Re: [PATCH crypto 1/2] lib/crypto: blake2s-generic: reduce code size on small systems

Re-wind the loops entirely on kernels optimized for code size. This is
really not good at all performance-wise. But on m68k, it shaves off 4k
of code size, which is apparently important.

Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 lib/crypto/blake2s-generic.c | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/lib/crypto/blake2s-generic.c b/lib/crypto/blake2s-generic.c
index 75ccb3e633e6..990f000e22ee 100644
--- a/lib/crypto/blake2s-generic.c
+++ b/lib/crypto/blake2s-generic.c

@@ -46,7 +46,7 @@ void blake2s_compress_generic(struct blake2s_state *state, const u8 *block,
 {
 	u32 m[16];
 	u32 v[16];
-	int i;
+	int i, j;
 
 	WARN_ON(IS_ENABLED(DEBUG) &&
 		(nblocks > 1 && inc != BLAKE2S_BLOCK_SIZE));

@@ -86,17 +86,23 @@ void blake2s_compress_generic(struct blake2s_state *state, const u8 *block,
 	G(r, 6, v[2], v[ 7], v[ 8], v[13]); \
 	G(r, 7, v[3], v[ 4], v[ 9], v[14]); \
 } while (0)
-		ROUND(0);
-		ROUND(1);
-		ROUND(2);
-		ROUND(3);
-		ROUND(4);
-		ROUND(5);
-		ROUND(6);
-		ROUND(7);
-		ROUND(8);
-		ROUND(9);
-
+		if (IS_ENABLED(CONFIG_CC_OPTIMIZE_FOR_SIZE)) {
+			for (i = 0; i < 10; ++i) {
+				for (j = 0; j < 8; ++j)
+					G(i, j, v[j % 4], v[((j + (j / 4)) % 4) + 4], v[((j + 2 * (j / 4)) % 4) + 8], v[((j + 3 * (j / 4)) % 4) + 12]);
+			}