lib/crypto: tests: Add hash-test-template.h and gen-hash-testvecs.py

Add hash-test-template.h which generates the following KUnit test cases
for hash functions:

    test_hash_test_vectors
    test_hash_all_lens_up_to_4096
    test_hash_incremental_updates
    test_hash_buffer_overruns
    test_hash_overlaps
    test_hash_alignment_consistency
    test_hash_ctx_zeroization
    test_hash_interrupt_context_1
    test_hash_interrupt_context_2
    test_hmac  (when HMAC is supported)
    benchmark_hash  (when CONFIG_CRYPTO_LIB_BENCHMARK=y)

The initial use cases for this will be sha224_kunit, sha256_kunit,
sha384_kunit, sha512_kunit, and poly1305_kunit.

Add a Python script gen-hash-testvecs.py which generates the test
vectors required by test_hash_test_vectors,
test_hash_all_lens_up_to_4096, and test_hmac.

Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250709200112.258500-2-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>

1 files changed, 102 insertions, 0 deletions

diff --git a/scripts/crypto/gen-hash-testvecs.py b/scripts/crypto/gen-hash-testvecs.py
new file mode 100755
index 000000000000..55f1010339a6
--- /dev/null
+++ b/scripts/crypto/gen-hash-testvecs.py
@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0-or-later
+#
+# Script that generates test vectors for the given cryptographic hash function.
+#
+# Copyright 2025 Google LLC
+
+import hashlib
+import hmac
+import sys
+
+DATA_LENS = [0, 1, 2, 3, 16, 32, 48, 49, 63, 64, 65, 127, 128, 129, 256, 511,
+             513, 1000, 3333, 4096, 4128, 4160, 4224, 16384]
+
+# Generate the given number of random bytes, using the length itself as the seed
+# for a simple linear congruential generator (LCG).  The C test code uses the
+# same LCG with the same seeding strategy to reconstruct the data, ensuring
+# reproducibility without explicitly storing the data in the test vectors.
+def rand_bytes(length):
+    seed = length
+    out = []
+    for _ in range(length):
+        seed = (seed * 25214903917 + 11) % 2**48
+        out.append((seed >> 16) % 256)
+    return bytes(out)
+
+def hash_init(alg):
+    return hashlib.new(alg)
+
+def hash_update(ctx, data):
+    ctx.update(data)
+
+def hash_final(ctx):
+    return ctx.digest()
+
+def compute_hash(alg, data):
+    ctx = hash_init(alg)
+    hash_update(ctx, data)
+    return hash_final(ctx)
+
+def print_bytes(prefix, value, bytes_per_line):
+    for i in range(0, len(value), bytes_per_line):
+        line = prefix + ''.join(f'0x{b:02x}, ' for b in value[i:i+bytes_per_line])
+        print(f'{line.rstrip()}')
+
+def print_static_u8_array_definition(name, value):
+    print('')
+    print(f'static const u8 {name} = {{')
+    print_bytes('\t', value, 8)
+    print('};')
+
+def print_c_struct_u8_array_field(name, value):
+    print(f'\t\t.{name} = {{')
+    print_bytes('\t\t\t', value, 8)
+    print('\t\t},')
+
+def gen_unkeyed_testvecs(alg):
+    print('')
+    print('static const struct {')
+    print('\tsize_t data_len;')
+    print(f'\tu8 digest[{alg.upper()}_DIGEST_SIZE];')
+    print('} hash_testvecs[] = {')
+    for data_len in DATA_LENS:
+        data = rand_bytes(data_len)
+        print('\t{')
+        print(f'\t\t.data_len = {data_len},')
+        print_c_struct_u8_array_field('digest', compute_hash(alg, data))
+        print('\t},')
+    print('};')
+
+    data = rand_bytes(4096)
+    ctx = hash_init(alg)
+    for data_len in range(len(data) + 1):
+        hash_update(ctx, compute_hash(alg, data[:data_len]))
+    print_static_u8_array_definition(
+            f'hash_testvec_consolidated[{alg.upper()}_DIGEST_SIZE]',
+            hash_final(ctx))
+
+def gen_hmac_testvecs(alg):
+    ctx = hmac.new(rand_bytes(32), digestmod=alg)
+    data = rand_bytes(4096)
+    for data_len in range(len(data) + 1):
+        ctx.update(data[:data_len])
+        key_len = data_len % 293
+        key = rand_bytes(key_len)
+        mac = hmac.digest(key, data[:data_len], alg)
+        ctx.update(mac)
+    print_static_u8_array_definition(
+            f'hmac_testvec_consolidated[{alg.upper()}_DIGEST_SIZE]',
+            ctx.digest())
+
+if len(sys.argv) != 2:
+    sys.stderr.write('Usage: gen-hash-testvecs.py ALGORITHM\n')
+    sys.stderr.write('ALGORITHM may be any supported by Python hashlib.\n')
+    sys.stderr.write('Example: gen-hash-testvecs.py sha512\n')
+    sys.exit(1)
+
+alg = sys.argv[1]
+print('/* SPDX-License-Identifier: GPL-2.0-or-later */')
+print(f'/* This file was generated by: {sys.argv[0]} {" ".join(sys.argv[1:])} */')
+gen_unkeyed_testvecs(alg)
+gen_hmac_testvecs(alg)