siphash: implement HalfSipHash1-3 for hash tables

HalfSipHash, or hsiphash, is a shortened version of SipHash, which
generates 32-bit outputs using a weaker 64-bit key. It has *much* lower
security margins, and shouldn't be used for anything too sensitive, but
it could be used as a hashtable key function replacement, if the output
is never exposed, and if the security requirement is not too high.

The goal is to make this something that performance-critical jhash users
would be willing to use.

On 64-bit machines, HalfSipHash1-3 is slower than SipHash1-3, so we alias
SipHash1-3 to HalfSipHash1-3 on those systems.

64-bit x86_64:
[    0.509409] test_siphash:     SipHash2-4 cycles: 4049181
[    0.510650] test_siphash:     SipHash1-3 cycles: 2512884
[    0.512205] test_siphash: HalfSipHash1-3 cycles: 3429920
[    0.512904] test_siphash:    JenkinsHash cycles:  978267
So, we map hsiphash() -> SipHash1-3

32-bit x86:
[    0.509868] test_siphash:     SipHash2-4 cycles: 14812892
[    0.513601] test_siphash:     SipHash1-3 cycles:  9510710
[    0.515263] test_siphash: HalfSipHash1-3 cycles:  3856157
[    0.515952] test_siphash:    JenkinsHash cycles:  1148567
So, we map hsiphash() -> HalfSipHash1-3

hsiphash() is roughly 3 times slower than jhash(), but comes with a
considerable security improvement.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Reviewed-by: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/lib/siphash.c b/lib/siphash.c
index c43cf40..3ae58b4 100644
--- a/lib/siphash.c
+++ b/lib/siphash.c
@@ -5,7 +5,9 @@
  * SipHash: a fast short-input PRF
  * https://131002.net/siphash/
  *
- * This implementation is specifically for SipHash2-4.
+ * This implementation is specifically for SipHash2-4 for a secure PRF
+ * and HalfSipHash1-3/SipHash1-3 for an insecure PRF only suitable for
+ * hashtables.
  */
 
 #include <linux/siphash.h>
@@ -230,3 +232,320 @@ u64 siphash_3u32(const u32 first, const u32 second, const u32 third,
 	POSTAMBLE
 }
 EXPORT_SYMBOL(siphash_3u32);
+
+#if BITS_PER_LONG == 64
+/* Note that on 64-bit, we make HalfSipHash1-3 actually be SipHash1-3, for
+ * performance reasons. On 32-bit, below, we actually implement HalfSipHash1-3.
+ */
+
+#define HSIPROUND SIPROUND
+#define HPREAMBLE(len) PREAMBLE(len)
+#define HPOSTAMBLE \
+	v3 ^= b; \
+	HSIPROUND; \
+	v0 ^= b; \
+	v2 ^= 0xff; \
+	HSIPROUND; \
+	HSIPROUND; \
+	HSIPROUND; \
+	return (v0 ^ v1) ^ (v2 ^ v3);
+
+u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
+{
+	const u8 *end = data + len - (len % sizeof(u64));
+	const u8 left = len & (sizeof(u64) - 1);
+	u64 m;
+	HPREAMBLE(len)
+	for (; data != end; data += sizeof(u64)) {
+		m = le64_to_cpup(data);
+		v3 ^= m;
+		HSIPROUND;
+		v0 ^= m;
+	}
+#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
+	if (left)
+		b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
+						  bytemask_from_count(left)));
+#else
+	switch (left) {
+	case 7: b |= ((u64)end[6]) << 48;
+	case 6: b |= ((u64)end[5]) << 40;
+	case 5: b |= ((u64)end[4]) << 32;
+	case 4: b |= le32_to_cpup(data); break;
+	case 3: b |= ((u64)end[2]) << 16;
+	case 2: b |= le16_to_cpup(data); break;
+	case 1: b |= end[0];
+	}
+#endif
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(__hsiphash_aligned);
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u32 __hsiphash_unaligned(const void *data, size_t len,
+			 const hsiphash_key_t *key)
+{
+	const u8 *end = data + len - (len % sizeof(u64));
+	const u8 left = len & (sizeof(u64) - 1);
+	u64 m;
+	HPREAMBLE(len)
+	for (; data != end; data += sizeof(u64)) {
+		m = get_unaligned_le64(data);
+		v3 ^= m;
+		HSIPROUND;
+		v0 ^= m;
+	}
+#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
+	if (left)
+		b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
+						  bytemask_from_count(left)));
+#else
+	switch (left) {
+	case 7: b |= ((u64)end[6]) << 48;
+	case 6: b |= ((u64)end[5]) << 40;
+	case 5: b |= ((u64)end[4]) << 32;
+	case 4: b |= get_unaligned_le32(end); break;
+	case 3: b |= ((u64)end[2]) << 16;
+	case 2: b |= get_unaligned_le16(end); break;
+	case 1: b |= end[0];
+	}
+#endif
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(__hsiphash_unaligned);
+#endif
+
+/**
+ * hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32
+ * @first: first u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key)
+{
+	HPREAMBLE(4)
+	b |= first;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_1u32);
+
+/**
+ * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32
+ * @first: first u32
+ * @second: second u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key)
+{
+	u64 combined = (u64)second << 32 | first;
+	HPREAMBLE(8)
+	v3 ^= combined;
+	HSIPROUND;
+	v0 ^= combined;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_2u32);
+
+/**
+ * hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32
+ * @first: first u32
+ * @second: second u32
+ * @third: third u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third,
+		  const hsiphash_key_t *key)
+{
+	u64 combined = (u64)second << 32 | first;
+	HPREAMBLE(12)
+	v3 ^= combined;
+	HSIPROUND;
+	v0 ^= combined;
+	b |= third;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_3u32);
+
+/**
+ * hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32
+ * @first: first u32
+ * @second: second u32
+ * @third: third u32
+ * @forth: forth u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third,
+		  const u32 forth, const hsiphash_key_t *key)
+{
+	u64 combined = (u64)second << 32 | first;
+	HPREAMBLE(16)
+	v3 ^= combined;
+	HSIPROUND;
+	v0 ^= combined;
+	combined = (u64)forth << 32 | third;
+	v3 ^= combined;
+	HSIPROUND;
+	v0 ^= combined;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_4u32);
+#else
+#define HSIPROUND \
+	do { \
+	v0 += v1; v1 = rol32(v1, 5); v1 ^= v0; v0 = rol32(v0, 16); \
+	v2 += v3; v3 = rol32(v3, 8); v3 ^= v2; \
+	v0 += v3; v3 = rol32(v3, 7); v3 ^= v0; \
+	v2 += v1; v1 = rol32(v1, 13); v1 ^= v2; v2 = rol32(v2, 16); \
+	} while (0)
+
+#define HPREAMBLE(len) \
+	u32 v0 = 0; \
+	u32 v1 = 0; \
+	u32 v2 = 0x6c796765U; \
+	u32 v3 = 0x74656462U; \
+	u32 b = ((u32)(len)) << 24; \
+	v3 ^= key->key[1]; \
+	v2 ^= key->key[0]; \
+	v1 ^= key->key[1]; \
+	v0 ^= key->key[0];
+
+#define HPOSTAMBLE \
+	v3 ^= b; \
+	HSIPROUND; \
+	v0 ^= b; \
+	v2 ^= 0xff; \
+	HSIPROUND; \
+	HSIPROUND; \
+	HSIPROUND; \
+	return v1 ^ v3;
+
+u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
+{
+	const u8 *end = data + len - (len % sizeof(u32));
+	const u8 left = len & (sizeof(u32) - 1);
+	u32 m;
+	HPREAMBLE(len)
+	for (; data != end; data += sizeof(u32)) {
+		m = le32_to_cpup(data);
+		v3 ^= m;
+		HSIPROUND;
+		v0 ^= m;
+	}
+	switch (left) {
+	case 3: b |= ((u32)end[2]) << 16;
+	case 2: b |= le16_to_cpup(data); break;
+	case 1: b |= end[0];
+	}
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(__hsiphash_aligned);
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u32 __hsiphash_unaligned(const void *data, size_t len,
+			 const hsiphash_key_t *key)
+{
+	const u8 *end = data + len - (len % sizeof(u32));
+	const u8 left = len & (sizeof(u32) - 1);
+	u32 m;
+	HPREAMBLE(len)
+	for (; data != end; data += sizeof(u32)) {
+		m = get_unaligned_le32(data);
+		v3 ^= m;
+		HSIPROUND;
+		v0 ^= m;
+	}
+	switch (left) {
+	case 3: b |= ((u32)end[2]) << 16;
+	case 2: b |= get_unaligned_le16(end); break;
+	case 1: b |= end[0];
+	}
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(__hsiphash_unaligned);
+#endif
+
+/**
+ * hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32
+ * @first: first u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key)
+{
+	HPREAMBLE(4)
+	v3 ^= first;
+	HSIPROUND;
+	v0 ^= first;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_1u32);
+
+/**
+ * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32
+ * @first: first u32
+ * @second: second u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key)
+{
+	HPREAMBLE(8)
+	v3 ^= first;
+	HSIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	HSIPROUND;
+	v0 ^= second;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_2u32);
+
+/**
+ * hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32
+ * @first: first u32
+ * @second: second u32
+ * @third: third u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third,
+		  const hsiphash_key_t *key)
+{
+	HPREAMBLE(12)
+	v3 ^= first;
+	HSIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	HSIPROUND;
+	v0 ^= second;
+	v3 ^= third;
+	HSIPROUND;
+	v0 ^= third;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_3u32);
+
+/**
+ * hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32
+ * @first: first u32
+ * @second: second u32
+ * @third: third u32
+ * @forth: forth u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third,
+		  const u32 forth, const hsiphash_key_t *key)
+{
+	HPREAMBLE(16)
+	v3 ^= first;
+	HSIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	HSIPROUND;
+	v0 ^= second;
+	v3 ^= third;
+	HSIPROUND;
+	v0 ^= third;
+	v3 ^= forth;
+	HSIPROUND;
+	v0 ^= forth;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_4u32);
+#endif