1
0
Fork 0
alistair23-linux/lib/textsearch.c

324 lines
9.3 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* lib/textsearch.c Generic text search interface
*
* Authors: Thomas Graf <tgraf@suug.ch>
* Pablo Neira Ayuso <pablo@netfilter.org>
*
* ==========================================================================
*/
/**
* DOC: ts_intro
* INTRODUCTION
*
* The textsearch infrastructure provides text searching facilities for
* both linear and non-linear data. Individual search algorithms are
* implemented in modules and chosen by the user.
*
* ARCHITECTURE
*
* .. code-block:: none
*
* User
* +----------------+
* | finish()|<--------------(6)-----------------+
* |get_next_block()|<--------------(5)---------------+ |
* | | Algorithm | |
* | | +------------------------------+
* | | | init() find() destroy() |
* | | +------------------------------+
* | | Core API ^ ^ ^
* | | +---------------+ (2) (4) (8)
* | (1)|----->| prepare() |---+ | |
* | (3)|----->| find()/next() |-----------+ |
* | (7)|----->| destroy() |----------------------+
* +----------------+ +---------------+
*
* (1) User configures a search by calling textsearch_prepare() specifying
* the search parameters such as the pattern and algorithm name.
* (2) Core requests the algorithm to allocate and initialize a search
* configuration according to the specified parameters.
* (3) User starts the search(es) by calling textsearch_find() or
* textsearch_next() to fetch subsequent occurrences. A state variable
* is provided to the algorithm to store persistent variables.
* (4) Core eventually resets the search offset and forwards the find()
* request to the algorithm.
* (5) Algorithm calls get_next_block() provided by the user continuously
* to fetch the data to be searched in block by block.
* (6) Algorithm invokes finish() after the last call to get_next_block
* to clean up any leftovers from get_next_block. (Optional)
* (7) User destroys the configuration by calling textsearch_destroy().
* (8) Core notifies the algorithm to destroy algorithm specific
* allocations. (Optional)
*
* USAGE
*
* Before a search can be performed, a configuration must be created
* by calling textsearch_prepare() specifying the searching algorithm,
* the pattern to look for and flags. As a flag, you can set TS_IGNORECASE
* to perform case insensitive matching. But it might slow down
* performance of algorithm, so you should use it at own your risk.
* The returned configuration may then be used for an arbitrary
* amount of times and even in parallel as long as a separate struct
* ts_state variable is provided to every instance.
*
* The actual search is performed by either calling
* textsearch_find_continuous() for linear data or by providing
* an own get_next_block() implementation and
* calling textsearch_find(). Both functions return
* the position of the first occurrence of the pattern or UINT_MAX if
* no match was found. Subsequent occurrences can be found by calling
* textsearch_next() regardless of the linearity of the data.
*
* Once you're done using a configuration it must be given back via
* textsearch_destroy.
*
* EXAMPLE::
*
* int pos;
* struct ts_config *conf;
* struct ts_state state;
* const char *pattern = "chicken";
* const char *example = "We dance the funky chicken";
*
* conf = textsearch_prepare("kmp", pattern, strlen(pattern),
* GFP_KERNEL, TS_AUTOLOAD);
* if (IS_ERR(conf)) {
* err = PTR_ERR(conf);
* goto errout;
* }
*
* pos = textsearch_find_continuous(conf, &state, example, strlen(example));
* if (pos != UINT_MAX)
* panic("Oh my god, dancing chickens at %d\n", pos);
*
* textsearch_destroy(conf);
*/
/* ========================================================================== */
#include <linux/module.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/rculist.h>
#include <linux/rcupdate.h>
#include <linux/err.h>
#include <linux/textsearch.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 02:04:11 -06:00
#include <linux/slab.h>
static LIST_HEAD(ts_ops);
static DEFINE_SPINLOCK(ts_mod_lock);
static inline struct ts_ops *lookup_ts_algo(const char *name)
{
struct ts_ops *o;
rcu_read_lock();
list_for_each_entry_rcu(o, &ts_ops, list) {
if (!strcmp(name, o->name)) {
if (!try_module_get(o->owner))
o = NULL;
rcu_read_unlock();
return o;
}
}
rcu_read_unlock();
return NULL;
}
/**
* textsearch_register - register a textsearch module
* @ops: operations lookup table
*
* This function must be called by textsearch modules to announce
* their presence. The specified &@ops must have %name set to a
* unique identifier and the callbacks find(), init(), get_pattern(),
* and get_pattern_len() must be implemented.
*
* Returns 0 or -EEXISTS if another module has already registered
* with same name.
*/
int textsearch_register(struct ts_ops *ops)
{
int err = -EEXIST;
struct ts_ops *o;
if (ops->name == NULL || ops->find == NULL || ops->init == NULL ||
ops->get_pattern == NULL || ops->get_pattern_len == NULL)
return -EINVAL;
spin_lock(&ts_mod_lock);
list_for_each_entry(o, &ts_ops, list) {
if (!strcmp(ops->name, o->name))
goto errout;
}
list_add_tail_rcu(&ops->list, &ts_ops);
err = 0;
errout:
spin_unlock(&ts_mod_lock);
return err;
}
EXPORT_SYMBOL(textsearch_register);
/**
* textsearch_unregister - unregister a textsearch module
* @ops: operations lookup table
*
* This function must be called by textsearch modules to announce
* their disappearance for examples when the module gets unloaded.
* The &ops parameter must be the same as the one during the
* registration.
*
* Returns 0 on success or -ENOENT if no matching textsearch
* registration was found.
*/
int textsearch_unregister(struct ts_ops *ops)
{
int err = 0;
struct ts_ops *o;
spin_lock(&ts_mod_lock);
list_for_each_entry(o, &ts_ops, list) {
if (o == ops) {
list_del_rcu(&o->list);
goto out;
}
}
err = -ENOENT;
out:
spin_unlock(&ts_mod_lock);
return err;
}
EXPORT_SYMBOL(textsearch_unregister);
struct ts_linear_state
{
unsigned int len;
const void *data;
};
static unsigned int get_linear_data(unsigned int consumed, const u8 **dst,
struct ts_config *conf,
struct ts_state *state)
{
struct ts_linear_state *st = (struct ts_linear_state *) state->cb;
if (likely(consumed < st->len)) {
*dst = st->data + consumed;
return st->len - consumed;
}
return 0;
}
/**
* textsearch_find_continuous - search a pattern in continuous/linear data
* @conf: search configuration
* @state: search state
* @data: data to search in
* @len: length of data
*
* A simplified version of textsearch_find() for continuous/linear data.
* Call textsearch_next() to retrieve subsequent matches.
*
* Returns the position of first occurrence of the pattern or
* %UINT_MAX if no occurrence was found.
*/
unsigned int textsearch_find_continuous(struct ts_config *conf,
struct ts_state *state,
const void *data, unsigned int len)
{
struct ts_linear_state *st = (struct ts_linear_state *) state->cb;
conf->get_next_block = get_linear_data;
st->data = data;
st->len = len;
return textsearch_find(conf, state);
}
EXPORT_SYMBOL(textsearch_find_continuous);
/**
* textsearch_prepare - Prepare a search
* @algo: name of search algorithm
* @pattern: pattern data
* @len: length of pattern
* @gfp_mask: allocation mask
* @flags: search flags
*
* Looks up the search algorithm module and creates a new textsearch
* configuration for the specified pattern.
*
* Note: The format of the pattern may not be compatible between
* the various search algorithms.
*
* Returns a new textsearch configuration according to the specified
* parameters or a ERR_PTR(). If a zero length pattern is passed, this
* function returns EINVAL.
*/
struct ts_config *textsearch_prepare(const char *algo, const void *pattern,
unsigned int len, gfp_t gfp_mask, int flags)
{
int err = -ENOENT;
struct ts_config *conf;
struct ts_ops *ops;
if (len == 0)
return ERR_PTR(-EINVAL);
ops = lookup_ts_algo(algo);
#ifdef CONFIG_MODULES
/*
* Why not always autoload you may ask. Some users are
* in a situation where requesting a module may deadlock,
* especially when the module is located on a NFS mount.
*/
if (ops == NULL && flags & TS_AUTOLOAD) {
request_module("ts_%s", algo);
ops = lookup_ts_algo(algo);
}
#endif
if (ops == NULL)
goto errout;
conf = ops->init(pattern, len, gfp_mask, flags);
if (IS_ERR(conf)) {
err = PTR_ERR(conf);
goto errout;
}
conf->ops = ops;
return conf;
errout:
if (ops)
module_put(ops->owner);
return ERR_PTR(err);
}
EXPORT_SYMBOL(textsearch_prepare);
/**
* textsearch_destroy - destroy a search configuration
* @conf: search configuration
*
* Releases all references of the configuration and frees
* up the memory.
*/
void textsearch_destroy(struct ts_config *conf)
{
if (conf->ops) {
if (conf->ops->destroy)
conf->ops->destroy(conf);
module_put(conf->ops->owner);
}
kfree(conf);
}
EXPORT_SYMBOL(textsearch_destroy);