7 +212,6 @@ $code=<<___;
 #else
 .syntax unified
 # ifdef __thumb2__
-#  define adrl adr
 .thumb
 # else
 .code   32
@@ -602,7 +601,8 @@ sha512_block_data_order_neon:
 	dmb				@ errata #451034 on early Cortex A8
 	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
 	VFP_ABI_PUSH
-	adrl	$Ktbl,K512
+	adr	$Ktbl,.Lsha512_block_data_order
+	sub	$Ktbl,$Ktbl,.Lsha512_block_data_order-K512
 	vldmia	$ctx,{$A-$H}		@ load context
 .Loop_neon:
 ___
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
index cb147db5cbfe..03014624f2ab 100644
--- a/arch/arm/crypto/sha512-core.S_shipped
+++ b/arch/arm/crypto/sha512-core.S_shipped
@@ -79,7 +79,6 @@
 #else
 .syntax unified
 # ifdef __thumb2__
-#  define adrl adr
 .thumb
 # else
 .code   32
@@ -543,7 +542,8 @@ sha512_block_data_order_neon:
 	dmb				@ errata #451034 on early Cortex A8
 	add	r2,r1,r2,lsl#7	@ len to point at the end of inp
 	VFP_ABI_PUSH
-	adrl	r3,K512
+	adr	r3,.Lsha512_block_data_order
+	sub	r3,r3,.Lsha512_block_data_order-K512
 	vldmia	r0,{d16-d23}		@ load context
 .Loop_neon:
 	vshr.u64	d24,d20,#14	@ 0
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index da1034867aaa..8536008e3e35 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -347,7 +347,7 @@ static int gcm_encrypt(struct aead_request *req)
 	u8 buf[AES_BLOCK_SIZE];
 	u8 iv[AES_BLOCK_SIZE];
 	u64 dg[2] = {};
-	u128 lengths;
+	be128 lengths;
 	u8 *tag;
 	int err;
 
@@ -461,7 +461,7 @@ static int gcm_decrypt(struct aead_request *req)
 	u8 buf[AES_BLOCK_SIZE];
 	u8 iv[AES_BLOCK_SIZE];
 	u64 dg[2] = {};
-	u128 lengths;
+	be128 lengths;
 	u8 *tag;
 	int err;
 
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index 565ef604ca04..c63b99211db3 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -25,6 +25,9 @@ struct sha1_ce_state {
 	u32			finalize;
 };
 
+extern const u32 sha1_ce_offsetof_count;
+extern const u32 sha1_ce_offsetof_finalize;
+
 asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
 				  int blocks);
 
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 9450d19b9e6e..5e956d7582a5 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -25,6 +25,9 @@ struct sha256_ce_state {
 	u32			finalize;
 };
 
+extern const u32 sha256_ce_offsetof_count;
+extern const u32 sha256_ce_offsetof_finalize;
+
 asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
 				  int blocks);
 
diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c
index dce86e75f1a8..c1c1ef9457fb 100644
--- a/arch/powerpc/crypto/crc-vpmsum_test.c
+++ b/arch/powerpc/crypto/crc-vpmsum_test.c
@@ -9,6 +9,7 @@
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/random.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/cpufeature.h>
@@ -22,10 +23,11 @@ static unsigned long iterations = 10000;
 static int __init crc_test_init(void)
 {
 	u16 crc16 = 0, verify16 = 0;
-	u32 crc32 = 0, verify32 = 0;
 	__le32 verify32le = 0;
 	unsigned char *data;
+	u32 verify32 = 0;
 	unsigned long i;
+	__le32 crc32;
 	int ret;
 
 	struct crypto_shash *crct10dif_tfm;
@@ -98,7 +100,7 @@ static int __init crc_test_init(void)
 			crypto_shash_final(crc32c_shash, (u8 *)(&crc32));
 			verify32 = le32_to_cpu(verify32le);
 		        verify32le = ~cpu_to_le32(__crc32c_le(~verify32, data+offset, len));
-			if (crc32 != (u32)verify32le) {
+			if (crc32 != verify32le) {
 				pr_err("FAILURE in CRC32: got 0x%08x expected 0x%08x (len %lu)\n",
 				       crc32, verify32, len);
 				break;
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
index 6737bcea1fa1..c025a01cf708 100644
--- a/arch/x86/crypto/blake2s-glue.c
+++ b/arch/x86/crypto/blake2s-glue.c
@@ -11,6 +11,7 @@
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 
 #include <asm/cpufeature.h>
 #include <asm/fpu/api.h>
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index e67a59130025..7b3a1cf0984b 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -12,6 +12,7 @@
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/simd.h>
 
 asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index d2d069bd459b..feccb5254c7e 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -28,9 +28,9 @@
 #define SCALE_F	sizeof(unsigned long)
 
 #ifdef CONFIG_X86_64
-#define REX_PRE "0x48, "
+#define CRC32_INST "crc32q %1, %q0"
 #else
-#define REX_PRE
+#define CRC32_INST "crc32l %1, %0"
 #endif
 
 #ifdef CONFIG_X86_64
@@ -48,11 +48,8 @@ asmlinkage unsigned int crc_pcl(const u8 *buffer, int len,
 static u32 crc32c_intel_le_hw_byte(u32 crc, unsigned char const *data, size_t length)
 {
 	while (length--) {
-		__asm__ __volatile__(
-			".byte 0xf2, 0xf, 0x38, 0xf0, 0xf1"
-			:"=S"(crc)
-			:"0"(crc), "c"(*data)
-		);
+		asm("crc32b %1, %0"
+		    : "+r" (crc) : "rm" (*data));
 		data++;
 	}
 
@@ -66,11 +63,8 @@ static u32 __pure crc32c_intel_le_hw(u32 crc, unsigned char const *p, size_t len
 	unsigned long *ptmp = (unsigned long *)p;
 
 	while (iquotient--) {
-		__asm__ __volatile__(
-			".byte 0xf2, " REX_PRE "0xf, 0x38, 0xf1, 0xf1;"
-			:"=S"(crc)
-			:"0"(crc), "c"(*ptmp)
-		);
+		asm(CRC32_INST
+		    : "+r" (crc) : "rm" (*ptmp));
 		ptmp++;
 	}
 
diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c
index 8acbb6584a37..5af8021b98ce 100644
--- a/arch/x86/crypto/curve25519-x86_64.c
+++ b/arch/x86/crypto/curve25519-x86_64.c
@@ -11,6 +11,7 @@
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/scatterlist.h>
 
 #include <asm/cpufeature.h>
 #include <asm/processor.h>
@@ -45,11 +46,11 @@ static inline u64 add_scalar(u64 *out, const u64 *f1, u64 f2)
 
 	asm volatile(
 		/* Clear registers to propagate the carry bit */
-		"  xor %%r8, %%r8;"
-		"  xor %%r9, %%r9;"
-		"  xor %%r10, %%r10;"
-		"  xor %%r11, %%r11;"
-		"  xor %1, %1;"
+		"  xor %%r8d, %%r8d;"
+		"  xor %%r9d, %%r9d;"
+		"  xor %%r10d, %%r10d;"
+		"  xor %%r11d, %%r11d;"
+		"  xor %k1, %k1;"
 
 		/* Begin addition chain */
 		"  addq 0(%3), %0;"
@@ -93,7 +94,7 @@ static inline void fadd(u64 *out, const u64 *f1, const u64 *f2)
 		"  cmovc %0, %%rax;"
 
 		/* Step 2: Add carry*38 to the original sum */
-		"  xor %%rcx, %%rcx;"
+		"  xor %%ecx, %%ecx;"
 		"  add %%rax, %%r8;"
 		"  adcx %%rcx, %%r9;"
 		"  movq %%r9, 8(%1);"
@@ -165,28 +166,28 @@ static inline void fmul(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 
 		/* Compute src1[0] * src2 */
 		"  movq 0(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  movq %%r8, 0(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  movq %%r8, 0(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  movq %%r10, 8(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"
 		/* Compute src1[1] * src2 */
 		"  movq 8(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  adcxq 8(%0), %%r8;"    "  movq %%r8, 8(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 8(%0), %%r8;"    "  movq %%r8, 8(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 16(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[2] * src2 */
 		"  movq 16(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 16(%0), %%r8;"    "  movq %%r8, 16(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 16(%0), %%r8;"   "  movq %%r8, 16(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 24(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[3] * src2 */
 		"  movq 24(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 24(%0), %%r8;"    "  movq %%r8, 24(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 24(%0), %%r8;"   "  movq %%r8, 24(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 32(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  movq %%rbx, 40(%0);"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  movq %%r14, 48(%0);"    "  mov $0, %%rax;"
@@ -200,7 +201,7 @@ static inline void fmul(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 32(%1), %%r8, %%r13;"
-		"  xor %3, %3;"
+		"  xor %k3, %k3;"
 		"  adoxq 0(%1), %%r8;"
 		"  mulxq 40(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
@@ -246,28 +247,28 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 
 		/* Compute src1[0] * src2 */
 		"  movq 0(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  movq %%r8, 0(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  movq %%r8, 0(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  movq %%r10, 8(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"
 		/* Compute src1[1] * src2 */
 		"  movq 8(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  adcxq 8(%0), %%r8;"    "  movq %%r8, 8(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 8(%0), %%r8;"    "  movq %%r8, 8(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 16(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[2] * src2 */
 		"  movq 16(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 16(%0), %%r8;"    "  movq %%r8, 16(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 16(%0), %%r8;"   "  movq %%r8, 16(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 24(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[3] * src2 */
 		"  movq 24(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 24(%0), %%r8;"    "  movq %%r8, 24(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 24(%0), %%r8;"   "  movq %%r8, 24(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 32(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  movq %%rbx, 40(%0);"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  movq %%r14, 48(%0);"    "  mov $0, %%rax;"
@@ -277,29 +278,29 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 
 		/* Compute src1[0] * src2 */
 		"  movq 32(%1), %%rdx;"
-		"  mulxq 32(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  movq %%r8, 64(%0);"
-		"  mulxq 40(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  movq %%r10, 72(%0);"
+		"  mulxq 32(%3), %%r8, %%r9;"      "  xor %%r10d, %%r10d;"   "  movq %%r8, 64(%0);"
+		"  mulxq 40(%3), %%r10, %%r11;"    "  adox %%r9, %%r10;"     "  movq %%r10, 72(%0);"
 		"  mulxq 48(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"
 		"  mulxq 56(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"
 		/* Compute src1[1] * src2 */
 		"  movq 40(%1), %%rdx;"
-		"  mulxq 32(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  adcxq 72(%0), %%r8;"    "  movq %%r8, 72(%0);"
-		"  mulxq 40(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 80(%0);"
+		"  mulxq 32(%3), %%r8, %%r9;"      "  xor %%r10d, %%r10d;"   "  adcxq 72(%0), %%r8;"   "  movq %%r8, 72(%0);"
+		"  mulxq 40(%3), %%r10, %%r11;"    "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 80(%0);"
 		"  mulxq 48(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 56(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[2] * src2 */
 		"  movq 48(%1), %%rdx;"
-		"  mulxq 32(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 80(%0), %%r8;"    "  movq %%r8, 80(%0);"
-		"  mulxq 40(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 88(%0);"
+		"  mulxq 32(%3), %%r8, %%r9;"      "  xor %%r10d, %%r10d;"   "  adcxq 80(%0), %%r8;"   "  movq %%r8, 80(%0);"
+		"  mulxq 40(%3), %%r10, %%r11;"    "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 88(%0);"
 		"  mulxq 48(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 56(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[3] * src2 */
 		"  movq 56(%1), %%rdx;"
-		"  mulxq 32(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 88(%0), %%r8;"    "  movq %%r8, 88(%0);"
-		"  mulxq 40(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 96(%0);"
+		"  mulxq 32(%3), %%r8, %%r9;"      "  xor %%r10d, %%r10d;"   "  adcxq 88(%0), %%r8;"   "  movq %%r8, 88(%0);"
+		"  mulxq 40(%3), %%r10, %%r11;"    "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 96(%0);"
 		"  mulxq 48(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  movq %%rbx, 104(%0);"    "  mov $0, %%r8;"
 		"  mulxq 56(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  movq %%r14, 112(%0);"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"     "  movq %%rax, 120(%0);"
@@ -312,7 +313,7 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 32(%1), %%r8, %%r13;"
-		"  xor %3, %3;"
+		"  xor %k3, %k3;"
 		"  adoxq 0(%1), %%r8;"
 		"  mulxq 40(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
@@ -345,7 +346,7 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 96(%1), %%r8, %%r13;"
-		"  xor %3, %3;"
+		"  xor %k3, %k3;"
 		"  adoxq 64(%1), %%r8;"
 		"  mulxq 104(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
@@ -516,7 +517,7 @@ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
 
 		/* Step 1: Compute all partial products */
 		"  movq 0(%1), %%rdx;"                                       /* f[0] */
-		"  mulxq 8(%1), %%r8, %%r14;"      "  xor %%r15, %%r15;"     /* f[1]*f[0] */
+		"  mulxq 8(%1), %%r8, %%r14;"      "  xor %%r15d, %%r15d;"   /* f[1]*f[0] */
 		"  mulxq 16(%1), %%r9, %%r10;"     "  adcx %%r14, %%r9;"     /* f[2]*f[0] */
 		"  mulxq 24(%1), %%rax, %%rcx;"    "  adcx %%rax, %%r10;"    /* f[3]*f[0] */
 		"  movq 24(%1), %%rdx;"                                      /* f[3] */
@@ -526,7 +527,7 @@ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
 		"  mulxq 16(%1), %%rax, %%rcx;"    "  mov $0, %%r14;"        /* f[2]*f[1] */
 
 		/* Step 2: Compute two parallel carry chains */
-		"  xor %%r15, %%r15;"
+		"  xor %%r15d, %%r15d;"
 		"  adox %%rax, %%r10;"
 		"  adcx %%r8, %%r8;"
 		"  adox %%rcx, %%r11;"
@@ -563,7 +564,7 @@ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 32(%1), %%r8, %%r13;"
-		"  xor %%rcx, %%rcx;"
+		"  xor %%ecx, %%ecx;"
 		"  adoxq 0(%1), %%r8;"
 		"  mulxq 40(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
@@ -607,7 +608,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 	asm volatile(
 		/* Step 1: Compute all partial products */
 		"  movq 0(%1), %%rdx;"                                       /* f[0] */
-		"  mulxq 8(%1), %%r8, %%r14;"      "  xor %%r15, %%r15;"     /* f[1]*f[0] */
+		"  mulxq 8(%1), %%r8, %%r14;"      "  xor %%r15d, %%r15d;"   /* f[1]*f[0] */
 		"  mulxq 16(%1), %%r9, %%r10;"     "  adcx %%r14, %%r9;"     /* f[2]*f[0] */
 		"  mulxq 24(%1), %%rax, %%rcx;"    "  adcx %%rax, %%r10;"    /* f[3]*f[0] */
 		"  movq 24(%1), %%rdx;"                                      /* f[3] */
@@ -617,7 +618,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 		"  mulxq 16(%1), %%rax, %%rcx;"    "  mov $0, %%r14;"        /* f[2]*f[1] */
 
 		/* Step 2: Compute two parallel carry chains */
-		"  xor %%r15, %%r15;"
+		"  xor %%r15d, %%r15d;"
 		"  adox %%rax, %%r10;"
 		"  adcx %%r8, %%r8;"
 		"  adox %%rcx, %%r11;"
@@ -647,7 +648,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 
 		/* Step 1: Compute all partial products */
 		"  movq 32(%1), %%rdx;"                                       /* f[0] */
-		"  mulxq 40(%1), %%r8, %%r14;"      "  xor %%r15, %%r15;"     /* f[1]*f[0] */
+		"  mulxq 40(%1), %%r8, %%r14;"     "  xor %%r15d, %%r15d;"   /* f[1]*f[0] */
 		"  mulxq 48(%1), %%r9, %%r10;"     "  adcx %%r14, %%r9;"     /* f[2]*f[0] */
 		"  mulxq 56(%1), %%rax, %%rcx;"    "  adcx %%rax, %%r10;"    /* f[3]*f[0] */
 		"  movq 56(%1), %%rdx;"                                      /* f[3] */
@@ -657,7 +658,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 		"  mulxq 48(%1), %%rax, %%rcx;"    "  mov $0, %%r14;"        /* f[2]*f[1] */
 
 		/* Step 2: Compute two parallel carry chains */
-		"  xor %%r15, %%r15;"
+		"  xor %%r15d, %%r15d;"
 		"  adox %%rax, %%r10;"
 		"  adcx %%r8, %%r8;"
 		"  adox %%rcx, %%r11;"
@@ -692,7 +693,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 32(%1), %%r8, %%r13;"
-		"  xor %%rcx, %%rcx;"
+		"  xor %%ecx, %%ecx;"
 		"  adoxq 0(%1), %%r8;"
 		"  mulxq 40(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
@@ -725,7 +726,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 96(%1), %%r8, %%r13;"
-		"  xor %%rcx, %%rcx;"
+		"  xor %%ecx, %%ecx;"
 		"  adoxq 64(%1), %%r8;"
 		"  mulxq 104(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c
index 80fcb85736e1..8ea5ab0f1ca7 100644
--- a/arch/x86/crypto/nhpoly1305-avx2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c
@@ -10,6 +10,7 @@
 #include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/simd.h>
 
 asmlinkage void nh_avx2(const u32 *key, const u8 *message, size_t message_len,
diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c
index cc6b7c1a2705..2b353d42ed13 100644
--- a/arch/x86/crypto/nhpoly1305-sse2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c
@@ -10,6 +10,7 @@
 #include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/simd.h>
 
 asmlinkage void nh_sse2(const u32 *key, const u8 *message, size_t message_len,
diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
index 137edcf038cb..7d568012cc15 100644
--- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
+++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
@@ -246,7 +246,7 @@ $code.=<<___ if (!$kernel);
 ___
 &declare_function("poly1305_init_x86_64", 32, 3);
 $code.=<<___;
-	xor	%rax,%rax
+	xor	%eax,%eax
 	mov	%rax,0($ctx)		# initialize hash value
 	mov	%rax,8($ctx)
 	mov	%rax,16($ctx)
@@ -2853,7 +2853,7 @@ $code.=<<___;
 .type	poly1305_init_base2_44,\@function,3
 .align	32
 poly1305_init_base2_44:
-	xor	%rax,%rax
+	xor	%eax,%eax
 	mov	%rax,0($ctx)		# initialize hash value
 	mov	%rax,8($ctx)
 	mov	%rax,16($ctx)
@@ -3947,7 +3947,7 @@ xor128_decrypt_n_pad:
 	mov	\$16,$len
 	sub	%r10,$len
 	xor	%eax,%eax
-	xor	%r11,%r11
+	xor	%r11d,%r11d
 .Loop_dec_byte:
 	mov	($inp,$otp),%r11b
 	mov	($otp),%al
@@ -4085,7 +4085,7 @@ avx_handler:
 	.long	0xa548f3fc		# cld; rep movsq
 
 	mov	$disp,%rsi
-	xor	%rcx,%rcx		# arg1, UNW_FLAG_NHANDLER
+	xor	%ecx,%ecx		# arg1, UNW_FLAG_NHANDLER
 	mov	8(%rsi),%rdx		# arg2, disp->ImageBase
 	mov	0(%rsi),%r8		# arg3, disp->ControlPc
 	mov	16(%rsi),%r9		# arg4, disp->FunctionEntry
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index dfe921efa9b2..e508dbd91813 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -11,6 +11,7 @@
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/intel-family.h>
 #include <asm/simd.h>
 
@@ -157,9 +158,6 @@ static unsigned int crypto_poly1305_setdctxkey(struct poly1305_desc_ctx *dctx,
 			dctx->s[1] = get_unaligned_le32(&inp[4]);
 			dctx->s[2] = get_unaligned_le32(&inp[8]);
 			dctx->s[3] = get_unaligned_le32(&inp[12]);
-			inp += POLY1305_BLOCK_SIZE;
-			len -= POLY1305_BLOCK_SIZE;
-			acc += POLY1305_BLOCK_SIZE;
 			dctx->sset = true;
 		}
 	}