Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1543038 > unrolled thread

[PATCH v5 0/4] The SipHash Patchset

Back to article view | Back to linux.kernel

Contents

  [PATCH v5 0/4] The SipHash Patchset "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-15 21:40 +0100
    [PATCH v5 4/4] random: use SipHash in place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-15 21:40 +0100
    [PATCH v5 3/4] secure_seq: use SipHash in place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-15 21:40 +0100
      RE: [PATCH v5 3/4] secure_seq: use SipHash in place of MD5 David Laight <David.Laight@ACULAB.COM> - 2016-12-16 11:10 +0100
        Re: [PATCH v5 3/4] secure_seq: use SipHash in place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-16 17:00 +0100
    [PATCH v5 2/4] siphash: add Nu{32,64} helpers "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-15 21:50 +0100
      RE: [PATCH v5 2/4] siphash: add Nu{32,64} helpers David Laight <David.Laight@ACULAB.COM> - 2016-12-16 11:50 +0100
        RE: [PATCH v5 2/4] siphash: add Nu{32,64} helpers "George Spelvin" <linux@sciencehorizons.net> - 2016-12-16 16:50 +0100
    [PATCH v6 4/5] md5: remove from lib and only live in crypto "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-16 04:10 +0100
    [PATCH v6 2/5] secure_seq: use SipHash in place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-16 04:10 +0100
    [PATCH v6 5/5] syncookies: use SipHash in place of SHA1 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-16 04:10 +0100
    [PATCH v6 0/5] The SipHash Patchset "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-16 04:10 +0100
      [PATCH v6 3/5] random: use SipHash in place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-16 04:10 +0100
        Re: [PATCH v6 3/5] random: use SipHash in place of MD5 Andy Lutomirski <luto@amacapital.net> - 2016-12-16 22:40 +0100
      [PATCH v6 1/5] siphash: add cryptographically secure PRF "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-16 04:10 +0100
      [PATCH v7 0/6] The SipHash Patchset "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 00:10 +0100
        [PATCH v7 6/6] siphash: implement HalfSipHash1-3 for hash tables "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 00:10 +0100
          Re: [PATCH v7 6/6] siphash: implement HalfSipHash1-3 for hash tables Andi Kleen <ak@linux.intel.com> - 2016-12-22 01:50 +0100
        [PATCH v7 5/6] syncookies: use SipHash in place of SHA1 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 00:10 +0100
        [PATCH v7 3/6] random: use SipHash in place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 00:10 +0100
          Re: [PATCH v7 3/6] random: use SipHash in place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 00:20 +0100
          Re: [PATCH v7 3/6] random: use SipHash in place of MD5 Andy Lutomirski <luto@amacapital.net> - 2016-12-22 01:00 +0100
            Re: [PATCH v7 3/6] random: use SipHash in place of MD5 Hannes Frederic Sowa <hannes@stressinduktion.org> - 2016-12-22 03:10 +0100
              Re: [PATCH v7 3/6] random: use SipHash in place of MD5 Andy Lutomirski <luto@amacapital.net> - 2016-12-22 03:20 +0100
              Re: [PATCH v7 3/6] random: use SipHash in place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 03:50 +0100
                Re: [PATCH v7 3/6] random: use SipHash in place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 04:20 +0100
                Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 Theodore Ts'o <tytso@mit.edu> - 2016-12-22 06:50 +0100
                  Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 07:10 +0100
                    Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 Theodore Ts'o <tytso@mit.edu> - 2016-12-22 17:00 +0100
                      Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 17:20 +0100
                        Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 Theodore Ts'o <tytso@mit.edu> - 2016-12-22 17:40 +0100
                          Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 17:40 +0100
                  Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 Hannes Frederic Sowa <hannes@stressinduktion.org> - 2016-12-22 13:50 +0100
                    Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 14:20 +0100
                      Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 Hannes Frederic Sowa <hannes@stressinduktion.org> - 2016-12-22 16:10 +0100
                        Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 16:20 +0100
                          Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 16:30 +0100
                            Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 Hannes Frederic Sowa <hannes@stressinduktion.org> - 2016-12-22 16:40 +0100
                              Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 16:50 +0100
                                Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 Hannes Frederic Sowa <hannes@stressinduktion.org> - 2016-12-22 17:00 +0100
                                  Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 17:00 +0100
                      Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 Theodore Ts'o <tytso@mit.edu> - 2016-12-22 17:00 +0100
                        Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 Hannes Frederic Sowa <hannes@stressinduktion.org> - 2016-12-22 19:10 +0100
                          Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 19:20 +0100
                          Re: [kernel-hardening] Re: [PATCH v7 3/6] random: use SipHash in  place of MD5 Theodore Ts'o <tytso@mit.edu> - 2016-12-22 21:00 +0100
            Re: [PATCH v7 3/6] random: use SipHash in place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 03:40 +0100
        [PATCH v7 4/6] md5: remove from lib and only live in crypto "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 00:10 +0100
        [PATCH v7 2/6] secure_seq: use SipHash in place of MD5 "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 00:10 +0100
        [PATCH v7 1/6] siphash: add cryptographically secure PRF "Jason A. Donenfeld" <Jason@zx2c4.com> - 2016-12-22 00:10 +0100
          Re: [PATCH v7 1/6] siphash: add cryptographically secure PRF Stephen Hemminger <stephen@networkplumber.org> - 2016-12-22 02:50 +0100

Page 1 of 3  [1] 2 3  Next page →

#1543038 — [PATCH v5 0/4] The SipHash Patchset

Hey folks,

I think we're approaching the end of the review for this patchset and we're
getting somewhat close to being ready for it being queued up. At this point,
I've incorporated all of the extremely helpful and instructive suggestions
from the list.

For this v5, we now accept u64[2] as the key, so that alignment is taken
care of naturally. For other alignment issues, we have both the fast aligned
version and the unaligned version, depending on what's necessary. We've
worked out the issues for struct padding. The functions now take a void
pointer to avoid ugly casting, which also helps us shed the inline helper
functions which were not very pretty. The replacements of MD5 have been
benchmarked and show a big increase in speed. We've even come up with a
better naming scheme for dword/qword. All and all it's shaping up nicely.

So, if this series looks good to you, please send along your Reviewed-by,
so we can begin to get this completed. If there are still lingering issues,
let me know and I'll incorporated them into a v6 if necessary.

Thanks,
Jason

Jason A. Donenfeld (4):
  siphash: add cryptographically secure PRF
  siphash: add Nu{32,64} helpers
  secure_seq: use SipHash in place of MD5
  random: use SipHash in place of MD5

 drivers/char/random.c   |  32 +++----
 include/linux/siphash.h |  65 ++++++++++++++
 lib/Kconfig.debug       |   6 +-
 lib/Makefile            |   5 +-
 lib/siphash.c           | 223 ++++++++++++++++++++++++++++++++++++++++++++++++
 lib/test_siphash.c      | 101 ++++++++++++++++++++++
 net/core/secure_seq.c   | 133 +++++++++++------------------
 7 files changed, 460 insertions(+), 105 deletions(-)
 create mode 100644 include/linux/siphash.h
 create mode 100644 lib/siphash.c
 create mode 100644 lib/test_siphash.c

-- 
2.11.0

[toc] | [next] | [standalone]

#1543052 — [PATCH v5 4/4] random: use SipHash in place of MD5

This duplicates the current algorithm for get_random_int/long, but uses
siphash instead. This comes with several benefits. It's certainly
faster and more cryptographically secure than MD5. This patch also
separates hashed fields into three values instead of one, in order to
increase diffusion.

The previous MD5 algorithm used a per-cpu MD5 state, which caused
successive calls to the function to chain upon each other. While it's
not entirely clear that this kind of chaining is absolutely necessary
when using a secure PRF like siphash, it can't hurt, and the timing of
the call chain does add a degree of natural entropy. So, in keeping with
this design, instead of the massive per-cpu 64-byte MD5 state, there is
instead a per-cpu previously returned value for chaining.

The speed benefits are substantial:

                | siphash | md5    | speedup |
		------------------------------
get_random_long | 137130  | 415983 | 3.03x   |
get_random_int  | 86384   | 343323 | 3.97x   |

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com>
Cc: Ted Tso <tytso@mit.edu>
---
 drivers/char/random.c | 32 +++++++++++++-------------------
 1 file changed, 13 insertions(+), 19 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index d6876d506220..a51f0ff43f00 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -262,6 +262,7 @@
 #include <linux/syscalls.h>
 #include <linux/completion.h>
 #include <linux/uuid.h>
+#include <linux/siphash.h>
 #include <crypto/chacha20.h>
 
 #include <asm/processor.h>
@@ -2042,7 +2043,7 @@ struct ctl_table random_table[] = {
 };
 #endif 	/* CONFIG_SYSCTL */
 
-static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
+static siphash_key_t random_int_secret;
 
 int random_int_secret_init(void)
 {
@@ -2050,8 +2051,7 @@ int random_int_secret_init(void)
 	return 0;
 }
 
-static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
-		__aligned(sizeof(unsigned long));
+static DEFINE_PER_CPU(u64, get_random_int_chaining);
 
 /*
  * Get a random word for internal kernel use only. Similar to urandom but
@@ -2061,19 +2061,16 @@ static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
  */
 unsigned int get_random_int(void)
 {
-	__u32 *hash;
 	unsigned int ret;
+	u64 *chaining;
 
 	if (arch_get_random_int(&ret))
 		return ret;
 
-	hash = get_cpu_var(get_random_int_hash);
-
-	hash[0] += current->pid + jiffies + random_get_entropy();
-	md5_transform(hash, random_int_secret);
-	ret = hash[0];
-	put_cpu_var(get_random_int_hash);
-
+	chaining = &get_cpu_var(get_random_int_chaining);
+	ret = *chaining = siphash_3u64(*chaining, jiffies, random_get_entropy() +
+				       current->pid, random_int_secret);
+	put_cpu_var(get_random_int_chaining);
 	return ret;
 }
 EXPORT_SYMBOL(get_random_int);
@@ -2083,19 +2080,16 @@ EXPORT_SYMBOL(get_random_int);
  */
 unsigned long get_random_long(void)
 {
-	__u32 *hash;
 	unsigned long ret;
+	u64 *chaining;
 
 	if (arch_get_random_long(&ret))
 		return ret;
 
-	hash = get_cpu_var(get_random_int_hash);
-
-	hash[0] += current->pid + jiffies + random_get_entropy();
-	md5_transform(hash, random_int_secret);
-	ret = *(unsigned long *)hash;
-	put_cpu_var(get_random_int_hash);
-
+	chaining = &get_cpu_var(get_random_int_chaining);
+	ret = *chaining = siphash_3u64(*chaining, jiffies, random_get_entropy() +
+				       current->pid, random_int_secret);
+	put_cpu_var(get_random_int_chaining);
 	return ret;
 }
 EXPORT_SYMBOL(get_random_long);
-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1543056 — [PATCH v5 3/4] secure_seq: use SipHash in place of MD5

This gives a clear speed and security improvement. Siphash is both
faster and is more solid crypto than the aging MD5.

Rather than manually filling MD5 buffers, for IPv6, we simply create
a layout by a simple anonymous struct, for which gcc generates
rather efficient code. For IPv4, we pass the values directly to the
short input convenience functions.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Miller <davem@davemloft.net>
Cc: David Laight <David.Laight@aculab.com>
Cc: Tom Herbert <tom@herbertland.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
 net/core/secure_seq.c | 133 ++++++++++++++++++++------------------------------
 1 file changed, 52 insertions(+), 81 deletions(-)

diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 88a8e429fc3e..c80583bf3213 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -1,3 +1,5 @@
+/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */
+
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/cryptohash.h>
@@ -8,14 +10,14 @@
 #include <linux/ktime.h>
 #include <linux/string.h>
 #include <linux/net.h>
-
+#include <linux/siphash.h>
 #include <net/secure_seq.h>
 
 #if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET)
+#include <linux/in6.h>
 #include <net/tcp.h>
-#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
 
-static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
+static siphash_key_t net_secret;
 
 static __always_inline void net_secret_init(void)
 {
@@ -44,44 +46,42 @@ static u32 seq_scale(u32 seq)
 u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 				 __be16 sport, __be16 dport, u32 *tsoff)
 {
-	u32 secret[MD5_MESSAGE_BYTES / 4];
-	u32 hash[MD5_DIGEST_WORDS];
-	u32 i;
-
+	const struct {
+		struct in6_addr saddr;
+		struct in6_addr daddr;
+		__be16 sport;
+		__be16 dport;
+		u32 padding;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.saddr = *(struct in6_addr *)saddr,
+		.daddr = *(struct in6_addr *)daddr,
+		.sport = sport,
+		.dport = dport
+	};
+	u64 hash;
 	net_secret_init();
-	memcpy(hash, saddr, 16);
-	for (i = 0; i < 4; i++)
-		secret[i] = net_secret[i] + (__force u32)daddr[i];
-	secret[4] = net_secret[4] +
-		(((__force u16)sport << 16) + (__force u16)dport);
-	for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
-		secret[i] = net_secret[i];
-
-	md5_transform(hash, secret);
-
-	*tsoff = sysctl_tcp_timestamps == 1 ? hash[1] : 0;
-	return seq_scale(hash[0]);
+	hash = siphash(&combined, sizeof(combined), net_secret);
+	*tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+	return seq_scale(hash);
 }
 EXPORT_SYMBOL(secure_tcpv6_sequence_number);
 
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport)
 {
-	u32 secret[MD5_MESSAGE_BYTES / 4];
-	u32 hash[MD5_DIGEST_WORDS];
-	u32 i;
-
+	const struct {
+		struct in6_addr saddr;
+		struct in6_addr daddr;
+		__be16 dport;
+		u16 padding1;
+		u32 padding2;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.saddr = *(struct in6_addr *)saddr,
+		.daddr = *(struct in6_addr *)daddr,
+		.dport = dport
+	};
 	net_secret_init();
-	memcpy(hash, saddr, 16);
-	for (i = 0; i < 4; i++)
-		secret[i] = net_secret[i] + (__force u32) daddr[i];
-	secret[4] = net_secret[4] + (__force u32)dport;
-	for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
-		secret[i] = net_secret[i];
-
-	md5_transform(hash, secret);
-
-	return hash[0];
+	return siphash(&combined, sizeof(combined), net_secret);
 }
 EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
@@ -91,33 +91,17 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 			       __be16 sport, __be16 dport, u32 *tsoff)
 {
-	u32 hash[MD5_DIGEST_WORDS];
-
+	u64 hash;
 	net_secret_init();
-	hash[0] = (__force u32)saddr;
-	hash[1] = (__force u32)daddr;
-	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
-	hash[3] = net_secret[15];
-
-	md5_transform(hash, net_secret);
-
-	*tsoff = sysctl_tcp_timestamps == 1 ? hash[1] : 0;
-	return seq_scale(hash[0]);
+	hash = siphash_4u32(saddr, daddr, sport, dport, net_secret);
+	*tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+	return seq_scale(hash);
 }
 
 u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
 {
-	u32 hash[MD5_DIGEST_WORDS];
-
 	net_secret_init();
-	hash[0] = (__force u32)saddr;
-	hash[1] = (__force u32)daddr;
-	hash[2] = (__force u32)dport ^ net_secret[14];
-	hash[3] = net_secret[15];
-
-	md5_transform(hash, net_secret);
-
-	return hash[0];
+	return siphash_4u32(saddr, daddr, dport, 0, net_secret);
 }
 EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
 #endif
@@ -126,21 +110,11 @@ EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
 u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 				__be16 sport, __be16 dport)
 {
-	u32 hash[MD5_DIGEST_WORDS];
 	u64 seq;
-
 	net_secret_init();
-	hash[0] = (__force u32)saddr;
-	hash[1] = (__force u32)daddr;
-	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
-	hash[3] = net_secret[15];
-
-	md5_transform(hash, net_secret);
-
-	seq = hash[0] | (((u64)hash[1]) << 32);
+	seq = siphash_4u32(saddr, daddr, sport, dport, net_secret);
 	seq += ktime_get_real_ns();
 	seq &= (1ull << 48) - 1;
-
 	return seq;
 }
 EXPORT_SYMBOL(secure_dccp_sequence_number);
@@ -149,26 +123,23 @@ EXPORT_SYMBOL(secure_dccp_sequence_number);
 u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
 				  __be16 sport, __be16 dport)
 {
-	u32 secret[MD5_MESSAGE_BYTES / 4];
-	u32 hash[MD5_DIGEST_WORDS];
+	const struct {
+		struct in6_addr saddr;
+		struct in6_addr daddr;
+		__be16 sport;
+		__be16 dport;
+		u32 padding;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.saddr = *(struct in6_addr *)saddr,
+		.daddr = *(struct in6_addr *)daddr,
+		.sport = sport,
+		.dport = dport
+	};
 	u64 seq;
-	u32 i;
-
 	net_secret_init();
-	memcpy(hash, saddr, 16);
-	for (i = 0; i < 4; i++)
-		secret[i] = net_secret[i] + (__force u32)daddr[i];
-	secret[4] = net_secret[4] +
-		(((__force u16)sport << 16) + (__force u16)dport);
-	for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
-		secret[i] = net_secret[i];
-
-	md5_transform(hash, secret);
-
-	seq = hash[0] | (((u64)hash[1]) << 32);
+	seq = siphash(&combined, sizeof(combined), net_secret);
 	seq += ktime_get_real_ns();
 	seq &= (1ull << 48) - 1;
-
 	return seq;
 }
 EXPORT_SYMBOL(secure_dccpv6_sequence_number);
-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1543330 — RE: [PATCH v5 3/4] secure_seq: use SipHash in place of MD5

From: Jason A. Donenfeld
> Sent: 15 December 2016 20:30
> This gives a clear speed and security improvement. Siphash is both
> faster and is more solid crypto than the aging MD5.
> 
> Rather than manually filling MD5 buffers, for IPv6, we simply create
> a layout by a simple anonymous struct, for which gcc generates
> rather efficient code. For IPv4, we pass the values directly to the
> short input convenience functions.
...
> diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
> index 88a8e429fc3e..c80583bf3213 100644
...
> +	const struct {
> +		struct in6_addr saddr;
> +		struct in6_addr daddr;
> +		__be16 sport;
> +		__be16 dport;
> +		u32 padding;
> +	} __aligned(SIPHASH_ALIGNMENT) combined = {
> +		.saddr = *(struct in6_addr *)saddr,
> +		.daddr = *(struct in6_addr *)daddr,
> +		.sport = sport,
> +		.dport = dport
> +	};

I think you should explicitly initialise the 'padding'.
It can do no harm and makes it obvious that it is necessary.

You are still putting over-aligned data on stack.
You only need to align it to the alignment of u64 (not the size of u64).
If an on-stack item has a stronger alignment requirement than the stack
the gcc has to generate two stack frames for the function.

If you assign to each field (instead of using initialisers) then you
can get the alignment by making the first member an anonymous union
of in6_addr and u64.

Oh - and wait a bit longer between revisions.

	David

[toc] | [prev] | [next] | [standalone]

#1543551 — Re: [PATCH v5 3/4] secure_seq: use SipHash in place of MD5

Hi David,

On Fri, Dec 16, 2016 at 10:59 AM, David Laight <David.Laight@aculab.com> wrote:
> You are still putting over-aligned data on stack.
> You only need to align it to the alignment of u64 (not the size of u64).
> If an on-stack item has a stronger alignment requirement than the stack
> the gcc has to generate two stack frames for the function.

Yesterday, folks were saying that sometimes 32-bit platforms need
8-byte alignment for certain 64-bit operations, so I shouldn't fall
back to 4-byte alignment there. But actually, looking at this more
closely, I can just make SIPHASH_ALIGNMENT == __alignof__(u64), which
will take care of all possible concerns, since gcc knows best which
platforms need what alignment. Thanks for making this clear to me with
"the alignment of u64 (not the size of u64)".

> Oh - and wait a bit longer between revisions.

Okay. We can be turtles.

Jason

[toc] | [prev] | [next] | [standalone]

#1543061 — [PATCH v5 2/4] siphash: add Nu{32,64} helpers

These restore parity with the jhash interface by providing high
performance helpers for common input sizes.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Tom Herbert <tom@herbertland.com>
---
 include/linux/siphash.h |  33 ++++++++++
 lib/siphash.c           | 157 +++++++++++++++++++++++++++++++++++++-----------
 lib/test_siphash.c      |  18 ++++++
 3 files changed, 172 insertions(+), 36 deletions(-)

diff --git a/include/linux/siphash.h b/include/linux/siphash.h
index 145cf5667078..6f5a08a0fc7e 100644
--- a/include/linux/siphash.h
+++ b/include/linux/siphash.h
@@ -29,4 +29,37 @@ static inline u64 siphash_unaligned(const void *data, size_t len,
 u64 siphash_unaligned(const void *data, size_t len, const siphash_key_t key);
 #endif
 
+u64 siphash_1u64(const u64 a, const siphash_key_t key);
+u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t key);
+u64 siphash_3u64(const u64 a, const u64 b, const u64 c,
+		 const siphash_key_t key);
+u64 siphash_4u64(const u64 a, const u64 b, const u64 c, const u64 d,
+		 const siphash_key_t key);
+
+static inline u64 siphash_2u32(const u32 a, const u32 b, const siphash_key_t key)
+{
+	return siphash_1u64((u64)b << 32 | a, key);
+}
+
+static inline u64 siphash_4u32(const u32 a, const u32 b, const u32 c, const u32 d,
+			       const siphash_key_t key)
+{
+	return siphash_2u64((u64)b << 32 | a, (u64)d << 32 | c, key);
+}
+
+static inline u64 siphash_6u32(const u32 a, const u32 b, const u32 c, const u32 d,
+			       const u32 e, const u32 f, const siphash_key_t key)
+{
+	return siphash_3u64((u64)b << 32 | a, (u64)d << 32 | c, (u64)f << 32 | e,
+			    key);
+}
+
+static inline u64 siphash_8u32(const u32 a, const u32 b, const u32 c, const u32 d,
+			       const u32 e, const u32 f, const u32 g, const u32 h,
+			       const siphash_key_t key)
+{
+	return siphash_4u64((u64)b << 32 | a, (u64)d << 32 | c, (u64)f << 32 | e,
+			    (u64)h << 32 | g, key);
+}
+
 #endif /* _LINUX_SIPHASH_H */
diff --git a/lib/siphash.c b/lib/siphash.c
index afc13cbb1b78..970c083ab06a 100644
--- a/lib/siphash.c
+++ b/lib/siphash.c
@@ -25,6 +25,29 @@
 	v2 += v1; v1 = rol64(v1, 17); v1 ^= v2; v2 = rol64(v2, 32); \
 	} while(0)
 
+#define PREAMBLE(len) \
+	u64 v0 = 0x736f6d6570736575ULL; \
+	u64 v1 = 0x646f72616e646f6dULL; \
+	u64 v2 = 0x6c7967656e657261ULL; \
+	u64 v3 = 0x7465646279746573ULL; \
+	u64 b = ((u64)len) << 56; \
+	v3 ^= key[1]; \
+	v2 ^= key[0]; \
+	v1 ^= key[1]; \
+	v0 ^= key[0];
+
+#define POSTAMBLE \
+	v3 ^= b; \
+	SIPROUND; \
+	SIPROUND; \
+	v0 ^= b; \
+	v2 ^= 0xff; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	return (v0 ^ v1) ^ (v2 ^ v3);
+
 /**
  * siphash - compute 64-bit siphash PRF value
  * @data: buffer to hash, must be aligned to SIPHASH_ALIGNMENT
@@ -33,18 +56,10 @@
  */
 u64 siphash(const void *data, size_t len, const siphash_key_t key)
 {
-	u64 v0 = 0x736f6d6570736575ULL;
-	u64 v1 = 0x646f72616e646f6dULL;
-	u64 v2 = 0x6c7967656e657261ULL;
-	u64 v3 = 0x7465646279746573ULL;
-	u64 b = ((u64)len) << 56;
-	u64 m;
 	const u8 *end = data + len - (len % sizeof(u64));
 	const u8 left = len & (sizeof(u64) - 1);
-	v3 ^= key[1];
-	v2 ^= key[0];
-	v1 ^= key[1];
-	v0 ^= key[0];
+	u64 m;
+	PREAMBLE(len)
 	for (; data != end; data += sizeof(u64)) {
 		m = le64_to_cpup(data);
 		v3 ^= m;
@@ -67,16 +82,7 @@ u64 siphash(const void *data, size_t len, const siphash_key_t key)
 	case 1: b |= end[0];
 	}
 #endif
-	v3 ^= b;
-	SIPROUND;
-	SIPROUND;
-	v0 ^= b;
-	v2 ^= 0xff;
-	SIPROUND;
-	SIPROUND;
-	SIPROUND;
-	SIPROUND;
-	return (v0 ^ v1) ^ (v2 ^ v3);
+	POSTAMBLE
 }
 EXPORT_SYMBOL(siphash);
 
@@ -89,18 +95,10 @@ EXPORT_SYMBOL(siphash);
  */
 u64 siphash_unaligned(const void *data, size_t len, const siphash_key_t key)
 {
-	u64 v0 = 0x736f6d6570736575ULL;
-	u64 v1 = 0x646f72616e646f6dULL;
-	u64 v2 = 0x6c7967656e657261ULL;
-	u64 v3 = 0x7465646279746573ULL;
-	u64 b = ((u64)len) << 56;
-	u64 m;
 	const u8 *end = data + len - (len % sizeof(u64));
 	const u8 left = len & (sizeof(u64) - 1);
-	v3 ^= key[1];
-	v2 ^= key[0];
-	v1 ^= key[1];
-	v0 ^= key[0];
+	u64 m;
+	PREAMBLE(len)
 	for (; data != end; data += sizeof(u64)) {
 		m = get_unaligned_le64(data);
 		v3 ^= m;
@@ -123,16 +121,103 @@ u64 siphash_unaligned(const void *data, size_t len, const siphash_key_t key)
 	case 1: b |= bytes[0];
 	}
 #endif
-	v3 ^= b;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_unaligned);
+#endif
+
+/**
+ * siphash_1u64 - compute 64-bit siphash PRF value of a u64
+ * @first: first u64
+ * @key: the siphash key
+ */
+u64 siphash_1u64(const u64 first, const siphash_key_t key)
+{
+	PREAMBLE(8)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_1u64);
+
+/**
+ * siphash_2u64 - compute 64-bit siphash PRF value of 2 u64
+ * @first: first u64
+ * @second: second u64
+ * @key: the siphash key
+ */
+u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t key)
+{
+	PREAMBLE(16)
+	v3 ^= first;
 	SIPROUND;
 	SIPROUND;
-	v0 ^= b;
-	v2 ^= 0xff;
+	v0 ^= first;
+	v3 ^= second;
 	SIPROUND;
 	SIPROUND;
+	v0 ^= second;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_2u64);
+
+/**
+ * siphash_3u64 - compute 64-bit siphash PRF value of 3 u64
+ * @first: first u64
+ * @second: second u64
+ * @third: third u64
+ * @key: the siphash key
+ */
+u64 siphash_3u64(const u64 first, const u64 second, const u64 third,
+		 const siphash_key_t key)
+{
+	PREAMBLE(24)
+	v3 ^= first;
 	SIPROUND;
 	SIPROUND;
-	return (v0 ^ v1) ^ (v2 ^ v3);
+	v0 ^= first;
+	v3 ^= second;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= second;
+	v3 ^= third;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= third;
+	POSTAMBLE
 }
-EXPORT_SYMBOL(siphash_unaligned);
-#endif
+EXPORT_SYMBOL(siphash_3u64);
+
+/**
+ * siphash_4u64 - compute 64-bit siphash PRF value of 4 u64
+ * @first: first u64
+ * @second: second u64
+ * @third: third u64
+ * @forth: forth u64
+ * @key: the siphash key
+ */
+u64 siphash_4u64(const u64 first, const u64 second, const u64 third,
+		 const u64 forth, const siphash_key_t key)
+{
+	PREAMBLE(32)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= second;
+	v3 ^= third;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= third;
+	v3 ^= forth;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= forth;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_4u64);
diff --git a/lib/test_siphash.c b/lib/test_siphash.c
index 93549e4e22c5..1635189c171f 100644
--- a/lib/test_siphash.c
+++ b/lib/test_siphash.c
@@ -67,6 +67,24 @@ static int __init siphash_test_init(void)
 			ret = -EINVAL;
 		}
 	}
+	if (siphash_1u64(0x0706050403020100ULL, test_key) != test_vectors[8]) {
+		pr_info("self-test 1u64: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_2u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL, test_key) != test_vectors[16]) {
+		pr_info("self-test 2u64: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_3u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL,
+			 0x1716151413121110ULL, test_key) != test_vectors[24]) {
+		pr_info("self-test 3u64: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_4u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL,
+			 0x1716151413121110ULL, 0x1f1e1d1c1b1a1918ULL, test_key) != test_vectors[32]) {
+		pr_info("self-test 4u64: FAIL\n");
+		ret = -EINVAL;
+	}
 	if (!ret)
 		pr_info("self-tests: pass\n");
 	return ret;
-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1543348 — RE: [PATCH v5 2/4] siphash: add Nu{32,64} helpers

From: Jason A. Donenfeld
> Sent: 15 December 2016 20:30
> These restore parity with the jhash interface by providing high
> performance helpers for common input sizes.
...
> +#define PREAMBLE(len) \
> +	u64 v0 = 0x736f6d6570736575ULL; \
> +	u64 v1 = 0x646f72616e646f6dULL; \
> +	u64 v2 = 0x6c7967656e657261ULL; \
> +	u64 v3 = 0x7465646279746573ULL; \
> +	u64 b = ((u64)len) << 56; \
> +	v3 ^= key[1]; \
> +	v2 ^= key[0]; \
> +	v1 ^= key[1]; \
> +	v0 ^= key[0];

Isn't that equivalent to:
	v0 = key[0];
	v1 = key[1];
	v2 = key[0] ^ (0x736f6d6570736575ULL ^ 0x646f72616e646f6dULL);
	v3 = key[1] ^ (0x646f72616e646f6dULL ^ 0x7465646279746573ULL);

Those constants also look like ASCII strings.
What cryptographic analysis has been done on the values?

	David

[toc] | [prev] | [next] | [standalone]

#1543535 — RE: [PATCH v5 2/4] siphash: add Nu{32,64} helpers

Jason A. Donenfeld wrote:
> Isn't that equivalent to:
>	v0 = key[0];
>	v1 = key[1];
>	v2 = key[0] ^ (0x736f6d6570736575ULL ^ 0x646f72616e646f6dULL);
>	v3 = key[1] ^ (0x646f72616e646f6dULL ^ 0x7465646279746573ULL);

(Pre-XORing key[] with the first two constants which, if the constants
are random in the first place, can be a no-op.)  Other than the typo
in the v2 line, yes.  If they key is non-public, then you can xor an
arbitrary constant in to both halves to slightly speed up the startup.

(Nits: There's a typo in the v2 line, you don't need to parenthesize
associative operators like xor, and the "ull" suffix is redundant here.)

> Those constants also look like ASCII strings.

They are.  The ASCII is "somepseudorandomlygeneratedbytes".

> What cryptographic analysis has been done on the values?

They're "nothing up my sleeve numbers".

They're arbitrary numbers, and almost any other values would do exactly
as well.  The main properties are:

1) They're different (particulatly v0 != v2 and v1 != v3), and
2) Neither they, nor their xor, is rotationally symmetric like 0x55555555.
   (Because SipHash is mostly rotationally symmetric, broken only by the
   interruption of the carry chain at the msbit, it helps slightly
   to break this up at the beginning.)

Those exact values only matter for portability.  If you don't need anyone
else to be able to compute matching outputs, then you could use any other
convenient constants (like the MD5 round constants).

[toc] | [prev] | [next] | [standalone]

#1543187 — [PATCH v6 4/5] md5: remove from lib and only live in crypto

The md5_transform function is no longer used any where in the tree,
except for the crypto api's actual implementation of md5, so we can drop
the function from lib and put it as a static function of the crypto
file, where it belongs. There should be no new users of md5_transform,
anyway, since there are more modern ways of doing what it once achieved.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 crypto/md5.c | 95 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 lib/Makefile |  2 +-
 lib/md5.c    | 95 ------------------------------------------------------------
 3 files changed, 95 insertions(+), 97 deletions(-)
 delete mode 100644 lib/md5.c

diff --git a/crypto/md5.c b/crypto/md5.c
index 2355a7c25c45..f7ae1a48225b 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -21,9 +21,11 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/types.h>
-#include <linux/cryptohash.h>
 #include <asm/byteorder.h>
 
+#define MD5_DIGEST_WORDS 4
+#define MD5_MESSAGE_BYTES 64
+
 const u8 md5_zero_message_hash[MD5_DIGEST_SIZE] = {
 	0xd4, 0x1d, 0x8c, 0xd9, 0x8f, 0x00, 0xb2, 0x04,
 	0xe9, 0x80, 0x09, 0x98, 0xec, 0xf8, 0x42, 0x7e,
@@ -47,6 +49,97 @@ static inline void cpu_to_le32_array(u32 *buf, unsigned int words)
 	}
 }
 
+#define F1(x, y, z)	(z ^ (x & (y ^ z)))
+#define F2(x, y, z)	F1(z, x, y)
+#define F3(x, y, z)	(x ^ y ^ z)
+#define F4(x, y, z)	(y ^ (x | ~z))
+
+#define MD5STEP(f, w, x, y, z, in, s) \
+	(w += f(x, y, z) + in, w = (w<<s | w>>(32-s)) + x)
+
+static void md5_transform(__u32 *hash, __u32 const *in)
+{
+	u32 a, b, c, d;
+
+	a = hash[0];
+	b = hash[1];
+	c = hash[2];
+	d = hash[3];
+
+	MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
+	MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
+	MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
+	MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
+	MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
+	MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
+	MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
+	MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
+	MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
+	MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
+	MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
+	MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
+	MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
+	MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
+	MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
+	MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
+
+	MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
+	MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
+	MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
+	MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
+	MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
+	MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
+	MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
+	MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
+	MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
+	MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
+	MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
+	MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
+	MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
+	MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
+	MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
+	MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
+
+	MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
+	MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
+	MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
+	MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
+	MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
+	MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
+	MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
+	MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
+	MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
+	MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
+	MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
+	MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
+	MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
+	MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
+	MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
+	MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
+
+	MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
+	MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
+	MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
+	MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
+	MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
+	MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
+	MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
+	MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
+	MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
+	MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
+	MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
+	MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
+	MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
+	MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
+	MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
+	MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
+
+	hash[0] += a;
+	hash[1] += b;
+	hash[2] += c;
+	hash[3] += d;
+}
+
 static inline void md5_transform_helper(struct md5_state *ctx)
 {
 	le32_to_cpu_array(ctx->block, sizeof(ctx->block) / sizeof(u32));
diff --git a/lib/Makefile b/lib/Makefile
index 71d398b04a74..1079152607e0 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -19,7 +19,7 @@ KCOV_INSTRUMENT_dynamic_debug.o := n
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o timerqueue.o\
 	 idr.o int_sqrt.o extable.o \
-	 sha1.o chacha20.o md5.o irq_regs.o argv_split.o \
+	 sha1.o chacha20.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o \
diff --git a/lib/md5.c b/lib/md5.c
deleted file mode 100644
index bb0cd01d356d..000000000000
--- a/lib/md5.c
+++ /dev/null
@@ -1,95 +0,0 @@
-#include <linux/compiler.h>
-#include <linux/export.h>
-#include <linux/cryptohash.h>
-
-#define F1(x, y, z)	(z ^ (x & (y ^ z)))
-#define F2(x, y, z)	F1(z, x, y)
-#define F3(x, y, z)	(x ^ y ^ z)
-#define F4(x, y, z)	(y ^ (x | ~z))
-
-#define MD5STEP(f, w, x, y, z, in, s) \
-	(w += f(x, y, z) + in, w = (w<<s | w>>(32-s)) + x)
-
-void md5_transform(__u32 *hash, __u32 const *in)
-{
-	u32 a, b, c, d;
-
-	a = hash[0];
-	b = hash[1];
-	c = hash[2];
-	d = hash[3];
-
-	MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
-	MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
-	MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
-	MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
-	MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
-	MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
-	MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
-	MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
-	MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
-	MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
-	MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
-	MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
-	MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
-	MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
-	MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
-	MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
-
-	MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
-	MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
-	MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
-	MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
-	MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
-	MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
-	MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
-	MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
-	MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
-	MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
-	MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
-	MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
-	MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
-	MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
-	MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
-	MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
-
-	MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
-	MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
-	MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
-	MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
-	MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
-	MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
-	MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
-	MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
-	MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
-	MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
-	MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
-	MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
-	MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
-	MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
-	MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
-	MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
-
-	MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
-	MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
-	MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
-	MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
-	MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
-	MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
-	MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
-	MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
-	MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
-	MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
-	MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
-	MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
-	MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
-	MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
-	MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
-	MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
-
-	hash[0] += a;
-	hash[1] += b;
-	hash[2] += c;
-	hash[3] += d;
-}
-EXPORT_SYMBOL(md5_transform);
-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1543188 — [PATCH v6 2/5] secure_seq: use SipHash in place of MD5

This gives a clear speed and security improvement. Siphash is both
faster and is more solid crypto than the aging MD5.

Rather than manually filling MD5 buffers, for IPv6, we simply create
a layout by a simple anonymous struct, for which gcc generates
rather efficient code. For IPv4, we pass the values directly to the
short input convenience functions.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Miller <davem@davemloft.net>
Cc: David Laight <David.Laight@aculab.com>
Cc: Tom Herbert <tom@herbertland.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
 net/core/secure_seq.c | 133 ++++++++++++++++++++------------------------------
 1 file changed, 52 insertions(+), 81 deletions(-)

diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 88a8e429fc3e..c80583bf3213 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -1,3 +1,5 @@
+/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */
+
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/cryptohash.h>
@@ -8,14 +10,14 @@
 #include <linux/ktime.h>
 #include <linux/string.h>
 #include <linux/net.h>
-
+#include <linux/siphash.h>
 #include <net/secure_seq.h>
 
 #if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET)
+#include <linux/in6.h>
 #include <net/tcp.h>
-#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
 
-static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
+static siphash_key_t net_secret;
 
 static __always_inline void net_secret_init(void)
 {
@@ -44,44 +46,42 @@ static u32 seq_scale(u32 seq)
 u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 				 __be16 sport, __be16 dport, u32 *tsoff)
 {
-	u32 secret[MD5_MESSAGE_BYTES / 4];
-	u32 hash[MD5_DIGEST_WORDS];
-	u32 i;
-
+	const struct {
+		struct in6_addr saddr;
+		struct in6_addr daddr;
+		__be16 sport;
+		__be16 dport;
+		u32 padding;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.saddr = *(struct in6_addr *)saddr,
+		.daddr = *(struct in6_addr *)daddr,
+		.sport = sport,
+		.dport = dport
+	};
+	u64 hash;
 	net_secret_init();
-	memcpy(hash, saddr, 16);
-	for (i = 0; i < 4; i++)
-		secret[i] = net_secret[i] + (__force u32)daddr[i];
-	secret[4] = net_secret[4] +
-		(((__force u16)sport << 16) + (__force u16)dport);
-	for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
-		secret[i] = net_secret[i];
-
-	md5_transform(hash, secret);
-
-	*tsoff = sysctl_tcp_timestamps == 1 ? hash[1] : 0;
-	return seq_scale(hash[0]);
+	hash = siphash(&combined, sizeof(combined), net_secret);
+	*tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+	return seq_scale(hash);
 }
 EXPORT_SYMBOL(secure_tcpv6_sequence_number);
 
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport)
 {
-	u32 secret[MD5_MESSAGE_BYTES / 4];
-	u32 hash[MD5_DIGEST_WORDS];
-	u32 i;
-
+	const struct {
+		struct in6_addr saddr;
+		struct in6_addr daddr;
+		__be16 dport;
+		u16 padding1;
+		u32 padding2;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.saddr = *(struct in6_addr *)saddr,
+		.daddr = *(struct in6_addr *)daddr,
+		.dport = dport
+	};
 	net_secret_init();
-	memcpy(hash, saddr, 16);
-	for (i = 0; i < 4; i++)
-		secret[i] = net_secret[i] + (__force u32) daddr[i];
-	secret[4] = net_secret[4] + (__force u32)dport;
-	for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
-		secret[i] = net_secret[i];
-
-	md5_transform(hash, secret);
-
-	return hash[0];
+	return siphash(&combined, sizeof(combined), net_secret);
 }
 EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
@@ -91,33 +91,17 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 			       __be16 sport, __be16 dport, u32 *tsoff)
 {
-	u32 hash[MD5_DIGEST_WORDS];
-
+	u64 hash;
 	net_secret_init();
-	hash[0] = (__force u32)saddr;
-	hash[1] = (__force u32)daddr;
-	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
-	hash[3] = net_secret[15];
-
-	md5_transform(hash, net_secret);
-
-	*tsoff = sysctl_tcp_timestamps == 1 ? hash[1] : 0;
-	return seq_scale(hash[0]);
+	hash = siphash_4u32(saddr, daddr, sport, dport, net_secret);
+	*tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+	return seq_scale(hash);
 }
 
 u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
 {
-	u32 hash[MD5_DIGEST_WORDS];
-
 	net_secret_init();
-	hash[0] = (__force u32)saddr;
-	hash[1] = (__force u32)daddr;
-	hash[2] = (__force u32)dport ^ net_secret[14];
-	hash[3] = net_secret[15];
-
-	md5_transform(hash, net_secret);
-
-	return hash[0];
+	return siphash_4u32(saddr, daddr, dport, 0, net_secret);
 }
 EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
 #endif
@@ -126,21 +110,11 @@ EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
 u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 				__be16 sport, __be16 dport)
 {
-	u32 hash[MD5_DIGEST_WORDS];
 	u64 seq;
-
 	net_secret_init();
-	hash[0] = (__force u32)saddr;
-	hash[1] = (__force u32)daddr;
-	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
-	hash[3] = net_secret[15];
-
-	md5_transform(hash, net_secret);
-
-	seq = hash[0] | (((u64)hash[1]) << 32);
+	seq = siphash_4u32(saddr, daddr, sport, dport, net_secret);
 	seq += ktime_get_real_ns();
 	seq &= (1ull << 48) - 1;
-
 	return seq;
 }
 EXPORT_SYMBOL(secure_dccp_sequence_number);
@@ -149,26 +123,23 @@ EXPORT_SYMBOL(secure_dccp_sequence_number);
 u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
 				  __be16 sport, __be16 dport)
 {
-	u32 secret[MD5_MESSAGE_BYTES / 4];
-	u32 hash[MD5_DIGEST_WORDS];
+	const struct {
+		struct in6_addr saddr;
+		struct in6_addr daddr;
+		__be16 sport;
+		__be16 dport;
+		u32 padding;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.saddr = *(struct in6_addr *)saddr,
+		.daddr = *(struct in6_addr *)daddr,
+		.sport = sport,
+		.dport = dport
+	};
 	u64 seq;
-	u32 i;
-
 	net_secret_init();
-	memcpy(hash, saddr, 16);
-	for (i = 0; i < 4; i++)
-		secret[i] = net_secret[i] + (__force u32)daddr[i];
-	secret[4] = net_secret[4] +
-		(((__force u16)sport << 16) + (__force u16)dport);
-	for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
-		secret[i] = net_secret[i];
-
-	md5_transform(hash, secret);
-
-	seq = hash[0] | (((u64)hash[1]) << 32);
+	seq = siphash(&combined, sizeof(combined), net_secret);
 	seq += ktime_get_real_ns();
 	seq &= (1ull << 48) - 1;
-
 	return seq;
 }
 EXPORT_SYMBOL(secure_dccpv6_sequence_number);
-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1543189 — [PATCH v6 5/5] syncookies: use SipHash in place of SHA1

SHA1 is slower and less secure than SipHash, and so replacing syncookie
generation with SipHash makes natural sense. Some BSDs have been doing
this for several years in fact.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 net/ipv4/syncookies.c | 20 ++++----------------
 net/ipv6/syncookies.c | 37 ++++++++++++++++---------------------
 2 files changed, 20 insertions(+), 37 deletions(-)

diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 3e88467d70ee..03bb068f8888 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -13,13 +13,13 @@
 #include <linux/tcp.h>
 #include <linux/slab.h>
 #include <linux/random.h>
-#include <linux/cryptohash.h>
+#include <linux/siphash.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <net/tcp.h>
 #include <net/route.h>
 
-static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
+static siphash_key_t syncookie_secret[2] __read_mostly;
 
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
@@ -48,24 +48,12 @@ static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
 #define TSBITS	6
 #define TSMASK	(((__u32)1 << TSBITS) - 1)
 
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv4_cookie_scratch);
-
 static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 		       u32 count, int c)
 {
-	__u32 *tmp;
-
 	net_get_random_once(syncookie_secret, sizeof(syncookie_secret));
-
-	tmp  = this_cpu_ptr(ipv4_cookie_scratch);
-	memcpy(tmp + 4, syncookie_secret[c], sizeof(syncookie_secret[c]));
-	tmp[0] = (__force u32)saddr;
-	tmp[1] = (__force u32)daddr;
-	tmp[2] = ((__force u32)sport << 16) + (__force u32)dport;
-	tmp[3] = count;
-	sha_transform(tmp + 16, (__u8 *)tmp, tmp + 16 + 5);
-
-	return tmp[17];
+	return siphash_4u32(saddr, daddr, (u32)sport << 16 | dport, count,
+			    syncookie_secret[c]);
 }
 
 
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index a4d49760bf43..04d19e89a3e0 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -16,7 +16,7 @@
 
 #include <linux/tcp.h>
 #include <linux/random.h>
-#include <linux/cryptohash.h>
+#include <linux/siphash.h>
 #include <linux/kernel.h>
 #include <net/ipv6.h>
 #include <net/tcp.h>
@@ -24,7 +24,7 @@
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
 
-static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
+static siphash_key_t syncookie6_secret[2] __read_mostly;
 
 /* RFC 2460, Section 8.3:
  * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
@@ -41,30 +41,25 @@ static __u16 const msstab[] = {
 	9000 - 60,
 };
 
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv6_cookie_scratch);
-
 static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr,
 		       __be16 sport, __be16 dport, u32 count, int c)
 {
-	__u32 *tmp;
+	const struct {
+		struct in6_addr saddr;
+		struct in6_addr daddr;
+		u32 count;
+		u16 sport;
+		u16 dport;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.saddr = *saddr,
+		.daddr = *daddr,
+		.count = count,
+		.sport = sport,
+		.dport = dport
+	};
 
 	net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret));
-
-	tmp  = this_cpu_ptr(ipv6_cookie_scratch);
-
-	/*
-	 * we have 320 bits of information to hash, copy in the remaining
-	 * 192 bits required for sha_transform, from the syncookie6_secret
-	 * and overwrite the digest with the secret
-	 */
-	memcpy(tmp + 10, syncookie6_secret[c], 44);
-	memcpy(tmp, saddr, 16);
-	memcpy(tmp + 4, daddr, 16);
-	tmp[8] = ((__force u32)sport << 16) + (__force u32)dport;
-	tmp[9] = count;
-	sha_transform(tmp + 16, (__u8 *)tmp, tmp + 16 + 5);
-
-	return tmp[17];
+	return siphash(&combined, sizeof(combined), syncookie6_secret[c]);
 }
 
 static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1543190 — [PATCH v6 0/5] The SipHash Patchset

Hey again,

This keeps getting more ambitious, which is good I suppose. If the frequency
of new versioned patchsets is too high for LKML and not customary, please let
me know. Otherwise, read on to see what's new this time...

With Hannes' suggestion, there is now only one siphash() function, which will
use the faster aligned version by compile-time constant folding. Additionally,
I now use constant folding to optionally switch to the helper siphash_Nu64
functions that are a bit faster for data of length 8, 16, 24, and 32. So, the
result is that you use siphash(data, len, key) if you have a buffer of sorts,
and then everything is taken care of for you. Or, if you have a series of
integers, you can opt to use siphash_Nu{32,64} functions instead. The basic
API is now complete.

After replacing MD5 in secure sequence number generation and the RNG, it
turned out that md5_transform wasn't used any place else in the tree, so
finally -- this is something to rejoice over -- lib/md5.c has been deleted and
now that function lives as a static function in crypto/md5.c where it belongs.

Meanwhile, it seems that sha_transform is used in places where SipHash would
be more fitting, so the IPv4 and IPv6 syncookies implementation now uses
SipHash, which should speed up TCP performance. Some BSDs already do this.

I'd like to replace sha_transform in addrconf, but that code is a bit gnarley,
so I don't want to be too meddlesome. I'm not entirely convinced either that
SipHash is a good choice for it. But I'm open to discussion here, so if you
have an opinion, please speak up.

If you've been following the evolution of this patchset, and think that
certain patches in it are fine, please do lend me your Reviewed-by to carry
into any subsequent versions, so that in case you disappear your useful
reviews will still keep the ball moving.

Thanks for all the great feedback thus far.

Jason

Jason A. Donenfeld (5):
  siphash: add cryptographically secure PRF
  secure_seq: use SipHash in place of MD5
  random: use SipHash in place of MD5
  md5: remove from lib and only live in crypto
  syncookies: use SipHash in place of SHA1

 MAINTAINERS             |   7 ++
 crypto/md5.c            |  95 +++++++++++++++++++++-
 drivers/char/random.c   |  32 +++-----
 include/linux/siphash.h |  86 ++++++++++++++++++++
 lib/Kconfig.debug       |   6 +-
 lib/Makefile            |   7 +-
 lib/md5.c               |  95 ----------------------
 lib/siphash.c           | 210 ++++++++++++++++++++++++++++++++++++++++++++++++
 lib/test_siphash.c      | 101 +++++++++++++++++++++++
 net/core/secure_seq.c   | 133 ++++++++++++------------------
 net/ipv4/syncookies.c   |  20 +----
 net/ipv6/syncookies.c   |  37 ++++-----
 12 files changed, 590 insertions(+), 239 deletions(-)
 create mode 100644 include/linux/siphash.h
 delete mode 100644 lib/md5.c
 create mode 100644 lib/siphash.c
 create mode 100644 lib/test_siphash.c

-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1543191 — [PATCH v6 3/5] random: use SipHash in place of MD5

This duplicates the current algorithm for get_random_int/long, but uses
siphash instead. This comes with several benefits. It's certainly
faster and more cryptographically secure than MD5. This patch also
separates hashed fields into three values instead of one, in order to
increase diffusion.

The previous MD5 algorithm used a per-cpu MD5 state, which caused
successive calls to the function to chain upon each other. While it's
not entirely clear that this kind of chaining is absolutely necessary
when using a secure PRF like siphash, it can't hurt, and the timing of
the call chain does add a degree of natural entropy. So, in keeping with
this design, instead of the massive per-cpu 64-byte MD5 state, there is
instead a per-cpu previously returned value for chaining.

The speed benefits are substantial:

                | siphash | md5    | speedup |
		------------------------------
get_random_long | 137130  | 415983 | 3.03x   |
get_random_int  | 86384   | 343323 | 3.97x   |

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com>
Cc: Ted Tso <tytso@mit.edu>
---
 drivers/char/random.c | 32 +++++++++++++-------------------
 1 file changed, 13 insertions(+), 19 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index d6876d506220..a51f0ff43f00 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -262,6 +262,7 @@
 #include <linux/syscalls.h>
 #include <linux/completion.h>
 #include <linux/uuid.h>
+#include <linux/siphash.h>
 #include <crypto/chacha20.h>
 
 #include <asm/processor.h>
@@ -2042,7 +2043,7 @@ struct ctl_table random_table[] = {
 };
 #endif 	/* CONFIG_SYSCTL */
 
-static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
+static siphash_key_t random_int_secret;
 
 int random_int_secret_init(void)
 {
@@ -2050,8 +2051,7 @@ int random_int_secret_init(void)
 	return 0;
 }
 
-static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
-		__aligned(sizeof(unsigned long));
+static DEFINE_PER_CPU(u64, get_random_int_chaining);
 
 /*
  * Get a random word for internal kernel use only. Similar to urandom but
@@ -2061,19 +2061,16 @@ static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
  */
 unsigned int get_random_int(void)
 {
-	__u32 *hash;
 	unsigned int ret;
+	u64 *chaining;
 
 	if (arch_get_random_int(&ret))
 		return ret;
 
-	hash = get_cpu_var(get_random_int_hash);
-
-	hash[0] += current->pid + jiffies + random_get_entropy();
-	md5_transform(hash, random_int_secret);
-	ret = hash[0];
-	put_cpu_var(get_random_int_hash);
-
+	chaining = &get_cpu_var(get_random_int_chaining);
+	ret = *chaining = siphash_3u64(*chaining, jiffies, random_get_entropy() +
+				       current->pid, random_int_secret);
+	put_cpu_var(get_random_int_chaining);
 	return ret;
 }
 EXPORT_SYMBOL(get_random_int);
@@ -2083,19 +2080,16 @@ EXPORT_SYMBOL(get_random_int);
  */
 unsigned long get_random_long(void)
 {
-	__u32 *hash;
 	unsigned long ret;
+	u64 *chaining;
 
 	if (arch_get_random_long(&ret))
 		return ret;
 
-	hash = get_cpu_var(get_random_int_hash);
-
-	hash[0] += current->pid + jiffies + random_get_entropy();
-	md5_transform(hash, random_int_secret);
-	ret = *(unsigned long *)hash;
-	put_cpu_var(get_random_int_hash);
-
+	chaining = &get_cpu_var(get_random_int_chaining);
+	ret = *chaining = siphash_3u64(*chaining, jiffies, random_get_entropy() +
+				       current->pid, random_int_secret);
+	put_cpu_var(get_random_int_chaining);
 	return ret;
 }
 EXPORT_SYMBOL(get_random_long);
-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1543767 — Re: [PATCH v6 3/5] random: use SipHash in place of MD5

On Thu, Dec 15, 2016 at 7:03 PM, Jason A. Donenfeld <Jason@zx2c4.com> wrote:
> -static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
> -               __aligned(sizeof(unsigned long));
> +static DEFINE_PER_CPU(u64, get_random_int_chaining);
>

[...]

>  unsigned long get_random_long(void)
>  {
> -       __u32 *hash;
>         unsigned long ret;
> +       u64 *chaining;
>
>         if (arch_get_random_long(&ret))
>                 return ret;
>
> -       hash = get_cpu_var(get_random_int_hash);
> -
> -       hash[0] += current->pid + jiffies + random_get_entropy();
> -       md5_transform(hash, random_int_secret);
> -       ret = *(unsigned long *)hash;
> -       put_cpu_var(get_random_int_hash);
> -
> +       chaining = &get_cpu_var(get_random_int_chaining);
> +       ret = *chaining = siphash_3u64(*chaining, jiffies, random_get_entropy() +
> +                                      current->pid, random_int_secret);
> +       put_cpu_var(get_random_int_chaining);
>         return ret;
>  }

I think it would be nice to try to strenghen the PRNG construction.
FWIW, I'm not an expert in PRNGs, and there's fairly extensive
literature, but I can at least try.  Here are some properties I'd
like:

1. A one-time leak of memory contents doesn't ruin security until
reboot.  This is especially value across suspend and/or hibernation.

2. An attack with a low work factor (2^64?) shouldn't break the scheme
until reboot.


This is effectively doing:

output = H(prev_output, weak "entropy", per-boot secret);

One unfortunately downside is that, if used in a context where an
attacker can see a single output, the attacker learns the chaining
value.  If the attacker can guess the entropy, then, with 2^64 work,
they learn the secret, and they can predict future outputs.

I would advocate adding two types of improvements.  First, re-seed it
every now and then (every 128 calls?) by just replacing both the
chaining value and the percpu secret with fresh CSPRNG output.
Second, change the mode so that an attacker doesn't learn so much
internal state.  For example:

output = H(old_chain, entropy, secret);
new_chain = old_chain + entropy + output;

This increases the effort needed to brute-force the internal state
from 2^64 to 2^128 (barring any weaknesses in the scheme).

Also, can we not call this get_random_int()?  get_random_int() sounds
too much like get_random_bytes(), and the latter is intended to be a
real CSPRNG.  Can we call it get_weak_random_int() or similar?

--Andy

[toc] | [prev] | [next] | [standalone]

#1543192 — [PATCH v6 1/5] siphash: add cryptographically secure PRF

SipHash is a 64-bit keyed hash function that is actually a
cryptographically secure PRF, like HMAC. Except SipHash is super fast,
and is meant to be used as a hashtable keyed lookup function, or as a
general PRF for short input use cases, such as sequence numbers or RNG
chaining.

For the first usage:

There are a variety of attacks known as "hashtable poisoning" in which an
attacker forms some data such that the hash of that data will be the
same, and then preceeds to fill up all entries of a hashbucket. This is
a realistic and well-known denial-of-service vector. Currently
hashtables use jhash, which is fast but not secure, and some kind of
rotating key scheme (or none at all, which isn't good). SipHash is meant
as a replacement for jhash in these cases.

There are a modicum of places in the kernel that are vulnerable to
hashtable poisoning attacks, either via userspace vectors or network
vectors, and there's not a reliable mechanism inside the kernel at the
moment to fix it. The first step toward fixing these issues is actually
getting a secure primitive into the kernel for developers to use. Then
we can, bit by bit, port things over to it as deemed appropriate.

While SipHash is extremely fast for a cryptographically secure function,
it is likely a bit slower than the insecure jhash, and so replacements
will be evaluated on a case-by-case basis based on whether or not the
difference in speed is negligible and whether or not the current jhash usage
poses a real security risk.

For the second usage:

A few places in the kernel are using MD5 or SHA1 for creating secure
sequence numbers, syn cookies, port numbers, or fast random numbers.
SipHash is a faster and more fitting, and more secure replacement for MD5
in those situations. Replacing MD5 and SHA1 with SipHash for these uses is
obvious and straight-forward, and so is submitted along with this patch
series. There shouldn't be much of a debate over its efficacy.

Dozens of languages are already using this internally for their hash
tables and PRFs. Some of the BSDs already use this in their kernels.
SipHash is a widely known high-speed solution to a widely known set of
problems, and it's time we catch-up.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Eric Biggers <ebiggers3@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
---
 MAINTAINERS             |   7 ++
 include/linux/siphash.h |  86 ++++++++++++++++++++
 lib/Kconfig.debug       |   6 +-
 lib/Makefile            |   5 +-
 lib/siphash.c           | 210 ++++++++++++++++++++++++++++++++++++++++++++++++
 lib/test_siphash.c      | 101 +++++++++++++++++++++++
 6 files changed, 410 insertions(+), 5 deletions(-)
 create mode 100644 include/linux/siphash.h
 create mode 100644 lib/siphash.c
 create mode 100644 lib/test_siphash.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 59c9895d73d5..5d87a8c1056a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11231,6 +11231,13 @@ F:	arch/arm/mach-s3c24xx/mach-bast.c
 F:	arch/arm/mach-s3c24xx/bast-ide.c
 F:	arch/arm/mach-s3c24xx/bast-irq.c
 
+SIPHASH PRF ROUTINES
+M:	Jason A. Donenfeld <Jason@zx2c4.com>
+S:	Maintained
+F:	lib/siphash.c
+F:	lib/test_siphash.c
+F:	include/linux/siphash.h
+
 TI DAVINCI MACHINE SUPPORT
 M:	Sekhar Nori <nsekhar@ti.com>
 M:	Kevin Hilman <khilman@kernel.org>
diff --git a/include/linux/siphash.h b/include/linux/siphash.h
new file mode 100644
index 000000000000..e82fce48a0f6
--- /dev/null
+++ b/include/linux/siphash.h
@@ -0,0 +1,86 @@
+/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.
+ *
+ * SipHash: a fast short-input PRF
+ * https://131002.net/siphash/
+ *
+ * This implementation is specifically for SipHash2-4.
+ */
+
+#ifndef _LINUX_SIPHASH_H
+#define _LINUX_SIPHASH_H
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+
+#define SIPHASH_ALIGNMENT 8
+typedef u64 siphash_key_t[2];
+
+u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t key);
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t key);
+#endif
+
+u64 siphash_1u64(const u64 a, const siphash_key_t key);
+u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t key);
+u64 siphash_3u64(const u64 a, const u64 b, const u64 c,
+		 const siphash_key_t key);
+u64 siphash_4u64(const u64 a, const u64 b, const u64 c, const u64 d,
+		 const siphash_key_t key);
+
+static inline u64 ___siphash_aligned(const u64 *data, size_t len, const siphash_key_t key)
+{
+	if (__builtin_constant_p(len) && len == 8)
+		return siphash_1u64(data[0], key);
+	if (__builtin_constant_p(len) && len == 16)
+		return siphash_2u64(data[0], data[1], key);
+	if (__builtin_constant_p(len) && len == 24)
+		return siphash_3u64(data[0], data[1], data[2], key);
+	if (__builtin_constant_p(len) && len == 32)
+		return siphash_4u64(data[0], data[1], data[2], data[3], key);
+	return __siphash_aligned(data, len, key);
+}
+
+/**
+ * siphash - compute 64-bit siphash PRF value
+ * @data: buffer to hash
+ * @size: size of @data
+ * @key: the siphash key
+ */
+static inline u64 siphash(const void *data, size_t len, const siphash_key_t key)
+{
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
+		return __siphash_unaligned(data, len, key);
+#endif
+	return ___siphash_aligned(data, len, key);
+}
+
+static inline u64 siphash_2u32(const u32 a, const u32 b, const siphash_key_t key)
+{
+	return siphash_1u64((u64)b << 32 | a, key);
+}
+
+static inline u64 siphash_4u32(const u32 a, const u32 b, const u32 c, const u32 d,
+			       const siphash_key_t key)
+{
+	return siphash_2u64((u64)b << 32 | a, (u64)d << 32 | c, key);
+}
+
+static inline u64 siphash_6u32(const u32 a, const u32 b, const u32 c, const u32 d,
+			       const u32 e, const u32 f, const siphash_key_t key)
+{
+	return siphash_3u64((u64)b << 32 | a, (u64)d << 32 | c, (u64)f << 32 | e,
+			    key);
+}
+
+static inline u64 siphash_8u32(const u32 a, const u32 b, const u32 c, const u32 d,
+			       const u32 e, const u32 f, const u32 g, const u32 h,
+			       const siphash_key_t key)
+{
+	return siphash_4u64((u64)b << 32 | a, (u64)d << 32 | c, (u64)f << 32 | e,
+			    (u64)h << 32 | g, key);
+}
+
+#endif /* _LINUX_SIPHASH_H */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7446097f72bd..86254ea99b45 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1843,9 +1843,9 @@ config TEST_HASH
 	tristate "Perform selftest on hash functions"
 	default n
 	help
-	  Enable this option to test the kernel's integer (<linux/hash,h>)
-	  and string (<linux/stringhash.h>) hash functions on boot
-	  (or module load).
+	  Enable this option to test the kernel's integer (<linux/hash.h>),
+	  string (<linux/stringhash.h>), and siphash (<linux/siphash.h>)
+	  hash functions on boot (or module load).
 
 	  This is intended to help people writing architecture-specific
 	  optimized versions.  If unsure, say N.
diff --git a/lib/Makefile b/lib/Makefile
index 50144a3aeebd..71d398b04a74 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -22,7 +22,8 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 sha1.o chacha20.o md5.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
-	 earlycpio.o seq_buf.o nmi_backtrace.o nodemask.o win_minmax.o
+	 earlycpio.o seq_buf.o siphash.o \
+	 nmi_backtrace.o nodemask.o win_minmax.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
@@ -44,7 +45,7 @@ obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o
 obj-y += kstrtox.o
 obj-$(CONFIG_TEST_BPF) += test_bpf.o
 obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
-obj-$(CONFIG_TEST_HASH) += test_hash.o
+obj-$(CONFIG_TEST_HASH) += test_hash.o test_siphash.o
 obj-$(CONFIG_TEST_KASAN) += test_kasan.o
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 obj-$(CONFIG_TEST_LKM) += test_module.o
diff --git a/lib/siphash.c b/lib/siphash.c
new file mode 100644
index 000000000000..7efc273de5d0
--- /dev/null
+++ b/lib/siphash.c
@@ -0,0 +1,210 @@
+/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.
+ *
+ * SipHash: a fast short-input PRF
+ * https://131002.net/siphash/
+ *
+ * This implementation is specifically for SipHash2-4.
+ */
+
+#include <linux/siphash.h>
+#include <asm/unaligned.h>
+
+#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
+#include <linux/dcache.h>
+#include <asm/word-at-a-time.h>
+#endif
+
+#define SIPROUND \
+	do { \
+	v0 += v1; v1 = rol64(v1, 13); v1 ^= v0; v0 = rol64(v0, 32); \
+	v2 += v3; v3 = rol64(v3, 16); v3 ^= v2; \
+	v0 += v3; v3 = rol64(v3, 21); v3 ^= v0; \
+	v2 += v1; v1 = rol64(v1, 17); v1 ^= v2; v2 = rol64(v2, 32); \
+	} while(0)
+
+#define PREAMBLE(len) \
+	u64 v0 = 0x736f6d6570736575ULL; \
+	u64 v1 = 0x646f72616e646f6dULL; \
+	u64 v2 = 0x6c7967656e657261ULL; \
+	u64 v3 = 0x7465646279746573ULL; \
+	u64 b = ((u64)len) << 56; \
+	v3 ^= key[1]; \
+	v2 ^= key[0]; \
+	v1 ^= key[1]; \
+	v0 ^= key[0];
+
+#define POSTAMBLE \
+	v3 ^= b; \
+	SIPROUND; \
+	SIPROUND; \
+	v0 ^= b; \
+	v2 ^= 0xff; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	return (v0 ^ v1) ^ (v2 ^ v3);
+
+u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t key)
+{
+	const u8 *end = data + len - (len % sizeof(u64));
+	const u8 left = len & (sizeof(u64) - 1);
+	u64 m;
+	PREAMBLE(len)
+	for (; data != end; data += sizeof(u64)) {
+		m = le64_to_cpup(data);
+		v3 ^= m;
+		SIPROUND;
+		SIPROUND;
+		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
+	POSTAMBLE
+}
+EXPORT_SYMBOL(__siphash_aligned);
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t key)
+{
+	const u8 *end = data + len - (len % sizeof(u64));
+	const u8 left = len & (sizeof(u64) - 1);
+	u64 m;
+	PREAMBLE(len)
+	for (; data != end; data += sizeof(u64)) {
+		m = get_unaligned_le64(data);
+		v3 ^= m;
+		SIPROUND;
+		SIPROUND;
+		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
+	POSTAMBLE
+}
+EXPORT_SYMBOL(__siphash_unaligned);
+#endif
+
+/**
+ * siphash_1u64 - compute 64-bit siphash PRF value of a u64
+ * @first: first u64
+ * @key: the siphash key
+ */
+u64 siphash_1u64(const u64 first, const siphash_key_t key)
+{
+	PREAMBLE(8)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_1u64);
+
+/**
+ * siphash_2u64 - compute 64-bit siphash PRF value of 2 u64
+ * @first: first u64
+ * @second: second u64
+ * @key: the siphash key
+ */
+u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t key)
+{
+	PREAMBLE(16)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= second;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_2u64);
+
+/**
+ * siphash_3u64 - compute 64-bit siphash PRF value of 3 u64
+ * @first: first u64
+ * @second: second u64
+ * @third: third u64
+ * @key: the siphash key
+ */
+u64 siphash_3u64(const u64 first, const u64 second, const u64 third,
+		 const siphash_key_t key)
+{
+	PREAMBLE(24)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= second;
+	v3 ^= third;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= third;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_3u64);
+
+/**
+ * siphash_4u64 - compute 64-bit siphash PRF value of 4 u64
+ * @first: first u64
+ * @second: second u64
+ * @third: third u64
+ * @forth: forth u64
+ * @key: the siphash key
+ */
+u64 siphash_4u64(const u64 first, const u64 second, const u64 third,
+		 const u64 forth, const siphash_key_t key)
+{
+	PREAMBLE(32)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= second;
+	v3 ^= third;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= third;
+	v3 ^= forth;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= forth;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_4u64);
diff --git a/lib/test_siphash.c b/lib/test_siphash.c
new file mode 100644
index 000000000000..906e58a2c946
--- /dev/null
+++ b/lib/test_siphash.c
@@ -0,0 +1,101 @@
+/* Test cases for siphash.c
+ *
+ * Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.
+ *
+ * SipHash: a fast short-input PRF
+ * https://131002.net/siphash/
+ *
+ * This implementation is specifically for SipHash2-4.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/siphash.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+
+/* Test vectors taken from official reference source available at:
+ *     https://131002.net/siphash/siphash24.c
+ */
+static const u64 test_vectors[64] = {
+	0x726fdb47dd0e0e31ULL, 0x74f839c593dc67fdULL, 0x0d6c8009d9a94f5aULL,
+	0x85676696d7fb7e2dULL, 0xcf2794e0277187b7ULL, 0x18765564cd99a68dULL,
+	0xcbc9466e58fee3ceULL, 0xab0200f58b01d137ULL, 0x93f5f5799a932462ULL,
+	0x9e0082df0ba9e4b0ULL, 0x7a5dbbc594ddb9f3ULL, 0xf4b32f46226bada7ULL,
+	0x751e8fbc860ee5fbULL, 0x14ea5627c0843d90ULL, 0xf723ca908e7af2eeULL,
+	0xa129ca6149be45e5ULL, 0x3f2acc7f57c29bdbULL, 0x699ae9f52cbe4794ULL,
+	0x4bc1b3f0968dd39cULL, 0xbb6dc91da77961bdULL, 0xbed65cf21aa2ee98ULL,
+	0xd0f2cbb02e3b67c7ULL, 0x93536795e3a33e88ULL, 0xa80c038ccd5ccec8ULL,
+	0xb8ad50c6f649af94ULL, 0xbce192de8a85b8eaULL, 0x17d835b85bbb15f3ULL,
+	0x2f2e6163076bcfadULL, 0xde4daaaca71dc9a5ULL, 0xa6a2506687956571ULL,
+	0xad87a3535c49ef28ULL, 0x32d892fad841c342ULL, 0x7127512f72f27cceULL,
+	0xa7f32346f95978e3ULL, 0x12e0b01abb051238ULL, 0x15e034d40fa197aeULL,
+	0x314dffbe0815a3b4ULL, 0x027990f029623981ULL, 0xcadcd4e59ef40c4dULL,
+	0x9abfd8766a33735cULL, 0x0e3ea96b5304a7d0ULL, 0xad0c42d6fc585992ULL,
+	0x187306c89bc215a9ULL, 0xd4a60abcf3792b95ULL, 0xf935451de4f21df2ULL,
+	0xa9538f0419755787ULL, 0xdb9acddff56ca510ULL, 0xd06c98cd5c0975ebULL,
+	0xe612a3cb9ecba951ULL, 0xc766e62cfcadaf96ULL, 0xee64435a9752fe72ULL,
+	0xa192d576b245165aULL, 0x0a8787bf8ecb74b2ULL, 0x81b3e73d20b49b6fULL,
+	0x7fa8220ba3b2eceaULL, 0x245731c13ca42499ULL, 0xb78dbfaf3a8d83bdULL,
+	0xea1ad565322a1a0bULL, 0x60e61c23a3795013ULL, 0x6606d7e446282b93ULL,
+	0x6ca4ecb15c5f91e1ULL, 0x9f626da15c9625f3ULL, 0xe51b38608ef25f57ULL,
+	0x958a324ceb064572ULL
+};
+static const siphash_key_t test_key =
+	{ 0x0706050403020100ULL , 0x0f0e0d0c0b0a0908ULL };
+
+static int __init siphash_test_init(void)
+{
+	u8 in[64] __aligned(SIPHASH_ALIGNMENT);
+	u8 in_unaligned[65];
+	u8 i;
+	int ret = 0;
+
+	for (i = 0; i < 64; ++i) {
+		in[i] = i;
+		in_unaligned[i + 1] = i;
+		if (siphash(in, i, test_key) != test_vectors[i]) {
+			pr_info("self-test aligned %u: FAIL\n", i + 1);
+			ret = -EINVAL;
+		}
+		if (siphash(in_unaligned + 1, i, test_key) != test_vectors[i]) {
+			pr_info("self-test unaligned %u: FAIL\n", i + 1);
+			ret = -EINVAL;
+		}
+	}
+	if (siphash_1u64(0x0706050403020100ULL, test_key) != test_vectors[8]) {
+		pr_info("self-test 1u64: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_2u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL, test_key) != test_vectors[16]) {
+		pr_info("self-test 2u64: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_3u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL,
+			 0x1716151413121110ULL, test_key) != test_vectors[24]) {
+		pr_info("self-test 3u64: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_4u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL,
+			 0x1716151413121110ULL, 0x1f1e1d1c1b1a1918ULL, test_key) != test_vectors[32]) {
+		pr_info("self-test 4u64: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (!ret)
+		pr_info("self-tests: pass\n");
+	return ret;
+}
+
+static void __exit siphash_test_exit(void)
+{
+}
+
+module_init(siphash_test_init);
+module_exit(siphash_test_exit);
+
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
+MODULE_LICENSE("Dual BSD/GPL");
-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1546023 — [PATCH v7 0/6] The SipHash Patchset

Hey folks,

Again we've made huge progress, with this latest version now shipping
Jean-Phillipe Aumasson's HalfSipHash, which should be much more competitive
with jhash (in addition to being more secure, of course).

There are dozens of little cleanups and improvements right and left throughout
this series, so I urge you to take a look at the whole thing. I've tried to
take into consideration lots of concerns and suggestions from many of you
over the last week.

There is also now documentation! And the test suite now has full coverage of
all functions.

Finally, there's been some significant benchmarking, and now a few commit
messages have some performance numbers.

Please send your Reviewed-by lines as you see fit.

Regards,
Jason

Jason A. Donenfeld (6):
  siphash: add cryptographically secure PRF
  secure_seq: use SipHash in place of MD5
  random: use SipHash in place of MD5
  md5: remove from lib and only live in crypto
  syncookies: use SipHash in place of SHA1
  siphash: implement HalfSipHash1-3 for hash tables

 Documentation/siphash.txt | 154 +++++++++++++
 MAINTAINERS               |   7 +
 crypto/md5.c              |  95 +++++++-
 drivers/char/random.c     |  84 ++++---
 include/linux/random.h    |   1 -
 include/linux/siphash.h   | 133 +++++++++++
 init/main.c               |   1 -
 lib/Kconfig.debug         |   6 +-
 lib/Makefile              |   7 +-
 lib/md5.c                 |  95 --------
 lib/siphash.c             | 548 ++++++++++++++++++++++++++++++++++++++++++++++
 lib/test_siphash.c        | 208 ++++++++++++++++++
 net/core/secure_seq.c     | 135 +++++-------
 net/ipv4/syncookies.c     |  20 +-
 net/ipv6/syncookies.c     |  37 ++--
 15 files changed, 1274 insertions(+), 257 deletions(-)
 create mode 100644 Documentation/siphash.txt
 create mode 100644 include/linux/siphash.h
 delete mode 100644 lib/md5.c
 create mode 100644 lib/siphash.c
 create mode 100644 lib/test_siphash.c

-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1546028 — [PATCH v7 6/6] 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>
Cc: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com>
---
 Documentation/siphash.txt |  75 +++++++++++
 include/linux/siphash.h   |  56 +++++++-
 lib/siphash.c             | 318 +++++++++++++++++++++++++++++++++++++++++++++-
 lib/test_siphash.c        | 139 ++++++++++++++++----
 4 files changed, 561 insertions(+), 27 deletions(-)

diff --git a/Documentation/siphash.txt b/Documentation/siphash.txt
index 39ff7f0438e7..f93c1d7104c4 100644
--- a/Documentation/siphash.txt
+++ b/Documentation/siphash.txt
@@ -77,3 +77,78 @@ Linux implements the "2-4" variant of SipHash.
 
 Read the SipHash paper if you're interested in learning more:
 https://131002.net/siphash/siphash.pdf
+
+
+~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~
+
+HalfSipHash - SipHash's insecure younger cousin
+-----------------------------------------------
+Written by Jason A. Donenfeld <jason@zx2c4.com>
+
+On the off-chance that SipHash is not fast enough for your needs, you might be
+able to justify using HalfSipHash, a terrifying but potentially useful
+possibility. HalfSipHash cuts SipHash's rounds down from "2-4" to "1-3" and,
+even scarier, uses an easily brute-forcable 64-bit key (with a 32-bit output)
+instead of SipHash's 128-bit key. However, this may appeal to some
+high-performance `jhash` users.
+
+Danger!
+
+Do not ever use HalfSipHash except for as a hashtable key function, and only
+then when you can be absolutely certain that the outputs will never be
+transmitted out of the kernel. This is only remotely useful over `jhash` as a
+means of mitigating hashtable flooding denial of service attacks.
+
+1. Generating a key
+
+Keys should always be generated from a cryptographically secure source of
+random numbers, either using get_random_bytes or get_random_once:
+
+hsiphash_key_t key;
+get_random_bytes(key, sizeof(key));
+
+If you're not deriving your key from here, you're doing it wrong.
+
+2. Using the functions
+
+There are two variants of the function, one that takes a list of integers, and
+one that takes a buffer:
+
+u32 hsiphash(const void *data, size_t len, siphash_key_t key);
+
+And:
+
+u32 hsiphash_1u32(u32, hsiphash_key_t key);
+u32 hsiphash_2u32(u32, u32, hsiphash_key_t key);
+u32 hsiphash_3u32(u32, u32, u32, hsiphash_key_t key);
+u32 hsiphash_4u32(u32, u32, u32, u32, hsiphash_key_t key);
+
+If you pass the generic hsiphash function something of a constant length, it
+will constant fold at compile-time and automatically choose one of the
+optimized functions.
+
+3. Hashtable key function usage:
+
+struct some_hashtable {
+	DECLARE_HASHTABLE(hashtable, 8);
+	hsiphash_key_t key;
+};
+
+void init_hashtable(struct some_hashtable *table)
+{
+	get_random_bytes(table->key, sizeof(table->key));
+}
+
+static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input)
+{
+	return &table->hashtable[hsiphash(input, sizeof(*input), table->key) & (HASH_SIZE(table->hashtable) - 1)];
+}
+
+You may then iterate like usual over the returned hash bucket.
+
+4. Performance
+
+HalfSipHash is roughly 3 times slower than JenkinsHash. For many replacements,
+this will not be a problem, as the hashtable lookup isn't the bottleneck. And
+in general, this is probably a good sacrifice to make for the security and DoS
+resistance of HalfSipHash.
diff --git a/include/linux/siphash.h b/include/linux/siphash.h
index 7aa666eb00d9..efab44c654f3 100644
--- a/include/linux/siphash.h
+++ b/include/linux/siphash.h
@@ -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.
  */
 
 #ifndef _LINUX_SIPHASH_H
@@ -76,4 +78,56 @@ static inline u64 siphash(const void *data, size_t len, const siphash_key_t key)
 	return ___siphash_aligned(data, len, key);
 }
 
+#if BITS_PER_LONG == 64
+typedef siphash_key_t hsiphash_key_t;
+#define HSIPHASH_ALIGNMENT SIPHASH_ALIGNMENT
+#else
+typedef u32 hsiphash_key_t[2];
+#define HSIPHASH_ALIGNMENT __alignof__(u32)
+#endif
+
+u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t key);
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t key);
+#endif
+
+u32 hsiphash_1u32(const u32 a, const hsiphash_key_t key);
+u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t key);
+u32 hsiphash_3u32(const u32 a, const u32 b, const u32 c,
+		  const hsiphash_key_t key);
+u32 hsiphash_4u32(const u32 a, const u32 b, const u32 c, const u32 d,
+		  const hsiphash_key_t key);
+
+static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len, const hsiphash_key_t key)
+{
+	if (__builtin_constant_p(len) && len == 4)
+		return hsiphash_1u32(le32_to_cpu(data[0]), key);
+	if (__builtin_constant_p(len) && len == 8)
+		return hsiphash_2u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]),
+				     key);
+	if (__builtin_constant_p(len) && len == 12)
+		return hsiphash_3u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]),
+				     le32_to_cpu(data[2]), key);
+	if (__builtin_constant_p(len) && len == 16)
+		return hsiphash_4u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]),
+				     le32_to_cpu(data[2]), le32_to_cpu(data[3]),
+				     key);
+	return __hsiphash_aligned(data, len, key);
+}
+
+/**
+ * hsiphash - compute 32-bit hsiphash PRF value
+ * @data: buffer to hash
+ * @size: size of @data
+ * @key: the hsiphash key
+ */
+static inline u32 hsiphash(const void *data, size_t len, const hsiphash_key_t key)
+{
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
+		return __hsiphash_unaligned(data, len, key);
+#endif
+	return ___hsiphash_aligned(data, len, key);
+}
+
 #endif /* _LINUX_SIPHASH_H */
diff --git a/lib/siphash.c b/lib/siphash.c
index ff2151313667..e2481226d96c 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 +232,317 @@ u64 siphash_3u32(const u32 first, const u32 second, const u32 third,
 	POSTAMBLE
 }
 EXPORT_SYMBOL(siphash_3u32);
+
+#if BITS_PER_LONG == 64
+/* Note that this HalfSipHash1-3 implementation on 64-bit
+ * isn't actually HalfSipHash1-3 but rather SipHash1-3. */
+
+#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[1]; \
+	v2 ^= key[0]; \
+	v1 ^= key[1]; \
+	v0 ^= 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
diff --git a/lib/test_siphash.c b/lib/test_siphash.c
index e0ba2cf8dc67..ac291ec27fb6 100644
--- a/lib/test_siphash.c
+++ b/lib/test_siphash.c
@@ -7,7 +7,9 @@
  * 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.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -18,10 +20,16 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 
-/* Test vectors taken from official reference source available at:
- *     https://131002.net/siphash/siphash24.c
+/* Test vectors taken from reference source available at:
+ *     https://github.com/veorq/SipHash
  */
-static const u64 test_vectors[64] = {
+
+
+
+static const siphash_key_t test_key_siphash =
+	{ 0x0706050403020100ULL , 0x0f0e0d0c0b0a0908ULL };
+
+static const u64 test_vectors_siphash[64] = {
 	0x726fdb47dd0e0e31ULL, 0x74f839c593dc67fdULL, 0x0d6c8009d9a94f5aULL,
 	0x85676696d7fb7e2dULL, 0xcf2794e0277187b7ULL, 0x18765564cd99a68dULL,
 	0xcbc9466e58fee3ceULL, 0xab0200f58b01d137ULL, 0x93f5f5799a932462ULL,
@@ -45,9 +53,64 @@ static const u64 test_vectors[64] = {
 	0x6ca4ecb15c5f91e1ULL, 0x9f626da15c9625f3ULL, 0xe51b38608ef25f57ULL,
 	0x958a324ceb064572ULL
 };
-static const siphash_key_t test_key =
+#if BITS_PER_LONG == 64
+static const hsiphash_key_t test_key_hsiphash =
 	{ 0x0706050403020100ULL , 0x0f0e0d0c0b0a0908ULL };
 
+static const u32 test_vectors_hsiphash[64] = {
+	0x050fc4dcU, 0x7d57ca93U, 0x4dc7d44dU,
+	0xe7ddf7fbU, 0x88d38328U, 0x49533b67U,
+	0xc59f22a7U, 0x9bb11140U, 0x8d299a8eU,
+	0x6c063de4U, 0x92ff097fU, 0xf94dc352U,
+	0x57b4d9a2U, 0x1229ffa7U, 0xc0f95d34U,
+	0x2a519956U, 0x7d908b66U, 0x63dbd80cU,
+	0xb473e63eU, 0x8d297d1cU, 0xa6cce040U,
+	0x2b45f844U, 0xa320872eU, 0xdae6c123U,
+	0x67349c8cU, 0x705b0979U, 0xca9913a5U,
+	0x4ade3b35U, 0xef6cd00dU, 0x4ab1e1f4U,
+	0x43c5e663U, 0x8c21d1bcU, 0x16a7b60dU,
+	0x7a8ff9bfU, 0x1f2a753eU, 0xbf186b91U,
+	0xada26206U, 0xa3c33057U, 0xae3a36a1U,
+	0x7b108392U, 0x99e41531U, 0x3f1ad944U,
+	0xc8138825U, 0xc28949a6U, 0xfaf8876bU,
+	0x9f042196U, 0x68b1d623U, 0x8b5114fdU,
+	0xdf074c46U, 0x12cc86b3U, 0x0a52098fU,
+	0x9d292f9aU, 0xa2f41f12U, 0x43a71ed0U,
+	0x73f0bce6U, 0x70a7e980U, 0x243c6d75U,
+	0xfdb71513U, 0xa67d8a08U, 0xb7e8f148U,
+	0xf7a644eeU, 0x0f1837f2U, 0x4b6694e0U,
+	0xb7bbb3a8U
+};
+#else
+static const hsiphash_key_t test_key_hsiphash =
+	{ 0x03020100U, 0x07060504U };
+
+static const u32 test_vectors_hsiphash[64] = {
+	0x5814c896U, 0xe7e864caU, 0xbc4b0e30U,
+	0x01539939U, 0x7e059ea6U, 0x88e3d89bU,
+	0xa0080b65U, 0x9d38d9d6U, 0x577999b1U,
+	0xc839caedU, 0xe4fa32cfU, 0x959246eeU,
+	0x6b28096cU, 0x66dd9cd6U, 0x16658a7cU,
+	0xd0257b04U, 0x8b31d501U, 0x2b1cd04bU,
+	0x06712339U, 0x522aca67U, 0x911bb605U,
+	0x90a65f0eU, 0xf826ef7bU, 0x62512debU,
+	0x57150ad7U, 0x5d473507U, 0x1ec47442U,
+	0xab64afd3U, 0x0a4100d0U, 0x6d2ce652U,
+	0x2331b6a3U, 0x08d8791aU, 0xbc6dda8dU,
+	0xe0f6c934U, 0xb0652033U, 0x9b9851ccU,
+	0x7c46fb7fU, 0x732ba8cbU, 0xf142997aU,
+	0xfcc9aa1bU, 0x05327eb2U, 0xe110131cU,
+	0xf9e5e7c0U, 0xa7d708a6U, 0x11795ab1U,
+	0x65671619U, 0x9f5fff91U, 0xd89c5267U,
+	0x007783ebU, 0x95766243U, 0xab639262U,
+	0x9c7e1390U, 0xc368dda6U, 0x38ddc455U,
+	0xfa13d379U, 0x979ea4e8U, 0x53ecd77eU,
+	0x2ee80657U, 0x33dbb66aU, 0xae3f0577U,
+	0x88b4c4ccU, 0x3e7f480bU, 0x74c1ebf8U,
+	0x87178304U
+};
+#endif
+
 static int __init siphash_test_init(void)
 {
 	u8 in[64] __aligned(SIPHASH_ALIGNMENT);
@@ -58,49 +121,75 @@ static int __init siphash_test_init(void)
 	for (i = 0; i < 64; ++i) {
 		in[i] = i;
 		in_unaligned[i + 1] = i;
-		if (siphash(in, i, test_key) != test_vectors[i]) {
-			pr_info("self-test aligned %u: FAIL\n", i + 1);
+		if (siphash(in, i, test_key_siphash) != test_vectors_siphash[i]) {
+			pr_info("siphash self-test aligned %u: FAIL\n", i + 1);
+			ret = -EINVAL;
+		}
+		if (siphash(in_unaligned + 1, i, test_key_siphash) != test_vectors_siphash[i]) {
+			pr_info("siphash self-test unaligned %u: FAIL\n", i + 1);
 			ret = -EINVAL;
 		}
-		if (siphash(in_unaligned + 1, i, test_key) != test_vectors[i]) {
-			pr_info("self-test unaligned %u: FAIL\n", i + 1);
+		if (hsiphash(in, i, test_key_hsiphash) != test_vectors_hsiphash[i]) {
+			pr_info("hsiphash self-test aligned %u: FAIL\n", i + 1);
+			ret = -EINVAL;
+		}
+		if (hsiphash(in_unaligned + 1, i, test_key_hsiphash) != test_vectors_hsiphash[i]) {
+			pr_info("hsiphash self-test unaligned %u: FAIL\n", i + 1);
 			ret = -EINVAL;
 		}
 	}
-	if (siphash_1u64(0x0706050403020100ULL, test_key) != test_vectors[8]) {
-		pr_info("self-test 1u64: FAIL\n");
+	if (siphash_1u64(0x0706050403020100ULL, test_key_siphash) != test_vectors_siphash[8]) {
+		pr_info("siphash self-test 1u64: FAIL\n");
 		ret = -EINVAL;
 	}
-	if (siphash_2u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL, test_key) != test_vectors[16]) {
-		pr_info("self-test 2u64: FAIL\n");
+	if (siphash_2u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL, test_key_siphash) != test_vectors_siphash[16]) {
+		pr_info("siphash self-test 2u64: FAIL\n");
 		ret = -EINVAL;
 	}
 	if (siphash_3u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL,
-			 0x1716151413121110ULL, test_key) != test_vectors[24]) {
-		pr_info("self-test 3u64: FAIL\n");
+			 0x1716151413121110ULL, test_key_siphash) != test_vectors_siphash[24]) {
+		pr_info("siphash self-test 3u64: FAIL\n");
 		ret = -EINVAL;
 	}
 	if (siphash_4u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL,
-			 0x1716151413121110ULL, 0x1f1e1d1c1b1a1918ULL, test_key) != test_vectors[32]) {
-		pr_info("self-test 4u64: FAIL\n");
+			 0x1716151413121110ULL, 0x1f1e1d1c1b1a1918ULL, test_key_siphash) != test_vectors_siphash[32]) {
+		pr_info("siphash self-test 4u64: FAIL\n");
 		ret = -EINVAL;
 	}
-	if (siphash_1u32(0x03020100U, test_key) != test_vectors[4]) {
-		pr_info("self-test 1u32: FAIL\n");
+	if (siphash_1u32(0x03020100U, test_key_siphash) != test_vectors_siphash[4]) {
+		pr_info("siphash self-test 1u32: FAIL\n");
 		ret = -EINVAL;
 	}
-	if (siphash_2u32(0x03020100U, 0x07060504U, test_key) != test_vectors[8]) {
-		pr_info("self-test 2u32: FAIL\n");
+	if (siphash_2u32(0x03020100U, 0x07060504U, test_key_siphash) != test_vectors_siphash[8]) {
+		pr_info("siphash self-test 2u32: FAIL\n");
 		ret = -EINVAL;
 	}
 	if (siphash_3u32(0x03020100U, 0x07060504U,
-			 0x0b0a0908U, test_key) != test_vectors[12]) {
-		pr_info("self-test 3u32: FAIL\n");
+			 0x0b0a0908U, test_key_siphash) != test_vectors_siphash[12]) {
+		pr_info("siphash self-test 3u32: FAIL\n");
 		ret = -EINVAL;
 	}
 	if (siphash_4u32(0x03020100U, 0x07060504U,
-			 0x0b0a0908U, 0x0f0e0d0cU, test_key) != test_vectors[16]) {
-		pr_info("self-test 4u32: FAIL\n");
+			 0x0b0a0908U, 0x0f0e0d0cU, test_key_siphash) != test_vectors_siphash[16]) {
+		pr_info("siphash self-test 4u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (hsiphash_1u32(0x03020100U, test_key_hsiphash) != test_vectors_hsiphash[4]) {
+		pr_info("hsiphash self-test 1u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (hsiphash_2u32(0x03020100U, 0x07060504U, test_key_hsiphash) != test_vectors_hsiphash[8]) {
+		pr_info("hsiphash self-test 2u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (hsiphash_3u32(0x03020100U, 0x07060504U,
+			  0x0b0a0908U, test_key_hsiphash) != test_vectors_hsiphash[12]) {
+		pr_info("hsiphash self-test 3u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (hsiphash_4u32(0x03020100U, 0x07060504U,
+			  0x0b0a0908U, 0x0f0e0d0cU, test_key_hsiphash) != test_vectors_hsiphash[16]) {
+		pr_info("hsiphash self-test 4u32: FAIL\n");
 		ret = -EINVAL;
 	}
 	if (!ret)
-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1546090 — Re: [PATCH v7 6/6] siphash: implement HalfSipHash1-3 for hash tables

> 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

I'm not sure what these numbers mean. Surely a single siphash2-4
does not take 4+ million cycles? 

If you run them in a loop please divide by the iterations.

But generally running small code in a loop is often an unrealistic
benchmark strategy because it hides cache misses, primes
predictors, changes frequencies and changes memory costs,
but also can overload pipelines and oversubscribe
resources.

[see also page 46+ in http://halobates.de/applicative-mental-models.pdf]

So the numbers you get there are at least somewhat
dubious. It would be good to have at least some test which
is not just a tiny micro benchmark to compare before making
conclusions.

-Andi

[toc] | [prev] | [next] | [standalone]

#1546029 — [PATCH v7 5/6] syncookies: use SipHash in place of SHA1

SHA1 is slower and less secure than SipHash, and so replacing syncookie
generation with SipHash makes natural sense. Some BSDs have been doing
this for several years in fact.

The speedup should be similar -- and even more impressive -- to the
speedup from the sequence number fix in this series.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David Miller <davem@davemloft.net>
---
 net/ipv4/syncookies.c | 20 ++++----------------
 net/ipv6/syncookies.c | 37 ++++++++++++++++---------------------
 2 files changed, 20 insertions(+), 37 deletions(-)

diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 3e88467d70ee..03bb068f8888 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -13,13 +13,13 @@
 #include <linux/tcp.h>
 #include <linux/slab.h>
 #include <linux/random.h>
-#include <linux/cryptohash.h>
+#include <linux/siphash.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <net/tcp.h>
 #include <net/route.h>
 
-static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
+static siphash_key_t syncookie_secret[2] __read_mostly;
 
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
@@ -48,24 +48,12 @@ static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
 #define TSBITS	6
 #define TSMASK	(((__u32)1 << TSBITS) - 1)
 
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv4_cookie_scratch);
-
 static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 		       u32 count, int c)
 {
-	__u32 *tmp;
-
 	net_get_random_once(syncookie_secret, sizeof(syncookie_secret));
-
-	tmp  = this_cpu_ptr(ipv4_cookie_scratch);
-	memcpy(tmp + 4, syncookie_secret[c], sizeof(syncookie_secret[c]));
-	tmp[0] = (__force u32)saddr;
-	tmp[1] = (__force u32)daddr;
-	tmp[2] = ((__force u32)sport << 16) + (__force u32)dport;
-	tmp[3] = count;
-	sha_transform(tmp + 16, (__u8 *)tmp, tmp + 16 + 5);
-
-	return tmp[17];
+	return siphash_4u32(saddr, daddr, (u32)sport << 16 | dport, count,
+			    syncookie_secret[c]);
 }
 
 
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index a4d49760bf43..be51fc0d99ad 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -16,7 +16,7 @@
 
 #include <linux/tcp.h>
 #include <linux/random.h>
-#include <linux/cryptohash.h>
+#include <linux/siphash.h>
 #include <linux/kernel.h>
 #include <net/ipv6.h>
 #include <net/tcp.h>
@@ -24,7 +24,7 @@
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
 
-static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
+static siphash_key_t syncookie6_secret[2] __read_mostly;
 
 /* RFC 2460, Section 8.3:
  * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
@@ -41,30 +41,25 @@ static __u16 const msstab[] = {
 	9000 - 60,
 };
 
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv6_cookie_scratch);
-
 static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr,
 		       __be16 sport, __be16 dport, u32 count, int c)
 {
-	__u32 *tmp;
+	const struct {
+		struct in6_addr saddr;
+		struct in6_addr daddr;
+		u32 count;
+		u16 sport;
+		u16 dport;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.saddr = *saddr,
+		.daddr = *daddr,
+		.count = count,
+		.sport = sport,
+		.dport = dport
+	};
 
 	net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret));
-
-	tmp  = this_cpu_ptr(ipv6_cookie_scratch);
-
-	/*
-	 * we have 320 bits of information to hash, copy in the remaining
-	 * 192 bits required for sha_transform, from the syncookie6_secret
-	 * and overwrite the digest with the secret
-	 */
-	memcpy(tmp + 10, syncookie6_secret[c], 44);
-	memcpy(tmp, saddr, 16);
-	memcpy(tmp + 4, daddr, 16);
-	tmp[8] = ((__force u32)sport << 16) + (__force u32)dport;
-	tmp[9] = count;
-	sha_transform(tmp + 16, (__u8 *)tmp, tmp + 16 + 5);
-
-	return tmp[17];
+	return siphash(&combined, offsetofend(typeof(combined), dport), syncookie6_secret[c]);
 }
 
 static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

#1546032 — [PATCH v7 3/6] random: use SipHash in place of MD5

This duplicates the current algorithm for get_random_int/long, but uses
siphash instead. This comes with several benefits. It's certainly
faster and more cryptographically secure than MD5. This patch also
separates hashed fields into three values instead of one, in order to
increase diffusion.

The previous MD5 algorithm used a per-cpu MD5 state, which caused
successive calls to the function to chain upon each other. While it's
not entirely clear that this kind of chaining is absolutely necessary
when using a secure PRF like siphash, it can't hurt, and the timing of
the call chain does add a degree of natural entropy. So, in keeping with
this design, instead of the massive per-cpu 64-byte MD5 state, there is
instead a per-cpu previously returned value for chaining.

The speed benefits are substantial:

                | siphash | md5    | speedup |
		------------------------------
get_random_long | 137130  | 415983 | 3.03x   |
get_random_int  | 86384   | 343323 | 3.97x   |

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com>
Cc: Ted Tso <tytso@mit.edu>
---
 drivers/char/random.c  | 84 +++++++++++++++++++++++++++++---------------------
 include/linux/random.h |  1 -
 init/main.c            |  1 -
 3 files changed, 49 insertions(+), 37 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index d6876d506220..ea9858d9d8b4 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -262,6 +262,7 @@
 #include <linux/syscalls.h>
 #include <linux/completion.h>
 #include <linux/uuid.h>
+#include <linux/siphash.h>
 #include <crypto/chacha20.h>
 
 #include <asm/processor.h>
@@ -2042,17 +2043,31 @@ struct ctl_table random_table[] = {
 };
 #endif 	/* CONFIG_SYSCTL */
 
-static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
 
-int random_int_secret_init(void)
+struct random_int_secret {
+	siphash_key_t secret;
+	u64 chaining;
+	unsigned long birthdate;
+	bool initialized;
+};
+static DEFINE_PER_CPU(struct random_int_secret, random_int_secret);
+
+enum {
+	SECRET_ROTATION_TIME = HZ * 60 * 5
+};
+
+static struct random_int_secret *get_random_int_secret(void)
 {
-	get_random_bytes(random_int_secret, sizeof(random_int_secret));
-	return 0;
+	struct random_int_secret *secret = &get_cpu_var(random_int_secret);
+	if (unlikely(!secret->initialized ||
+		     !time_is_after_jiffies(secret->birthdate + SECRET_ROTATION_TIME))) {
+		secret->initialized = true;
+		secret->birthdate = jiffies;
+		get_random_bytes(secret->secret, sizeof(secret->secret));
+	}
+	return secret;
 }
 
-static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
-		__aligned(sizeof(unsigned long));
-
 /*
  * Get a random word for internal kernel use only. Similar to urandom but
  * with the goal of minimal entropy pool depletion. As a result, the random
@@ -2061,20 +2076,20 @@ static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
  */
 unsigned int get_random_int(void)
 {
-	__u32 *hash;
-	unsigned int ret;
-
-	if (arch_get_random_int(&ret))
-		return ret;
-
-	hash = get_cpu_var(get_random_int_hash);
-
-	hash[0] += current->pid + jiffies + random_get_entropy();
-	md5_transform(hash, random_int_secret);
-	ret = hash[0];
-	put_cpu_var(get_random_int_hash);
-
-	return ret;
+	unsigned int arch_result;
+	u64 result;
+	struct random_int_secret *secret;
+
+	if (arch_get_random_int(&arch_result))
+		return arch_result;
+
+	secret = get_random_int_secret();
+	result = siphash_3u64(secret->chaining, jiffies,
+			      (u64)random_get_entropy() + current->pid,
+			      secret->secret);
+	secret->chaining += result;
+	put_cpu_var(secret);
+	return result;
 }
 EXPORT_SYMBOL(get_random_int);
 
@@ -2083,20 +2098,19 @@ EXPORT_SYMBOL(get_random_int);
  */
 unsigned long get_random_long(void)
 {
-	__u32 *hash;
-	unsigned long ret;
-
-	if (arch_get_random_long(&ret))
-		return ret;
-
-	hash = get_cpu_var(get_random_int_hash);
-
-	hash[0] += current->pid + jiffies + random_get_entropy();
-	md5_transform(hash, random_int_secret);
-	ret = *(unsigned long *)hash;
-	put_cpu_var(get_random_int_hash);
-
-	return ret;
+	unsigned long arch_result;
+	u64 result;
+	struct random_int_secret *secret;
+
+	if (arch_get_random_long(&arch_result))
+		return arch_result;
+
+	secret = get_random_int_secret();
+	result = siphash_3u64(secret->chaining, jiffies, random_get_entropy() +
+			      current->pid, secret->secret);
+	secret->chaining += result;
+	put_cpu_var(secret);
+	return result;
 }
 EXPORT_SYMBOL(get_random_long);
 
diff --git a/include/linux/random.h b/include/linux/random.h
index 7bd2403e4fef..16ab429735a7 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -37,7 +37,6 @@ extern void get_random_bytes(void *buf, int nbytes);
 extern int add_random_ready_callback(struct random_ready_callback *rdy);
 extern void del_random_ready_callback(struct random_ready_callback *rdy);
 extern void get_random_bytes_arch(void *buf, int nbytes);
-extern int random_int_secret_init(void);
 
 #ifndef MODULE
 extern const struct file_operations random_fops, urandom_fops;
diff --git a/init/main.c b/init/main.c
index 23c275cca73a..a3af9296cafd 100644
--- a/init/main.c
+++ b/init/main.c
@@ -879,7 +879,6 @@ static void __init do_basic_setup(void)
 	do_ctors();
 	usermodehelper_enable();
 	do_initcalls();
-	random_int_secret_init();
 }
 
 static void __init do_pre_smp_initcalls(void)
-- 
2.11.0

[toc] | [prev] | [next] | [standalone]

Page 1 of 3  [1] 2 3  Next page →

Back to top | Article view | linux.kernel

csiph-web