summaryrefslogtreecommitdiff
path: root/Documentation/siphash.txt
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-07-15 12:58:58 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-07-15 12:58:58 -0700
commit486088bc4689f826b80aa317b45ac9e42e8b25ee (patch)
treeadf5847a6119d24da990d9e336f005c4a316e6be /Documentation/siphash.txt
parent52f6c588c77b76d548201470c2a28263a41b462b (diff)
parent43e5f7e1fa66531777c49791014c3124ea9208d8 (diff)
Merge tag 'standardize-docs' of git://git.lwn.net/linux
Pull documentation format standardization from Jonathan Corbet: "This series converts a number of top-level documents to the RST format without incorporating them into the Sphinx tree. The hope is to bring some uniformity to kernel documentation and, perhaps more importantly, have our existing docs serve as an example of the desired formatting for those that will be added later. Mauro has gone through and fixed up a lot of top-level documentation files to make them conform to the RST format, but without moving or renaming them in any way. This will help when we incorporate the ones we want to keep into the Sphinx doctree, but the real purpose is to bring a bit of uniformity to our documentation and let the top-level docs serve as examples for those writing new ones" * tag 'standardize-docs' of git://git.lwn.net/linux: (84 commits) docs: kprobes.txt: Fix whitespacing tee.txt: standardize document format cgroup-v2.txt: standardize document format dell_rbu.txt: standardize document format zorro.txt: standardize document format xz.txt: standardize document format xillybus.txt: standardize document format vfio.txt: standardize document format vfio-mediated-device.txt: standardize document format unaligned-memory-access.txt: standardize document format this_cpu_ops.txt: standardize document format svga.txt: standardize document format static-keys.txt: standardize document format smsc_ece1099.txt: standardize document format SM501.txt: standardize document format siphash.txt: standardize document format sgi-ioc4.txt: standardize document format SAK.txt: standardize document format rpmsg.txt: standardize document format robust-futexes.txt: standardize document format ...
Diffstat (limited to 'Documentation/siphash.txt')
-rw-r--r--Documentation/siphash.txt164
1 files changed, 89 insertions, 75 deletions
diff --git a/Documentation/siphash.txt b/Documentation/siphash.txt
index 908d348ff777..9965821ab333 100644
--- a/Documentation/siphash.txt
+++ b/Documentation/siphash.txt
@@ -1,6 +1,8 @@
- SipHash - a short input PRF
------------------------------------------------
-Written by Jason A. Donenfeld <jason@zx2c4.com>
+===========================
+SipHash - a short input PRF
+===========================
+
+:Author: Written by Jason A. Donenfeld <jason@zx2c4.com>
SipHash is a cryptographically secure PRF -- a keyed hash function -- that
performs very well for short inputs, hence the name. It was designed by
@@ -13,58 +15,61 @@ an input buffer or several input integers. It spits out an integer that is
indistinguishable from random. You may then use that integer as part of secure
sequence numbers, secure cookies, or mask it off for use in a hash table.
-1. Generating a key
+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:
+random numbers, either using get_random_bytes or get_random_once::
-siphash_key_t key;
-get_random_bytes(&key, sizeof(key));
+ siphash_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
+Using the functions
+===================
There are two variants of the function, one that takes a list of integers, and
-one that takes a buffer:
+one that takes a buffer::
-u64 siphash(const void *data, size_t len, const siphash_key_t *key);
+ u64 siphash(const void *data, size_t len, const siphash_key_t *key);
-And:
+And::
-u64 siphash_1u64(u64, const siphash_key_t *key);
-u64 siphash_2u64(u64, u64, const siphash_key_t *key);
-u64 siphash_3u64(u64, u64, u64, const siphash_key_t *key);
-u64 siphash_4u64(u64, u64, u64, u64, const siphash_key_t *key);
-u64 siphash_1u32(u32, const siphash_key_t *key);
-u64 siphash_2u32(u32, u32, const siphash_key_t *key);
-u64 siphash_3u32(u32, u32, u32, const siphash_key_t *key);
-u64 siphash_4u32(u32, u32, u32, u32, const siphash_key_t *key);
+ u64 siphash_1u64(u64, const siphash_key_t *key);
+ u64 siphash_2u64(u64, u64, const siphash_key_t *key);
+ u64 siphash_3u64(u64, u64, u64, const siphash_key_t *key);
+ u64 siphash_4u64(u64, u64, u64, u64, const siphash_key_t *key);
+ u64 siphash_1u32(u32, const siphash_key_t *key);
+ u64 siphash_2u32(u32, u32, const siphash_key_t *key);
+ u64 siphash_3u32(u32, u32, u32, const siphash_key_t *key);
+ u64 siphash_4u32(u32, u32, u32, u32, const siphash_key_t *key);
If you pass the generic siphash 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:
+Hashtable key function usage::
-struct some_hashtable {
- DECLARE_HASHTABLE(hashtable, 8);
- siphash_key_t key;
-};
+ struct some_hashtable {
+ DECLARE_HASHTABLE(hashtable, 8);
+ siphash_key_t key;
+ };
-void init_hashtable(struct some_hashtable *table)
-{
- get_random_bytes(&table->key, sizeof(table->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[siphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)];
-}
+ static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input)
+ {
+ return &table->hashtable[siphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)];
+ }
You may then iterate like usual over the returned hash bucket.
-4. Security
+Security
+========
SipHash has a very high security margin, with its 128-bit key. So long as the
key is kept secret, it is impossible for an attacker to guess the outputs of
@@ -73,7 +78,8 @@ is significant.
Linux implements the "2-4" variant of SipHash.
-5. Struct-passing Pitfalls
+Struct-passing Pitfalls
+=======================
Often times the XuY functions will not be large enough, and instead you'll
want to pass a pre-filled struct to siphash. When doing this, it's important
@@ -81,30 +87,32 @@ to always ensure the struct has no padding holes. The easiest way to do this
is to simply arrange the members of the struct in descending order of size,
and to use offsetendof() instead of sizeof() for getting the size. For
performance reasons, if possible, it's probably a good thing to align the
-struct to the right boundary. Here's an example:
-
-const struct {
- struct in6_addr saddr;
- u32 counter;
- u16 dport;
-} __aligned(SIPHASH_ALIGNMENT) combined = {
- .saddr = *(struct in6_addr *)saddr,
- .counter = counter,
- .dport = dport
-};
-u64 h = siphash(&combined, offsetofend(typeof(combined), dport), &secret);
-
-6. Resources
+struct to the right boundary. Here's an example::
+
+ const struct {
+ struct in6_addr saddr;
+ u32 counter;
+ u16 dport;
+ } __aligned(SIPHASH_ALIGNMENT) combined = {
+ .saddr = *(struct in6_addr *)saddr,
+ .counter = counter,
+ .dport = dport
+ };
+ u64 h = siphash(&combined, offsetofend(typeof(combined), dport), &secret);
+
+Resources
+=========
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>
+===============================================
+
+:Author: 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
@@ -120,7 +128,8 @@ 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
+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:
@@ -130,44 +139,49 @@ get_random_bytes(&key, sizeof(key));
If you're not deriving your key from here, you're doing it wrong.
-2. Using the functions
+Using the functions
+===================
There are two variants of the function, one that takes a list of integers, and
-one that takes a buffer:
+one that takes a buffer::
-u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key);
+ u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key);
-And:
+And::
-u32 hsiphash_1u32(u32, const hsiphash_key_t *key);
-u32 hsiphash_2u32(u32, u32, const hsiphash_key_t *key);
-u32 hsiphash_3u32(u32, u32, u32, const hsiphash_key_t *key);
-u32 hsiphash_4u32(u32, u32, u32, u32, const hsiphash_key_t *key);
+ u32 hsiphash_1u32(u32, const hsiphash_key_t *key);
+ u32 hsiphash_2u32(u32, u32, const hsiphash_key_t *key);
+ u32 hsiphash_3u32(u32, u32, u32, const hsiphash_key_t *key);
+ u32 hsiphash_4u32(u32, u32, u32, u32, const 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:
+Hashtable key function usage
+============================
+
+::
-struct some_hashtable {
- DECLARE_HASHTABLE(hashtable, 8);
- hsiphash_key_t key;
-};
+ 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));
-}
+ 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)];
-}
+ 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
+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