Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Merge the crypto tree to resolve the conflict between the temporary
and long-term fixes in algif_skcipher.

7 files changed, 61 insertions, 42 deletions

diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index 1cd792db15ef..1eab79c9ac48 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -117,11 +117,10 @@
 	.set T1, REG_T1
 .endm
 
-#define K_BASE		%r8
 #define HASH_PTR	%r9
+#define BLOCKS_CTR	%r8
 #define BUFFER_PTR	%r10
 #define BUFFER_PTR2	%r13
-#define BUFFER_END	%r11
 
 #define PRECALC_BUF	%r14
 #define WK_BUF		%r15
@@ -205,14 +204,14 @@
 		 * blended AVX2 and ALU instruction scheduling
 		 * 1 vector iteration per 8 rounds
 		 */
-		vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP
+		vmovdqu (i * 2)(BUFFER_PTR), W_TMP
 	.elseif ((i & 7) == 1)
-		vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\
+		vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\
 			 WY_TMP, WY_TMP
 	.elseif ((i & 7) == 2)
 		vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
 	.elseif ((i & 7) == 4)
-		vpaddd  K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 	.elseif ((i & 7) == 7)
 		vmovdqu  WY_TMP, PRECALC_WK(i&~7)
 
@@ -255,7 +254,7 @@
 		vpxor	WY, WY_TMP, WY_TMP
 	.elseif ((i & 7) == 7)
 		vpxor	WY_TMP2, WY_TMP, WY
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -291,7 +290,7 @@
 		vpsrld	$30, WY, WY
 		vpor	WY, WY_TMP, WY
 	.elseif ((i & 7) == 7)
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -446,6 +445,16 @@
 
 .endm
 
+/* Add constant only if (%2 > %3) condition met (uses RTA as temp)
+ * %1 + %2 >= %3 ? %4 : 0
+ */
+.macro ADD_IF_GE a, b, c, d
+	mov     \a, RTA
+	add     $\d, RTA
+	cmp     $\c, \b
+	cmovge  RTA, \a
+.endm
+
 /*
  * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
  */
@@ -463,13 +472,16 @@
 	lea	(2*4*80+32)(%rsp), WK_BUF
 
 	# Precalc WK for first 2 blocks
-	PRECALC_OFFSET = 0
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64
 	.set i, 0
 	.rept    160
 		PRECALC i
 		.set i, i + 1
 	.endr
-	PRECALC_OFFSET = 128
+
+	/* Go to next block if needed */
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 	xchg	WK_BUF, PRECALC_BUF
 
 	.align 32
@@ -479,8 +491,8 @@ _loop:
 	 * we use K_BASE value as a signal of a last block,
 	 * it is set below by: cmovae BUFFER_PTR, K_BASE
 	 */
-	cmp	K_BASE, BUFFER_PTR
-	jne	_begin
+	test BLOCKS_CTR, BLOCKS_CTR
+	jnz _begin
 	.align 32
 	jmp	_end
 	.align 32
@@ -512,10 +524,10 @@ _loop0:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR       /* move to next odd-64-byte block */
-	cmp	BUFFER_END, BUFFER_PTR    /* is current block the last one? */
-	cmovae	K_BASE, BUFFER_PTR	/* signal the last iteration smartly */
-
+	/* Update Counter */
+	sub $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128
 	/*
 	 * rounds
 	 * 60,62,64,66,68
@@ -532,8 +544,8 @@ _loop0:
 	UPDATE_HASH	12(HASH_PTR), D
 	UPDATE_HASH	16(HASH_PTR), E
 
-	cmp	K_BASE, BUFFER_PTR	/* is current block the last one? */
-	je	_loop
+	test	BLOCKS_CTR, BLOCKS_CTR
+	jz	_loop
 
 	mov	TB, B
 
@@ -575,10 +587,10 @@ _loop2:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR2      /* move to next even-64-byte block */
-
-	cmp	BUFFER_END, BUFFER_PTR2   /* is current block the last one */
-	cmovae	K_BASE, BUFFER_PTR       /* signal the last iteration smartly */
+	/* update counter */
+	sub     $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 
 	jmp	_loop3
 _loop3:
@@ -641,19 +653,12 @@ _loop3:
 
 	avx2_zeroupper
 
-	lea	K_XMM_AR(%rip), K_BASE
-
+	/* Setup initial values */
 	mov	CTX, HASH_PTR
 	mov	BUF, BUFFER_PTR
-	lea	64(BUF), BUFFER_PTR2
-
-	shl	$6, CNT			/* mul by 64 */
-	add	BUF, CNT
-	add	$64, CNT
-	mov	CNT, BUFFER_END
 
-	cmp	BUFFER_END, BUFFER_PTR2
-	cmovae	K_BASE, BUFFER_PTR2
+	mov	BUF, BUFFER_PTR2
+	mov	CNT, BLOCKS_CTR
 
 	xmm_mov	BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
 
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index f960a043cdeb..fc61739150e7 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
 
 static bool avx2_usable(void)
 {
-	if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
+	if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
 		&& boot_cpu_has(X86_FEATURE_BMI1)
 		&& boot_cpu_has(X86_FEATURE_BMI2))
 		return true;
diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
index 8b3c04d625c3..4a45fa4890c0 100644
--- a/crypto/chacha20_generic.c
+++ b/crypto/chacha20_generic.c
@@ -91,9 +91,14 @@ int crypto_chacha20_crypt(struct skcipher_request *req)
 	crypto_chacha20_init(state, ctx, walk.iv);
 
 	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
+
 		chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
-				 walk.nbytes);
-		err = skcipher_walk_done(&walk, 0);
+				 nbytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 6ceb0e2758bb..d54971d2d1c8 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -32675,6 +32675,10 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 			  "\x5b\x86\x2f\x37\x30\xe3\x7c\xfd"
 			  "\xc4\xfd\x80\x6c\x22\xf2\x21",
 		.rlen	= 375,
+		.also_non_np = 1,
+		.np	= 3,
+		.tap	= { 375 - 20, 4, 16 },
+
 	}, { /* RFC7539 A.2. Test Vector #3 */
 		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
 			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
@@ -33049,6 +33053,9 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = {
 			  "\xa1\xed\xad\xd5\x76\xfa\x24\x8f"
 			  "\x98",
 		.rlen	= 1281,
+		.also_non_np = 1,
+		.np	= 3,
+		.tap	= { 1200, 1, 80 },
 	},
 };
 
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 8527a5899a2f..3f819399cd95 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -883,10 +883,7 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
 	if (ret)
 		return ret;
 
-	memcpy(ctx->ipad, &istate.state, SHA1_DIGEST_SIZE);
-	memcpy(ctx->opad, &ostate.state, SHA1_DIGEST_SIZE);
-
-	for (i = 0; i < ARRAY_SIZE(istate.state); i++) {
+	for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(u32); i++) {
 		if (ctx->ipad[i] != le32_to_cpu(istate.state[i]) ||
 		    ctx->opad[i] != le32_to_cpu(ostate.state[i])) {
 			ctx->base.needs_inv = true;
@@ -894,6 +891,9 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
 		}
 	}
 
+	memcpy(ctx->ipad, &istate.state, SHA1_DIGEST_SIZE);
+	memcpy(ctx->opad, &ostate.state, SHA1_DIGEST_SIZE);
+
 	return 0;
 }
 
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 427cbe012729..dadc4a808df5 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -1073,7 +1073,7 @@ static int aead_perform(struct aead_request *req, int encrypt,
 		req_ctx->hmac_virt = dma_pool_alloc(buffer_pool, flags,
 				&crypt->icv_rev_aes);
 		if (unlikely(!req_ctx->hmac_virt))
-			goto free_buf_src;
+			goto free_buf_dst;
 		if (!encrypt) {
 			scatterwalk_map_and_copy(req_ctx->hmac_virt,
 				req->src, cryptlen, authsize, 0);
@@ -1088,10 +1088,10 @@ static int aead_perform(struct aead_request *req, int encrypt,
 	BUG_ON(qmgr_stat_overflow(SEND_QID));
 	return -EINPROGRESS;
 
-free_buf_src:
-	free_buf_chain(dev, req_ctx->src, crypt->src_buf);
 free_buf_dst:
 	free_buf_chain(dev, req_ctx->dst, crypt->dst_buf);
+free_buf_src:
+	free_buf_chain(dev, req_ctx->src, crypt->src_buf);
 	crypt->ctl_flags = CTL_FLAG_UNUSED;
 	return -ENOMEM;
 }
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index 5a0f75a3bf01..eead4b339466 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -364,11 +364,11 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 	}
 
 	miter.consumed = lzeros;
-	sg_miter_stop(&miter);
 
 	nbytes -= lzeros;
 	nbits = nbytes * 8;
 	if (nbits > MAX_EXTERN_MPI_BITS) {
+		sg_miter_stop(&miter);
 		pr_info("MPI: mpi too large (%u bits)\n", nbits);
 		return NULL;
 	}
@@ -376,6 +376,8 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 	if (nbytes > 0)
 		nbits -= count_leading_zeros(*buff) - (BITS_PER_LONG - 8);
 
+	sg_miter_stop(&miter);
+
 	nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
 	val = mpi_alloc(nlimbs);
 	if (!val)