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

Pull crypto updates from Herbert Xu:
 "Here is the crypto update for 4.14:

  API:
   - Defer scompress scratch buffer allocation to first use.
   - Add __crypto_xor that takes separte src and dst operands.
   - Add ahash multiple registration interface.
   - Revamped aead/skcipher algif code to fix async IO properly.

  Drivers:
   - Add non-SIMD fallback code path on ARM for SVE.
   - Add AMD Security Processor framework for ccp.
   - Add support for RSA in ccp.
   - Add XTS-AES-256 support for CCP version 5.
   - Add support for PRNG in sun4i-ss.
   - Add support for DPAA2 in caam.
   - Add ARTPEC crypto support.
   - Add Freescale RNGC hwrng support.
   - Add Microchip / Atmel ECC driver.
   - Add support for STM32 HASH module"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (116 commits)
  crypto: af_alg - get_page upon reassignment to TX SGL
  crypto: cavium/nitrox - Fix an error handling path in 'nitrox_probe()'
  crypto: inside-secure - fix an error handling path in safexcel_probe()
  crypto: rockchip - Don't dequeue the request when device is busy
  crypto: cavium - add release_firmware to all return case
  crypto: sahara - constify platform_device_id
  MAINTAINERS: Add ARTPEC crypto maintainer
  crypto: axis - add ARTPEC-6/7 crypto accelerator driver
  crypto: hash - add crypto_(un)register_ahashes()
  dt-bindings: crypto: add ARTPEC crypto
  crypto: algif_aead - fix comment regarding memory layout
  crypto: ccp - use dma_mapping_error to check map error
  lib/mpi: fix build with clang
  crypto: sahara - Remove leftover from previous used spinlock
  crypto: sahara - Fix dma unmap direction
  crypto: af_alg - consolidation of duplicate code
  crypto: caam - Remove unused dentry members
  crypto: ccp - select CONFIG_CRYPTO_RSA
  crypto: ccp - avoid uninitialized variable warning
  crypto: serpent - improve __serpent_setkey with UBSAN
  ...

1 files changed, 26 insertions, 4 deletions

diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 0ed9486f75dd..fd1ff2b13dfa 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -1,7 +1,7 @@
 /*
  * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
  *
- * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2014 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -9,6 +9,7 @@
  */
 
 #include <asm/neon.h>
+#include <asm/simd.h>
 #include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
 #include <crypto/sha.h>
@@ -34,13 +35,19 @@ const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state,
 const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state,
 						 finalize);
 
+asmlinkage void sha256_block_data_order(u32 *digest, u8 const *src, int blocks);
+
 static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
 			    unsigned int len)
 {
 	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
 
+	if (!may_use_simd())
+		return sha256_base_do_update(desc, data, len,
+				(sha256_block_fn *)sha256_block_data_order);
+
 	sctx->finalize = 0;
-	kernel_neon_begin_partial(28);
+	kernel_neon_begin();
 	sha256_base_do_update(desc, data, len,
 			      (sha256_block_fn *)sha2_ce_transform);
 	kernel_neon_end();
@@ -54,13 +61,22 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
 	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
 	bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE);
 
+	if (!may_use_simd()) {
+		if (len)
+			sha256_base_do_update(desc, data, len,
+				(sha256_block_fn *)sha256_block_data_order);
+		sha256_base_do_finalize(desc,
+				(sha256_block_fn *)sha256_block_data_order);
+		return sha256_base_finish(desc, out);
+	}
+
 	/*
 	 * Allow the asm code to perform the finalization if there is no
 	 * partial data and the input is a round multiple of the block size.
 	 */
 	sctx->finalize = finalize;
 
-	kernel_neon_begin_partial(28);
+	kernel_neon_begin();
 	sha256_base_do_update(desc, data, len,
 			      (sha256_block_fn *)sha2_ce_transform);
 	if (!finalize)
@@ -74,8 +90,14 @@ static int sha256_ce_final(struct shash_desc *desc, u8 *out)
 {
 	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
 
+	if (!may_use_simd()) {
+		sha256_base_do_finalize(desc,
+				(sha256_block_fn *)sha256_block_data_order);
+		return sha256_base_finish(desc, out);
+	}
+
 	sctx->finalize = 0;
-	kernel_neon_begin_partial(28);
+	kernel_neon_begin();
 	sha256_base_do_finalize(desc, (sha256_block_fn *)sha2_ce_transform);
 	kernel_neon_end();
 	return sha256_base_finish(desc, out);