random: vDSO: move prototype of arch chacha function to vdso/getrandom.h

Having the prototype for __arch_chacha20_blocks_nostack in
arch/x86/include/asm/vdso/getrandom.h meant that the prototype and large
doc comment were cloned by every architecture, which has been causing
unnecessary churn. Instead move it into include/vdso/getrandom.h, where
it can be shared by all archs implementing it.

As a side bonus, this then lets us use that prototype in the
vdso_test_chacha self test, to ensure that it matches the source, and
indeed doing so turned up some inconsistencies, which are rectified
here.
Suggested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

arch/x86/include/asm/vdso/getrandom.h

@@ -37,19 +37,6 @@ static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void
 	return &__vdso_rng_data;
 }
 
-/**
- * __arch_chacha20_blocks_nostack - Generate ChaCha20 stream without using the stack.
- * @dst_bytes:	Destination buffer to hold @nblocks * 64 bytes of output.
- * @key:	32-byte input key.
- * @counter:	8-byte counter, read on input and updated on return.
- * @nblocks:	Number of blocks to generate.
- *
- * Generates a given positive number of blocks of ChaCha20 output with nonce=0, and does not write
- * to any stack or memory outside of the parameters passed to it, in order to mitigate stack data
- * leaking into forked child processes.
- */
-extern void __arch_chacha20_blocks_nostack(u8 *dst_bytes, const u32 *key, u32 *counter, size_t nblocks);
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */

include/vdso/getrandom.h

@@ -43,4 +43,17 @@ struct vgetrandom_state {
 	bool 			in_use;
 };
 
+/**
+ * __arch_chacha20_blocks_nostack - Generate ChaCha20 stream without using the stack.
+ * @dst_bytes:	Destination buffer to hold @nblocks * 64 bytes of output.
+ * @key:	32-byte input key.
+ * @counter:	8-byte counter, read on input and updated on return.
+ * @nblocks:	Number of blocks to generate.
+ *
+ * Generates a given positive number of blocks of ChaCha20 output with nonce=0, and does not write
+ * to any stack or memory outside of the parameters passed to it, in order to mitigate stack data
+ * leaking into forked child processes.
+ */
+extern void __arch_chacha20_blocks_nostack(u8 *dst_bytes, const u32 *key, u32 *counter, size_t nblocks);
+
 #endif /* _VDSO_GETRANDOM_H */

tools/testing/selftests/vDSO/vdso_test_chacha.c

@@ -7,16 +7,20 @@
 #include <sys/random.h>
 #include <string.h>
 #include <stdint.h>
+#include <stdbool.h>
 #include "../kselftest.h"
 
-extern void __arch_chacha20_blocks_nostack(uint8_t *dst_bytes, const uint8_t *key, uint32_t *counter, size_t nblocks);
+typedef uint8_t u8;
+typedef uint32_t u32;
+typedef uint64_t u64;
+#include <vdso/getrandom.h>
 
 int main(int argc, char *argv[])
 {
 	enum { TRIALS = 1000, BLOCKS = 128, BLOCK_SIZE = 64 };
 	static const uint8_t nonce[8] = { 0 };
 	uint32_t counter[2];
-	uint8_t key[32];
+	uint32_t key[8];
 	uint8_t output1[BLOCK_SIZE * BLOCKS], output2[BLOCK_SIZE * BLOCKS];
 
 	ksft_print_header();
@@ -27,7 +31,7 @@ int main(int argc, char *argv[])
 			printf("getrandom() failed!\n");
 			return KSFT_SKIP;
 		}
-		crypto_stream_chacha20(output1, sizeof(output1), nonce, key);
+		crypto_stream_chacha20(output1, sizeof(output1), nonce, (uint8_t *)key);
 		for (unsigned int split = 0; split < BLOCKS; ++split) {
 			memset(output2, 'X', sizeof(output2));
 			memset(counter, 0, sizeof(counter));