[LIB]: Textsearch infrastructure.

The textsearch infrastructure provides text searching
facitilies for both linear and non-linear data.
Individual search algorithms are implemented in modules
and chosen by the user.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 326 insertions, 1 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 2d4d4e3bc4aa..5bc2d523e6d1 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -63,5 +63,11 @@ config REED_SOLOMON_ENC16
 config REED_SOLOMON_DEC16
         boolean
 
-endmenu
+config TEXTSEARCH
+        boolean "Textsearch infrastructure"
+        default y
+        help
+          Say Y here if you want to provide a textsearch infrastructure
+          to other subsystems.
 
+endmenu
diff --git a/lib/Makefile b/lib/Makefile
index dcb4231916e2..3e917436ad60 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -36,6 +36,8 @@ obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
 obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
 obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
 
+lib-$(CONFIG_TEXTSEARCH) += textsearch.o
+
 hostprogs-y     := gen_crc32table
 clean-files     := crc32table.h
 
diff --git a/lib/textsearch.c b/lib/textsearch.c
new file mode 100644
index 000000000000..1e934c196f0f
--- /dev/null
+++ b/lib/textsearch.c
@@ -0,0 +1,317 @@
+/*
+ * lib/textsearch.c     Generic text search interface
+ *
+ *              This program is free software; you can redistribute it and/or
+ *              modify it under the terms of the GNU General Public License
+ *              as published by the Free Software Foundation; either version
+ *              2 of the License, or (at your option) any later version.
+ *
+ * Authors:     Thomas Graf <tgraf@suug.ch>
+ *              Pablo Neira Ayuso <pablo@eurodev.net>
+ *
+ * ==========================================================================
+ *
+ * INTRODUCTION
+ *
+ *   The textsearch infrastructure provides text searching facitilies for
+ *   both linear and non-linear data. Individual search algorithms are
+ *   implemented in modules and chosen by the user.
+ *
+ * ARCHITECTURE
+ *
+ *      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 _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 _find() or _next() to
+ *       fetch subsequent occurrences. A state variable is provided
+ *       to the algorihtm to store persistant 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 continously
+ *       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 _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() specyfing the searching algorithm and
+ *   the pattern to look for. The returned configuration may then be used
+ *   for an arbitary 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 patern or UINT_MAX if
+ *   no match was found. Subsequent occurences 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/config.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/rcupdate.h>
+#include <linux/err.h>
+#include <linux/textsearch.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;
+}
+
+/**
+ * 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.
+ */