Re: [PATCH 4/3] sha512: reduce stack usage even on i386

[Alexey Dobriyan <adobriyan@xxxxxxxxx>]

On 1/28/12, Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx> wrote:
> On Fri, Jan 27, 2012 at 08:51:30PM +0300, Alexey Dobriyan wrote:
>>
>> I think this is because your tree contained "%16" code instead if "&15".
>> Now that it contains "&15" it should become applicable.
>
> OK.
>
>> --------------------------------------------------------------------------
>> [PATCH] sha512: reduce stack usage even on i386
>
> Can you try the approach that git takes with using asm to read
> and write W (see previous email from Linus in respone to my push
> request)? As it stands your patch is simply relying on gcc's
> ability to optimise.  At least with asm volatile we know that
> gcc will leave it alone.

For some reason it doesn't. :-( I've also tried full barriers.

With this patch, stack usage is still ~900 bytes.

diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index dd0439d..35e7ae7 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -66,16 +66,6 @@ static const u64 sha512_K[80] = {
 #define s0(x)       (ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7))
 #define s1(x)       (ror64(x,19) ^ ror64(x,61) ^ (x >> 6))

-static inline void LOAD_OP(int I, u64 *W, const u8 *input)
-{
-	W[I] = __be64_to_cpu( ((__be64*)(input))[I] );
-}
-
-static inline void BLEND_OP(int I, u64 *W)
-{
-	W[I & 15] += s1(W[(I-2) & 15]) + W[(I-7) & 15] + s0(W[(I-15) & 15]);
-}
-
 static void
 sha512_transform(u64 *state, const u8 *input)
 {
@@ -84,26 +74,29 @@ sha512_transform(u64 *state, const u8 *input)
 	int i;
 	u64 W[16];

-	/* load the input */
-        for (i = 0; i < 16; i++)
-                LOAD_OP(i, W, input);
-
 	/* load the state into our registers */
 	a=state[0];   b=state[1];   c=state[2];   d=state[3];
 	e=state[4];   f=state[5];   g=state[6];   h=state[7];

 #define SHA512_0_15(i, a, b, c, d, e, f, g, h)			\
-	t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + W[i];	\
+	{							\
+	u64 tmp = be64_to_cpu(*((__be64 *)input + (i)));	\
+	*(volatile u64 *)&W[i] = tmp;				\
+	t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + tmp;	\
 	t2 = e0(a) + Maj(a, b, c);				\
 	d += t1;						\
-	h = t1 + t2
+	h = t1 + t2;						\
+	}

 #define SHA512_16_79(i, a, b, c, d, e, f, g, h)			\
-	BLEND_OP(i, W);						\
-	t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + W[(i)&15];\
+	{							\
+	u64 tmp = W[(i) & 15] + s1(W[(i-2) & 15]) + W[(i-7) & 15] +
s0(W[(i-15) & 15]);\
+	*(volatile u64 *)&W[(i) & 15] = tmp;			\
+	t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + tmp;	\
 	t2 = e0(a) + Maj(a, b, c);				\
 	d += t1;						\
-	h = t1 + t2
+	h = t1 + t2;						\
+	}

 	for (i = 0; i < 16; i += 8) {
 		SHA512_0_15(i, a, b, c, d, e, f, g, h);
--
To unsubscribe from this list: send the line "unsubscribe linux-crypto" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html