Add support for platforms which has no efficient unaligned memory access

Without it, it caused 55.2% slowdown in throughput at TP-Link WR1043ND, MIPS32r2@400Mhz.

Simply check for CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS at compile time.

Test on TP-Link WR1043ND, MIPS32r2@400Mhz.
Setup: https://lists.zx2c4.com/pipermail/wireguard/2016-August/000331.html

Benchmarks before:

root@lede:~# iperf3 -c 10.0.0.1 -i 10
[ ID] Interval           Transfer     Bandwidth       Retr  Cwnd
[  4]   0.00-10.13  sec  28.8 MBytes  23.8 Mbits/sec    0    202 KBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-10.13  sec  28.8 MBytes  23.8 Mbits/sec    0             sender
[  4]   0.00-10.13  sec  28.8 MBytes  23.8 Mbits/sec                  receiver

root@lede:~# iperf3 -c 10.0.0.1 -i 10 -u -b 1G
[ ID] Interval           Transfer     Bandwidth       Total Datagrams
[  4]   0.00-10.00  sec  31.1 MBytes  26.1 Mbits/sec  3982
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bandwidth       Jitter    Lost/Total Datagrams
[  4]   0.00-10.00  sec  31.1 MBytes  26.1 Mbits/sec  0.049 ms  0/3982 (0%)
[  4] Sent 3982 datagrams

Benchmarks with aligned memory fetching:

root@lede:~# iperf3 -c 10.0.0.1 -i 10
[ ID] Interval           Transfer     Bandwidth       Retr  Cwnd
[  4]   0.00-10.22  sec  52.5 MBytes  43.1 Mbits/sec    0    145 KBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-10.22  sec  52.5 MBytes  43.1 Mbits/sec    0             sender
[  4]   0.00-10.22  sec  52.5 MBytes  43.1 Mbits/sec                  receiver

iperf Done.
root@lede:~# iperf3 -c 10.0.0.1 -i 10 -u -b 1G
[ ID] Interval           Transfer     Bandwidth       Total Datagrams
[  4]   0.00-10.00  sec  56.3 MBytes  47.2 Mbits/sec  7207
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bandwidth       Jitter    Lost/Total Datagrams
[  4]   0.00-10.00  sec  56.3 MBytes  47.2 Mbits/sec  0.041 ms  0/7207 (0%)
[  4] Sent 7207 datagrams

src/crypto/chacha20poly1305.c

@@ -248,13 +248,29 @@ struct poly1305_ctx {

static void poly1305_init(struct poly1305_ctx *ctx, const u8 key[static POLY1305_KEY_SIZE])
{
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
	u32 t0, t1, t2, t3;	
#endif

	memset(ctx, 0, sizeof(struct poly1305_ctx));
	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
	ctx->r[0] = (le32_to_cpuvp(key +  0) >> 0) & 0x3ffffff;
	ctx->r[1] = (le32_to_cpuvp(key +  3) >> 2) & 0x3ffff03;
	ctx->r[2] = (le32_to_cpuvp(key +  6) >> 4) & 0x3ffc0ff;
	ctx->r[3] = (le32_to_cpuvp(key +  9) >> 6) & 0x3f03fff;
	ctx->r[4] = (le32_to_cpuvp(key + 12) >> 8) & 0x00fffff;
#else	
	t0 = le32_to_cpuvp(key + 0);
	t1 = le32_to_cpuvp(key + 4);
	t2 = le32_to_cpuvp(key + 8);
	t3 = le32_to_cpuvp(key +12);
	ctx->r[0] = t0 & 0x3ffffff; t0 >>= 26; t0 |= t1 << 6;
	ctx->r[1] = t0 & 0x3ffff03; t1 >>= 20; t1 |= t2 << 12;
	ctx->r[2] = t1 & 0x3ffc0ff; t2 >>= 14; t2 |= t3 << 18;
	ctx->r[3] = t2 & 0x3f03fff; t3 >>= 8;
	ctx->r[4] = t3 & 0x00fffff;
#endif
	ctx->s[0] = le32_to_cpuvp(key +  16);
	ctx->s[1] = le32_to_cpuvp(key +  20);
	ctx->s[2] = le32_to_cpuvp(key +  24);
@@ -267,6 +283,9 @@ static unsigned int poly1305_generic_blocks(struct poly1305_ctx *ctx, const u8 *
	u32 s1, s2, s3, s4;
	u32 h0, h1, h2, h3, h4;
	u64 d0, d1, d2, d3, d4;
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS	
	u32 t0, t1, t2, t3;
#endif

	r0 = ctx->r[0];
	r1 = ctx->r[1];
@@ -287,11 +306,23 @@ static unsigned int poly1305_generic_blocks(struct poly1305_ctx *ctx, const u8 *

	while (likely(srclen >= POLY1305_BLOCK_SIZE)) {
		/* h += m[i] */
#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
		h0 += (le32_to_cpuvp(src +  0) >> 0) & 0x3ffffff;
		h1 += (le32_to_cpuvp(src +  3) >> 2) & 0x3ffffff;
		h2 += (le32_to_cpuvp(src +  6) >> 4) & 0x3ffffff;
		h3 += (le32_to_cpuvp(src +  9) >> 6) & 0x3ffffff;
		h4 += (le32_to_cpuvp(src + 12) >> 8) | hibit;
#else	
		t0 = le32_to_cpuvp(src +  0);
		t1 = le32_to_cpuvp(src +  4);
		t2 = le32_to_cpuvp(src +  8);
		t3 = le32_to_cpuvp(src + 12);
		h0 += t0 & 0x3ffffff;
		h1 += sr((((u64)t1 << 32) | t0), 26) & 0x3ffffff;
		h2 += sr((((u64)t2 << 32) | t1), 20) & 0x3ffffff;
		h3 += sr((((u64)t3 << 32) | t2), 14) & 0x3ffffff;
		h4 += (t3 >> 8) | hibit;
#endif		

		/* h *= r */
		d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) + mlt(h3, s2) + mlt(h4, s1);