289 lines
13 KiB
Text
289 lines
13 KiB
Text
=pod
|
|
|
|
=head1 NAME
|
|
|
|
lh_new, lh_free, lh_insert, lh_delete, lh_retrieve, lh_doall, lh_doall_arg, lh_error - dynamic hash table
|
|
|
|
=head1 SYNOPSIS
|
|
|
|
#include <openssl/lhash.h>
|
|
|
|
LHASH *lh_new(LHASH_HASH_FN_TYPE hash, LHASH_COMP_FN_TYPE compare);
|
|
void lh_free(LHASH *table);
|
|
|
|
void *lh_insert(LHASH *table, void *data);
|
|
void *lh_delete(LHASH *table, void *data);
|
|
void *lh_retrieve(LHASH *table, void *data);
|
|
|
|
void lh_doall(LHASH *table, LHASH_DOALL_FN_TYPE func);
|
|
void lh_doall_arg(LHASH *table, LHASH_DOALL_ARG_FN_TYPE func,
|
|
void *arg);
|
|
|
|
int lh_error(LHASH *table);
|
|
|
|
typedef int (*LHASH_COMP_FN_TYPE)(const void *, const void *);
|
|
typedef unsigned long (*LHASH_HASH_FN_TYPE)(const void *);
|
|
typedef void (*LHASH_DOALL_FN_TYPE)(const void *);
|
|
typedef void (*LHASH_DOALL_ARG_FN_TYPE)(const void *, const void *);
|
|
|
|
=head1 DESCRIPTION
|
|
|
|
This library implements dynamic hash tables. The hash table entries
|
|
can be arbitrary structures. Usually they consist of key and value
|
|
fields.
|
|
|
|
lh_new() creates a new B<LHASH> structure to store arbitrary data
|
|
entries, and provides the 'hash' and 'compare' callbacks to be used in
|
|
organising the table's entries. The B<hash> callback takes a pointer
|
|
to a table entry as its argument and returns an unsigned long hash
|
|
value for its key field. The hash value is normally truncated to a
|
|
power of 2, so make sure that your hash function returns well mixed
|
|
low order bits. The B<compare> callback takes two arguments (pointers
|
|
to two hash table entries), and returns 0 if their keys are equal,
|
|
non-zero otherwise. If your hash table will contain items of some
|
|
particular type and the B<hash> and B<compare> callbacks hash/compare
|
|
these types, then the B<DECLARE_LHASH_HASH_FN> and
|
|
B<IMPLEMENT_LHASH_COMP_FN> macros can be used to create callback
|
|
wrappers of the prototypes required by lh_new(). These provide
|
|
per-variable casts before calling the type-specific callbacks written
|
|
by the application author. These macros, as well as those used for
|
|
the "doall" callbacks, are defined as;
|
|
|
|
#define DECLARE_LHASH_HASH_FN(f_name,o_type) \
|
|
unsigned long f_name##_LHASH_HASH(const void *);
|
|
#define IMPLEMENT_LHASH_HASH_FN(f_name,o_type) \
|
|
unsigned long f_name##_LHASH_HASH(const void *arg) { \
|
|
o_type a = (o_type)arg; \
|
|
return f_name(a); }
|
|
#define LHASH_HASH_FN(f_name) f_name##_LHASH_HASH
|
|
|
|
#define DECLARE_LHASH_COMP_FN(f_name,o_type) \
|
|
int f_name##_LHASH_COMP(const void *, const void *);
|
|
#define IMPLEMENT_LHASH_COMP_FN(f_name,o_type) \
|
|
int f_name##_LHASH_COMP(const void *arg1, const void *arg2) { \
|
|
o_type a = (o_type)arg1; \
|
|
o_type b = (o_type)arg2; \
|
|
return f_name(a,b); }
|
|
#define LHASH_COMP_FN(f_name) f_name##_LHASH_COMP
|
|
|
|
#define DECLARE_LHASH_DOALL_FN(f_name,o_type) \
|
|
void f_name##_LHASH_DOALL(const void *);
|
|
#define IMPLEMENT_LHASH_DOALL_FN(f_name,o_type) \
|
|
void f_name##_LHASH_DOALL(const void *arg) { \
|
|
o_type a = (o_type)arg; \
|
|
f_name(a); }
|
|
#define LHASH_DOALL_FN(f_name) f_name##_LHASH_DOALL
|
|
|
|
#define DECLARE_LHASH_DOALL_ARG_FN(f_name,o_type,a_type) \
|
|
void f_name##_LHASH_DOALL_ARG(const void *, const void *);
|
|
#define IMPLEMENT_LHASH_DOALL_ARG_FN(f_name,o_type,a_type) \
|
|
void f_name##_LHASH_DOALL_ARG(const void *arg1, const void *arg2) { \
|
|
o_type a = (o_type)arg1; \
|
|
a_type b = (a_type)arg2; \
|
|
f_name(a,b); }
|
|
#define LHASH_DOALL_ARG_FN(f_name) f_name##_LHASH_DOALL_ARG
|
|
|
|
An example of a hash table storing (pointers to) structures of type 'STUFF'
|
|
could be defined as follows;
|
|
|
|
/* Calculates the hash value of 'tohash' (implemented elsewhere) */
|
|
unsigned long STUFF_hash(const STUFF *tohash);
|
|
/* Orders 'arg1' and 'arg2' (implemented elsewhere) */
|
|
int STUFF_cmp(const STUFF *arg1, const STUFF *arg2);
|
|
/* Create the type-safe wrapper functions for use in the LHASH internals */
|
|
static IMPLEMENT_LHASH_HASH_FN(STUFF_hash, const STUFF *)
|
|
static IMPLEMENT_LHASH_COMP_FN(STUFF_cmp, const STUFF *);
|
|
/* ... */
|
|
int main(int argc, char *argv[]) {
|
|
/* Create the new hash table using the hash/compare wrappers */
|
|
LHASH *hashtable = lh_new(LHASH_HASH_FN(STUFF_hash),
|
|
LHASH_COMP_FN(STUFF_cmp));
|
|
/* ... */
|
|
}
|
|
|
|
lh_free() frees the B<LHASH> structure B<table>. Allocated hash table
|
|
entries will not be freed; consider using lh_doall() to deallocate any
|
|
remaining entries in the hash table (see below).
|
|
|
|
lh_insert() inserts the structure pointed to by B<data> into B<table>.
|
|
If there already is an entry with the same key, the old value is
|
|
replaced. Note that lh_insert() stores pointers, the data are not
|
|
copied.
|
|
|
|
lh_delete() deletes an entry from B<table>.
|
|
|
|
lh_retrieve() looks up an entry in B<table>. Normally, B<data> is
|
|
a structure with the key field(s) set; the function will return a
|
|
pointer to a fully populated structure.
|
|
|
|
lh_doall() will, for every entry in the hash table, call B<func> with
|
|
the data item as its parameter. For lh_doall() and lh_doall_arg(),
|
|
function pointer casting should be avoided in the callbacks (see
|
|
B<NOTE>) - instead, either declare the callbacks to match the
|
|
prototype required in lh_new() or use the declare/implement macros to
|
|
create type-safe wrappers that cast variables prior to calling your
|
|
type-specific callbacks. An example of this is illustrated here where
|
|
the callback is used to cleanup resources for items in the hash table
|
|
prior to the hashtable itself being deallocated:
|
|
|
|
/* Cleans up resources belonging to 'a' (this is implemented elsewhere) */
|
|
void STUFF_cleanup(STUFF *a);
|
|
/* Implement a prototype-compatible wrapper for "STUFF_cleanup" */
|
|
IMPLEMENT_LHASH_DOALL_FN(STUFF_cleanup, STUFF *)
|
|
/* ... then later in the code ... */
|
|
/* So to run "STUFF_cleanup" against all items in a hash table ... */
|
|
lh_doall(hashtable, LHASH_DOALL_FN(STUFF_cleanup));
|
|
/* Then the hash table itself can be deallocated */
|
|
lh_free(hashtable);
|
|
|
|
When doing this, be careful if you delete entries from the hash table
|
|
in your callbacks: the table may decrease in size, moving the item
|
|
that you are currently on down lower in the hash table - this could
|
|
cause some entries to be skipped during the iteration. The second
|
|
best solution to this problem is to set hash-E<gt>down_load=0 before
|
|
you start (which will stop the hash table ever decreasing in size).
|
|
The best solution is probably to avoid deleting items from the hash
|
|
table inside a "doall" callback!
|
|
|
|
lh_doall_arg() is the same as lh_doall() except that B<func> will be
|
|
called with B<arg> as the second argument and B<func> should be of
|
|
type B<LHASH_DOALL_ARG_FN_TYPE> (a callback prototype that is passed
|
|
both the table entry and an extra argument). As with lh_doall(), you
|
|
can instead choose to declare your callback with a prototype matching
|
|
the types you are dealing with and use the declare/implement macros to
|
|
create compatible wrappers that cast variables before calling your
|
|
type-specific callbacks. An example of this is demonstrated here
|
|
(printing all hash table entries to a BIO that is provided by the
|
|
caller):
|
|
|
|
/* Prints item 'a' to 'output_bio' (this is implemented elsewhere) */
|
|
void STUFF_print(const STUFF *a, BIO *output_bio);
|
|
/* Implement a prototype-compatible wrapper for "STUFF_print" */
|
|
static IMPLEMENT_LHASH_DOALL_ARG_FN(STUFF_print, const STUFF *, BIO *)
|
|
/* ... then later in the code ... */
|
|
/* Print out the entire hashtable to a particular BIO */
|
|
lh_doall_arg(hashtable, LHASH_DOALL_ARG_FN(STUFF_print), logging_bio);
|
|
|
|
lh_error() can be used to determine if an error occurred in the last
|
|
operation. lh_error() is a macro.
|
|
|
|
=head1 RETURN VALUES
|
|
|
|
lh_new() returns B<NULL> on error, otherwise a pointer to the new
|
|
B<LHASH> structure.
|
|
|
|
When a hash table entry is replaced, lh_insert() returns the value
|
|
being replaced. B<NULL> is returned on normal operation and on error.
|
|
|
|
lh_delete() returns the entry being deleted. B<NULL> is returned if
|
|
there is no such value in the hash table.
|
|
|
|
lh_retrieve() returns the hash table entry if it has been found,
|
|
B<NULL> otherwise.
|
|
|
|
lh_error() returns 1 if an error occurred in the last operation, 0
|
|
otherwise.
|
|
|
|
lh_free(), lh_doall() and lh_doall_arg() return no values.
|
|
|
|
=head1 NOTE
|
|
|
|
The various LHASH macros and callback types exist to make it possible
|
|
to write type-safe code without resorting to function-prototype
|
|
casting - an evil that makes application code much harder to
|
|
audit/verify and also opens the window of opportunity for stack
|
|
corruption and other hard-to-find bugs. It also, apparently, violates
|
|
ANSI-C.
|
|
|
|
The LHASH code regards table entries as constant data. As such, it
|
|
internally represents lh_insert()'d items with a "const void *"
|
|
pointer type. This is why callbacks such as those used by lh_doall()
|
|
and lh_doall_arg() declare their prototypes with "const", even for the
|
|
parameters that pass back the table items' data pointers - for
|
|
consistency, user-provided data is "const" at all times as far as the
|
|
LHASH code is concerned. However, as callers are themselves providing
|
|
these pointers, they can choose whether they too should be treating
|
|
all such parameters as constant.
|
|
|
|
As an example, a hash table may be maintained by code that, for
|
|
reasons of encapsulation, has only "const" access to the data being
|
|
indexed in the hash table (ie. it is returned as "const" from
|
|
elsewhere in their code) - in this case the LHASH prototypes are
|
|
appropriate as-is. Conversely, if the caller is responsible for the
|
|
life-time of the data in question, then they may well wish to make
|
|
modifications to table item passed back in the lh_doall() or
|
|
lh_doall_arg() callbacks (see the "STUFF_cleanup" example above). If
|
|
so, the caller can either cast the "const" away (if they're providing
|
|
the raw callbacks themselves) or use the macros to declare/implement
|
|
the wrapper functions without "const" types.
|
|
|
|
Callers that only have "const" access to data they're indexing in a
|
|
table, yet declare callbacks without constant types (or cast the
|
|
"const" away themselves), are therefore creating their own risks/bugs
|
|
without being encouraged to do so by the API. On a related note,
|
|
those auditing code should pay special attention to any instances of
|
|
DECLARE/IMPLEMENT_LHASH_DOALL_[ARG_]_FN macros that provide types
|
|
without any "const" qualifiers.
|
|
|
|
=head1 BUGS
|
|
|
|
lh_insert() returns B<NULL> both for success and error.
|
|
|
|
=head1 INTERNALS
|
|
|
|
The following description is based on the SSLeay documentation:
|
|
|
|
The B<lhash> library implements a hash table described in the
|
|
I<Communications of the ACM> in 1991. What makes this hash table
|
|
different is that as the table fills, the hash table is increased (or
|
|
decreased) in size via OPENSSL_realloc(). When a 'resize' is done, instead of
|
|
all hashes being redistributed over twice as many 'buckets', one
|
|
bucket is split. So when an 'expand' is done, there is only a minimal
|
|
cost to redistribute some values. Subsequent inserts will cause more
|
|
single 'bucket' redistributions but there will never be a sudden large
|
|
cost due to redistributing all the 'buckets'.
|
|
|
|
The state for a particular hash table is kept in the B<LHASH> structure.
|
|
The decision to increase or decrease the hash table size is made
|
|
depending on the 'load' of the hash table. The load is the number of
|
|
items in the hash table divided by the size of the hash table. The
|
|
default values are as follows. If (hash->up_load E<lt> load) =E<gt>
|
|
expand. if (hash-E<gt>down_load E<gt> load) =E<gt> contract. The
|
|
B<up_load> has a default value of 1 and B<down_load> has a default value
|
|
of 2. These numbers can be modified by the application by just
|
|
playing with the B<up_load> and B<down_load> variables. The 'load' is
|
|
kept in a form which is multiplied by 256. So
|
|
hash-E<gt>up_load=8*256; will cause a load of 8 to be set.
|
|
|
|
If you are interested in performance the field to watch is
|
|
num_comp_calls. The hash library keeps track of the 'hash' value for
|
|
each item so when a lookup is done, the 'hashes' are compared, if
|
|
there is a match, then a full compare is done, and
|
|
hash-E<gt>num_comp_calls is incremented. If num_comp_calls is not equal
|
|
to num_delete plus num_retrieve it means that your hash function is
|
|
generating hashes that are the same for different values. It is
|
|
probably worth changing your hash function if this is the case because
|
|
even if your hash table has 10 items in a 'bucket', it can be searched
|
|
with 10 B<unsigned long> compares and 10 linked list traverses. This
|
|
will be much less expensive that 10 calls to your compare function.
|
|
|
|
lh_strhash() is a demo string hashing function:
|
|
|
|
unsigned long lh_strhash(const char *c);
|
|
|
|
Since the B<LHASH> routines would normally be passed structures, this
|
|
routine would not normally be passed to lh_new(), rather it would be
|
|
used in the function passed to lh_new().
|
|
|
|
=head1 SEE ALSO
|
|
|
|
L<lh_stats(3)|lh_stats(3)>
|
|
|
|
=head1 HISTORY
|
|
|
|
The B<lhash> library is available in all versions of SSLeay and OpenSSL.
|
|
lh_error() was added in SSLeay 0.9.1b.
|
|
|
|
This manpage is derived from the SSLeay documentation.
|
|
|
|
=cut
|