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

Pull crypto update from Herbert Xu:
 "Here is the crypto update for 4.1:

  New interfaces:
   - user-space interface for AEAD
   - user-space interface for RNG (i.e., pseudo RNG)

  New hashes:
   - ARMv8 SHA1/256
   - ARMv8 AES
   - ARMv8 GHASH
   - ARM assembler and NEON SHA256
   - MIPS OCTEON SHA1/256/512
   - MIPS img-hash SHA1/256 and MD5
   - Power 8 VMX AES/CBC/CTR/GHASH
   - PPC assembler AES, SHA1/256 and MD5
   - Broadcom IPROC RNG driver

  Cleanups/fixes:
   - prevent internal helper algos from being exposed to user-space
   - merge common code from assembly/C SHA implementations
   - misc fixes"

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (169 commits)
  crypto: arm - workaround for building with old binutils
  crypto: arm/sha256 - avoid sha256 code on ARMv7-M
  crypto: x86/sha512_ssse3 - move SHA-384/512 SSSE3 implementation to base layer
  crypto: x86/sha256_ssse3 - move SHA-224/256 SSSE3 implementation to base layer
  crypto: x86/sha1_ssse3 - move SHA-1 SSSE3 implementation to base layer
  crypto: arm64/sha2-ce - move SHA-224/256 ARMv8 implementation to base layer
  crypto: arm64/sha1-ce - move SHA-1 ARMv8 implementation to base layer
  crypto: arm/sha2-ce - move SHA-224/256 ARMv8 implementation to base layer
  crypto: arm/sha256 - move SHA-224/256 ASM/NEON implementation to base layer
  crypto: arm/sha1-ce - move SHA-1 ARMv8 implementation to base layer
  crypto: arm/sha1_neon - move SHA-1 NEON implementation to base layer
  crypto: arm/sha1 - move SHA-1 ARM asm implementation to base layer
  crypto: sha512-generic - move to generic glue implementation
  crypto: sha256-generic - move to generic glue implementation
  crypto: sha1-generic - move to generic glue implementation
  crypto: sha512 - implement base layer for SHA-512
  crypto: sha256 - implement base layer for SHA-256
  crypto: sha1 - implement base layer for SHA-1
  crypto: api - remove instance when test failed
  crypto: api - Move alg ref count init to crypto_check_alg
  ...

5 files changed, 130 insertions, 322 deletions

diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index b1b5b893eb20..05d9e16c0dfd 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -284,7 +284,8 @@ static struct crypto_alg aes_algs[] = { {
         .cra_name               = "__ecb-aes-" MODE,
         .cra_driver_name        = "__driver-ecb-aes-" MODE,
         .cra_priority           = 0,
-        .cra_flags              = CRYPTO_ALG_TYPE_BLKCIPHER,
+        .cra_flags              = CRYPTO_ALG_TYPE_BLKCIPHER |
+                                  CRYPTO_ALG_INTERNAL,
         .cra_blocksize          = AES_BLOCK_SIZE,
         .cra_ctxsize            = sizeof(struct crypto_aes_ctx),
         .cra_alignmask          = 7,
@@ -302,7 +303,8 @@ static struct crypto_alg aes_algs[] = { {
         .cra_name               = "__cbc-aes-" MODE,
         .cra_driver_name        = "__driver-cbc-aes-" MODE,
         .cra_priority           = 0,
-        .cra_flags              = CRYPTO_ALG_TYPE_BLKCIPHER,
+        .cra_flags              = CRYPTO_ALG_TYPE_BLKCIPHER |
+                                  CRYPTO_ALG_INTERNAL,
         .cra_blocksize          = AES_BLOCK_SIZE,
         .cra_ctxsize            = sizeof(struct crypto_aes_ctx),
         .cra_alignmask          = 7,
@@ -320,7 +322,8 @@ static struct crypto_alg aes_algs[] = { {
         .cra_name               = "__ctr-aes-" MODE,
         .cra_driver_name        = "__driver-ctr-aes-" MODE,
         .cra_priority           = 0,
-        .cra_flags              = CRYPTO_ALG_TYPE_BLKCIPHER,
+        .cra_flags              = CRYPTO_ALG_TYPE_BLKCIPHER |
+                                  CRYPTO_ALG_INTERNAL,
         .cra_blocksize          = 1,
         .cra_ctxsize            = sizeof(struct crypto_aes_ctx),
         .cra_alignmask          = 7,
@@ -338,7 +341,8 @@ static struct crypto_alg aes_algs[] = { {
         .cra_name               = "__xts-aes-" MODE,
         .cra_driver_name        = "__driver-xts-aes-" MODE,
         .cra_priority           = 0,
-        .cra_flags              = CRYPTO_ALG_TYPE_BLKCIPHER,
+        .cra_flags              = CRYPTO_ALG_TYPE_BLKCIPHER |
+                                  CRYPTO_ALG_INTERNAL,
         .cra_blocksize          = AES_BLOCK_SIZE,
         .cra_ctxsize            = sizeof(struct crypto_aes_xts_ctx),
         .cra_alignmask          = 7,
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 09d57d98609c..033aae6d732a 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -66,8 +66,8 @@
         .word           0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
 
         /*
-         * void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
-         *                        u8 *head, long bytes)
+         * void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
+         *                        int blocks)
          */
 ENTRY(sha1_ce_transform)
         /* load round constants */
@@ -78,25 +78,22 @@ ENTRY(sha1_ce_transform)
         ld1r            {k3.4s}, [x6]
 
         /* load state */
-        ldr             dga, [x2]
-        ldr             dgb, [x2, #16]
+        ldr             dga, [x0]
+        ldr             dgb, [x0, #16]
 
-        /* load partial state (if supplied) */
-        cbz             x3, 0f
-        ld1             {v8.4s-v11.4s}, [x3]
-        b               1f
+        /* load sha1_ce_state::finalize */
+        ldr             w4, [x0, #:lo12:sha1_ce_offsetof_finalize]
 
         /* load input */
 0:      ld1             {v8.4s-v11.4s}, [x1], #64
-        sub             w0, w0, #1
+        sub             w2, w2, #1
 
-1:
 CPU_LE( rev32           v8.16b, v8.16b          )
 CPU_LE( rev32           v9.16b, v9.16b          )
 CPU_LE( rev32           v10.16b, v10.16b        )
 CPU_LE( rev32           v11.16b, v11.16b        )
 
-2:      add             t0.4s, v8.4s, k0.4s
+1:      add             t0.4s, v8.4s, k0.4s
         mov             dg0v.16b, dgav.16b
 
         add_update      c, ev, k0,  8,  9, 10, 11, dgb
@@ -127,15 +124,15 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
         add             dgbv.2s, dgbv.2s, dg1v.2s
         add             dgav.4s, dgav.4s, dg0v.4s
 
-        cbnz            w0, 0b
+        cbnz            w2, 0b
 
         /*
          * Final block: add padding and total bit count.
-         * Skip if we have no total byte count in x4. In that case, the input
-         * size was not a round multiple of the block size, and the padding is
-         * handled by the C code.
+         * Skip if the input size was not a round multiple of the block size,
+         * the padding is handled by the C code in that case.
          */
         cbz             x4, 3f
+        ldr             x4, [x0, #:lo12:sha1_ce_offsetof_count]
         movi            v9.2d, #0
         mov             x8, #0x80000000
         movi            v10.2d, #0
@@ -144,10 +141,10 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
         mov             x4, #0
         mov             v11.d[0], xzr
         mov             v11.d[1], x7
-        b               2b
+        b               1b
 
         /* store new state */
-3:      str             dga, [x2]
-        str             dgb, [x2, #16]
+3:      str             dga, [x0]
+        str             dgb, [x0, #16]
         ret
 ENDPROC(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index 6fe83f37a750..114e7cc5de8c 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -12,144 +12,81 @@
 #include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
 #include <crypto/sha.h>
+#include <crypto/sha1_base.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 
+#define ASM_EXPORT(sym, val) \
+        asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val));
+
 MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
 
-asmlinkage void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
-                                  u8 *head, long bytes);
+struct sha1_ce_state {
+        struct sha1_state       sst;
+        u32                     finalize;
+};
 
-static int sha1_init(struct shash_desc *desc)
-{
-        struct sha1_state *sctx = shash_desc_ctx(desc);
+asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
+                                  int blocks);
 
-        *sctx = (struct sha1_state){
-                .state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
-        };
-        return 0;
-}
-
-static int sha1_update(struct shash_desc *desc, const u8 *data,
-                       unsigned int len)
+static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
+                          unsigned int len)
 {
-        struct sha1_state *sctx = shash_desc_ctx(desc);
-        unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
-
-        sctx->count += len;
-
-        if ((partial + len) >= SHA1_BLOCK_SIZE) {
-                int blocks;
-
-                if (partial) {
-                        int p = SHA1_BLOCK_SIZE - partial;
+        struct sha1_ce_state *sctx = shash_desc_ctx(desc);
 
-                        memcpy(sctx->buffer + partial, data, p);
-                        data += p;
-                        len -= p;
-                }
-
-                blocks = len / SHA1_BLOCK_SIZE;
-                len %= SHA1_BLOCK_SIZE;
-
-                kernel_neon_begin_partial(16);
-                sha1_ce_transform(blocks, data, sctx->state,
-                                  partial ? sctx->buffer : NULL, 0);
-                kernel_neon_end();
+        sctx->finalize = 0;
+        kernel_neon_begin_partial(16);
+        sha1_base_do_update(desc, data, len,
+                            (sha1_block_fn *)sha1_ce_transform);
+        kernel_neon_end();
 
-                data += blocks * SHA1_BLOCK_SIZE;
-                partial = 0;
-        }
-        if (len)
-                memcpy(sctx->buffer + partial, data, len);
         return 0;
 }
 
-static int sha1_final(struct shash_desc *desc, u8 *out)
+static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
+                         unsigned int len, u8 *out)
 {
-        static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
+        struct sha1_ce_state *sctx = shash_desc_ctx(desc);
+        bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE);
 
-        struct sha1_state *sctx = shash_desc_ctx(desc);
-        __be64 bits = cpu_to_be64(sctx->count << 3);
-        __be32 *dst = (__be32 *)out;
-        int i;
-
-        u32 padlen = SHA1_BLOCK_SIZE
-                     - ((sctx->count + sizeof(bits)) % SHA1_BLOCK_SIZE);
-
-        sha1_update(desc, padding, padlen);
-        sha1_update(desc, (const u8 *)&bits, sizeof(bits));
-
-        for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
-                put_unaligned_be32(sctx->state[i], dst++);
-
-        *sctx = (struct sha1_state){};
-        return 0;
-}
-
-static int sha1_finup(struct shash_desc *desc, const u8 *data,
-                      unsigned int len, u8 *out)
-{
-        struct sha1_state *sctx = shash_desc_ctx(desc);
-        __be32 *dst = (__be32 *)out;
-        int blocks;
-        int i;
-
-        if (sctx->count || !len || (len % SHA1_BLOCK_SIZE)) {
-                sha1_update(desc, data, len);
-                return sha1_final(desc, out);
-        }
+        ASM_EXPORT(sha1_ce_offsetof_count,
+                   offsetof(struct sha1_ce_state, sst.count));
+        ASM_EXPORT(sha1_ce_offsetof_finalize,
+                   offsetof(struct sha1_ce_state, finalize));
 
         /*
-         * Use a fast path if the input is a multiple of 64 bytes. In
-         * this case, there is no need to copy data around, and we can
-         * perform the entire digest calculation in a single invocation
-         * of sha1_ce_transform()
+         * 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.
          */
-        blocks = len / SHA1_BLOCK_SIZE;
+        sctx->finalize = finalize;
 
         kernel_neon_begin_partial(16);
-        sha1_ce_transform(blocks, data, sctx->state, NULL, len);
+        sha1_base_do_update(desc, data, len,
+                            (sha1_block_fn *)sha1_ce_transform);
+        if (!finalize)
+                sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_ce_transform);
         kernel_neon_end();
-
-        for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
-                put_unaligned_be32(sctx->state[i], dst++);
-
-        *sctx = (struct sha1_state){};
-        return 0;
+        return sha1_base_finish(desc, out);
 }
 
-static int sha1_export(struct shash_desc *desc, void *out)
+static int sha1_ce_final(struct shash_desc *desc, u8 *out)
 {
-        struct sha1_state *sctx = shash_desc_ctx(desc);
-        struct sha1_state *dst = out;
-
-        *dst = *sctx;
-        return 0;
-}
-
-static int sha1_import(struct shash_desc *desc, const void *in)
-{
-        struct sha1_state *sctx = shash_desc_ctx(desc);
-        struct sha1_state const *src = in;
-
-        *sctx = *src;
-        return 0;
+        kernel_neon_begin_partial(16);
+        sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_ce_transform);
+        kernel_neon_end();
+        return sha1_base_finish(desc, out);
 }
 
 static struct shash_alg alg = {
-        .init                   = sha1_init,
-        .update                 = sha1_update,
-        .final                  = sha1_final,
-        .finup                  = sha1_finup,
-        .export                 = sha1_export,
-        .import                 = sha1_import,
-        .descsize               = sizeof(struct sha1_state),
+        .init                   = sha1_base_init,
+        .update                 = sha1_ce_update,
+        .final                  = sha1_ce_final,
+        .finup                  = sha1_ce_finup,
+        .descsize               = sizeof(struct sha1_ce_state),
         .digestsize             = SHA1_DIGEST_SIZE,
-        .statesize              = sizeof(struct sha1_state),
         .base                   = {
                 .cra_name               = "sha1",
                 .cra_driver_name        = "sha1-ce",
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 7f29fc031ea8..5df9d9d470ad 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -73,8 +73,8 @@
         .word           0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
 
         /*
-         * void sha2_ce_transform(int blocks, u8 const *src, u32 *state,
-         *                        u8 *head, long bytes)
+         * void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
+         *                        int blocks)
          */
 ENTRY(sha2_ce_transform)
         /* load round constants */
@@ -85,24 +85,21 @@ ENTRY(sha2_ce_transform)
         ld1             {v12.4s-v15.4s}, [x8]
 
         /* load state */
-        ldp             dga, dgb, [x2]
+        ldp             dga, dgb, [x0]
 
-        /* load partial input (if supplied) */
-        cbz             x3, 0f
-        ld1             {v16.4s-v19.4s}, [x3]
-        b               1f
+        /* load sha256_ce_state::finalize */
+        ldr             w4, [x0, #:lo12:sha256_ce_offsetof_finalize]
 
         /* load input */
 0:      ld1             {v16.4s-v19.4s}, [x1], #64
-        sub             w0, w0, #1
+        sub             w2, w2, #1
 
-1:
 CPU_LE( rev32           v16.16b, v16.16b        )
 CPU_LE( rev32           v17.16b, v17.16b        )
 CPU_LE( rev32           v18.16b, v18.16b        )
 CPU_LE( rev32           v19.16b, v19.16b        )
 
-2:      add             t0.4s, v16.4s, v0.4s
+1:      add             t0.4s, v16.4s, v0.4s
         mov             dg0v.16b, dgav.16b
         mov             dg1v.16b, dgbv.16b
 
@@ -131,15 +128,15 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
         add             dgbv.4s, dgbv.4s, dg1v.4s
 
         /* handled all input blocks? */
-        cbnz            w0, 0b
+        cbnz            w2, 0b
 
         /*
          * Final block: add padding and total bit count.
-         * Skip if we have no total byte count in x4. In that case, the input
-         * size was not a round multiple of the block size, and the padding is
-         * handled by the C code.
+         * Skip if the input size was not a round multiple of the block size,
+         * the padding is handled by the C code in that case.
          */
         cbz             x4, 3f
+        ldr             x4, [x0, #:lo12:sha256_ce_offsetof_count]
         movi            v17.2d, #0
         mov             x8, #0x80000000
         movi            v18.2d, #0
@@ -148,9 +145,9 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
         mov             x4, #0
         mov             v19.d[0], xzr
         mov             v19.d[1], x7
-        b               2b
+        b               1b
 
         /* store new state */
-3:      stp             dga, dgb, [x2]
+3:      stp             dga, dgb, [x0]
         ret
 ENDPROC(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index ae67e88c28b9..1340e44c048b 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -12,206 +12,82 @@
 #include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
 #include <crypto/sha.h>
+#include <crypto/sha256_base.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 
+#define ASM_EXPORT(sym, val) \
+        asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val));
+
 MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
 
-asmlinkage int sha2_ce_transform(int blocks, u8 const *src, u32 *state,
-                                 u8 *head, long bytes);
-
-static int sha224_init(struct shash_desc *desc)
-{
-        struct sha256_state *sctx = shash_desc_ctx(desc);
-
-        *sctx = (struct sha256_state){
-                .state = {
-                        SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3,
-                        SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7,
-                }
-        };
-        return 0;
-}
-
-static int sha256_init(struct shash_desc *desc)
-{
-        struct sha256_state *sctx = shash_desc_ctx(desc);
-
-        *sctx = (struct sha256_state){
-                .state = {
-                        SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
-                        SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7,
-                }
-        };
-        return 0;
-}
-
-static int sha2_update(struct shash_desc *desc, const u8 *data,
-                       unsigned int len)
-{
-        struct sha256_state *sctx = shash_desc_ctx(desc);
-        unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
-
-        sctx->count += len;
-
-        if ((partial + len) >= SHA256_BLOCK_SIZE) {
-                int blocks;
-
-                if (partial) {
-                        int p = SHA256_BLOCK_SIZE - partial;
-
-                        memcpy(sctx->buf + partial, data, p);
-                        data += p;
-                        len -= p;
-                }
+struct sha256_ce_state {
+        struct sha256_state     sst;
+        u32                     finalize;
+};
 
-                blocks = len / SHA256_BLOCK_SIZE;
-                len %= SHA256_BLOCK_SIZE;
+asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
+                                  int blocks);
 
-                kernel_neon_begin_partial(28);
-                sha2_ce_transform(blocks, data, sctx->state,
-                                  partial ? sctx->buf : NULL, 0);
-                kernel_neon_end();
-
-                data += blocks * SHA256_BLOCK_SIZE;
-                partial = 0;
-        }
-        if (len)
-                memcpy(sctx->buf + partial, data, len);
-        return 0;
-}
-
-static void sha2_final(struct shash_desc *desc)
+static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
+                            unsigned int len)
 {
-        static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
-
-        struct sha256_state *sctx = shash_desc_ctx(desc);
-        __be64 bits = cpu_to_be64(sctx->count << 3);
-        u32 padlen = SHA256_BLOCK_SIZE
-                     - ((sctx->count + sizeof(bits)) % SHA256_BLOCK_SIZE);
-
-        sha2_update(desc, padding, padlen);
-        sha2_update(desc, (const u8 *)&bits, sizeof(bits));
-}
-
-static int sha224_final(struct shash_desc *desc, u8 *out)
-{
-        struct sha256_state *sctx = shash_desc_ctx(desc);
-        __be32 *dst = (__be32 *)out;
-        int i;
-
-        sha2_final(desc);
-
-        for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
-                put_unaligned_be32(sctx->state[i], dst++);
-
-        *sctx = (struct sha256_state){};
-        return 0;
-}
+        struct sha256_ce_state *sctx = shash_desc_ctx(desc);
 
-static int sha256_final(struct shash_desc *desc, u8 *out)
-{
-        struct sha256_state *sctx = shash_desc_ctx(desc);
-        __be32 *dst = (__be32 *)out;
-        int i;
-
-        sha2_final(desc);
-
-        for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
-                put_unaligned_be32(sctx->state[i], dst++);
+        sctx->finalize = 0;
+        kernel_neon_begin_partial(28);
+        sha256_base_do_update(desc, data, len,
+                              (sha256_block_fn *)sha2_ce_transform);
+        kernel_neon_end();
 
-        *sctx = (struct sha256_state){};
         return 0;
 }
 
-static void sha2_finup(struct shash_desc *desc, const u8 *data,
-                       unsigned int len)
+static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
+                           unsigned int len, u8 *out)
 {
-        struct sha256_state *sctx = shash_desc_ctx(desc);
-        int blocks;
+        struct sha256_ce_state *sctx = shash_desc_ctx(desc);
+        bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE);
 
-        if (sctx->count || !len || (len % SHA256_BLOCK_SIZE)) {
-                sha2_update(desc, data, len);
-                sha2_final(desc);
-                return;
-        }
+        ASM_EXPORT(sha256_ce_offsetof_count,
+                   offsetof(struct sha256_ce_state, sst.count));
+        ASM_EXPORT(sha256_ce_offsetof_finalize,
+                   offsetof(struct sha256_ce_state, finalize));
 
         /*
-         * Use a fast path if the input is a multiple of 64 bytes. In
-         * this case, there is no need to copy data around, and we can
-         * perform the entire digest calculation in a single invocation
-         * of sha2_ce_transform()
+         * 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.
          */
-        blocks = len / SHA256_BLOCK_SIZE;
+        sctx->finalize = finalize;
 
         kernel_neon_begin_partial(28);
-        sha2_ce_transform(blocks, data, sctx->state, NULL, len);
+        sha256_base_do_update(desc, data, len,
+                              (sha256_block_fn *)sha2_ce_transform);
+        if (!finalize)
+                sha256_base_do_finalize(desc,
+                                        (sha256_block_fn *)sha2_ce_transform);
         kernel_neon_end();
+        return sha256_base_finish(desc, out);
 }
 
-static int sha224_finup(struct shash_desc *desc, const u8 *data,
-                        unsigned int len, u8 *out)
+static int sha256_ce_final(struct shash_desc *desc, u8 *out)
 {
-        struct sha256_state *sctx = shash_desc_ctx(desc);
-        __be32 *dst = (__be32 *)out;
-        int i;
-
-        sha2_finup(desc, data, len);
-
-        for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
-                put_unaligned_be32(sctx->state[i], dst++);
-
-        *sctx = (struct sha256_state){};
-        return 0;
-}
-
-static int sha256_finup(struct shash_desc *desc, const u8 *data,
-                        unsigned int len, u8 *out)
-{
-        struct sha256_state *sctx = shash_desc_ctx(desc);
-        __be32 *dst = (__be32 *)out;
-        int i;
-
-        sha2_finup(desc, data, len);
-
-        for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
-                put_unaligned_be32(sctx->state[i], dst++);
-
-        *sctx = (struct sha256_state){};
-        return 0;
-}
-
-static int sha2_export(struct shash_desc *desc, void *out)
-{
-        struct sha256_state *sctx = shash_desc_ctx(desc);
-        struct sha256_state *dst = out;
-
-        *dst = *sctx;
-        return 0;
-}
-
-static int sha2_import(struct shash_desc *desc, const void *in)
-{
-        struct sha256_state *sctx = shash_desc_ctx(desc);
-        struct sha256_state const *src = in;
-
-        *sctx = *src;
-        return 0;
+        kernel_neon_begin_partial(28);
+        sha256_base_do_finalize(desc, (sha256_block_fn *)sha2_ce_transform);
+        kernel_neon_end();
+        return sha256_base_finish(desc, out);
 }
 
 static struct shash_alg algs[] = { {
-        .init                   = sha224_init,
-        .update                 = sha2_update,
-        .final                  = sha224_final,
-        .finup                  = sha224_finup,
-        .export                 = sha2_export,
-        .import                 = sha2_import,
-        .descsize               = sizeof(struct sha256_state),
+        .init                   = sha224_base_init,
+        .update                 = sha256_ce_update,
+        .final                  = sha256_ce_final,
+        .finup                  = sha256_ce_finup,
+        .descsize               = sizeof(struct sha256_ce_state),
         .digestsize             = SHA224_DIGEST_SIZE,
-        .statesize              = sizeof(struct sha256_state),
         .base                   = {
                 .cra_name               = "sha224",
                 .cra_driver_name        = "sha224-ce",
@@ -221,15 +97,12 @@ static struct shash_alg algs[] = { {
                 .cra_module             = THIS_MODULE,
         }
 }, {
-        .init                   = sha256_init,
-        .update                 = sha2_update,
-        .final                  = sha256_final,
-        .finup                  = sha256_finup,
-        .export                 = sha2_export,
-        .import                 = sha2_import,
-        .descsize               = sizeof(struct sha256_state),
+        .init                   = sha256_base_init,
+        .update                 = sha256_ce_update,
+        .final                  = sha256_ce_final,
+        .finup                  = sha256_ce_finup,
+        .descsize               = sizeof(struct sha256_ce_state),
         .digestsize             = SHA256_DIGEST_SIZE,
-        .statesize              = sizeof(struct sha256_state),
         .base                   = {
                 .cra_name               = "sha256",
                 .cra_driver_name        = "sha256-ce",