summaryrefslogtreecommitdiff
path: root/fs/unicode
diff options
context:
space:
mode:
authorChristoph Hellwig <hch@lst.de>2021-09-15 09:00:04 +0200
committerGabriel Krisman Bertazi <krisman@collabora.com>2021-10-11 17:02:02 -0300
commit6ca99ce756c27852d1ea1e555045de1c920f30ed (patch)
tree3cedb519da25bfe7e8c3cce48f03c47599ce953e /fs/unicode
parentfbc59d65059ecfea8b746715e920c325cc16cede (diff)
unicode: cache the normalization tables in struct unicode_map
Instead of repeatedly looking up the version add pointers to the NFD and NFD+CF tables to struct unicode_map, and pass a unicode_map plus index to the functions using the normalization tables. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Diffstat (limited to 'fs/unicode')
-rw-r--r--fs/unicode/utf8-core.c37
-rw-r--r--fs/unicode/utf8-norm.c45
-rw-r--r--fs/unicode/utf8-selftest.c80
-rw-r--r--fs/unicode/utf8n.h10
4 files changed, 78 insertions, 94 deletions
diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
index dca2865c3bee..d9f713d38c0a 100644
--- a/fs/unicode/utf8-core.c
+++ b/fs/unicode/utf8-core.c
@@ -5,16 +5,13 @@
#include <linux/slab.h>
#include <linux/parser.h>
#include <linux/errno.h>
-#include <linux/unicode.h>
#include <linux/stringhash.h>
#include "utf8n.h"
int utf8_validate(const struct unicode_map *um, const struct qstr *str)
{
- const struct utf8data *data = utf8nfdi(um->version);
-
- if (utf8nlen(data, str->name, str->len) < 0)
+ if (utf8nlen(um, UTF8_NFDI, str->name, str->len) < 0)
return -1;
return 0;
}
@@ -23,14 +20,13 @@ EXPORT_SYMBOL(utf8_validate);
int utf8_strncmp(const struct unicode_map *um,
const struct qstr *s1, const struct qstr *s2)
{
- const struct utf8data *data = utf8nfdi(um->version);
struct utf8cursor cur1, cur2;
int c1, c2;
- if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0)
+ if (utf8ncursor(&cur1, um, UTF8_NFDI, s1->name, s1->len) < 0)
return -EINVAL;
- if (utf8ncursor(&cur2, data, s2->name, s2->len) < 0)
+ if (utf8ncursor(&cur2, um, UTF8_NFDI, s2->name, s2->len) < 0)
return -EINVAL;
do {
@@ -50,14 +46,13 @@ EXPORT_SYMBOL(utf8_strncmp);
int utf8_strncasecmp(const struct unicode_map *um,
const struct qstr *s1, const struct qstr *s2)
{
- const struct utf8data *data = utf8nfdicf(um->version);
struct utf8cursor cur1, cur2;
int c1, c2;
- if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0)
+ if (utf8ncursor(&cur1, um, UTF8_NFDICF, s1->name, s1->len) < 0)
return -EINVAL;
- if (utf8ncursor(&cur2, data, s2->name, s2->len) < 0)
+ if (utf8ncursor(&cur2, um, UTF8_NFDICF, s2->name, s2->len) < 0)
return -EINVAL;
do {
@@ -81,12 +76,11 @@ int utf8_strncasecmp_folded(const struct unicode_map *um,
const struct qstr *cf,
const struct qstr *s1)
{
- const struct utf8data *data = utf8nfdicf(um->version);
struct utf8cursor cur1;
int c1, c2;
int i = 0;
- if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0)
+ if (utf8ncursor(&cur1, um, UTF8_NFDICF, s1->name, s1->len) < 0)
return -EINVAL;
do {
@@ -105,11 +99,10 @@ EXPORT_SYMBOL(utf8_strncasecmp_folded);
int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
unsigned char *dest, size_t dlen)
{
- const struct utf8data *data = utf8nfdicf(um->version);
struct utf8cursor cur;
size_t nlen = 0;
- if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+ if (utf8ncursor(&cur, um, UTF8_NFDICF, str->name, str->len) < 0)
return -EINVAL;
for (nlen = 0; nlen < dlen; nlen++) {
@@ -128,12 +121,11 @@ EXPORT_SYMBOL(utf8_casefold);
int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
struct qstr *str)
{
- const struct utf8data *data = utf8nfdicf(um->version);
struct utf8cursor cur;
int c;
unsigned long hash = init_name_hash(salt);
- if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+ if (utf8ncursor(&cur, um, UTF8_NFDICF, str->name, str->len) < 0)
return -EINVAL;
while ((c = utf8byte(&cur))) {
@@ -149,11 +141,10 @@ EXPORT_SYMBOL(utf8_casefold_hash);
int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
unsigned char *dest, size_t dlen)
{
- const struct utf8data *data = utf8nfdi(um->version);
struct utf8cursor cur;
ssize_t nlen = 0;
- if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+ if (utf8ncursor(&cur, um, UTF8_NFDI, str->name, str->len) < 0)
return -EINVAL;
for (nlen = 0; nlen < dlen; nlen++) {
@@ -180,7 +171,17 @@ struct unicode_map *utf8_load(unsigned int version)
if (!um)
return ERR_PTR(-ENOMEM);
um->version = version;
+ um->ntab[UTF8_NFDI] = utf8nfdi(version);
+ if (!um->ntab[UTF8_NFDI])
+ goto out_free_um;
+ um->ntab[UTF8_NFDICF] = utf8nfdicf(version);
+ if (!um->ntab[UTF8_NFDICF])
+ goto out_free_um;
return um;
+
+out_free_um:
+ kfree(um);
+ return ERR_PTR(-EINVAL);
}
EXPORT_SYMBOL(utf8_load);
diff --git a/fs/unicode/utf8-norm.c b/fs/unicode/utf8-norm.c
index 1ac90fa00070..7c1f28ab31a8 100644
--- a/fs/unicode/utf8-norm.c
+++ b/fs/unicode/utf8-norm.c
@@ -309,21 +309,19 @@ utf8hangul(const char *str, unsigned char *hangul)
* is well-formed and corresponds to a known unicode code point. The
* shorthand for this will be "is valid UTF-8 unicode".
*/
-static utf8leaf_t *utf8nlookup(const struct utf8data *data,
- unsigned char *hangul, const char *s, size_t len)
+static utf8leaf_t *utf8nlookup(const struct unicode_map *um,
+ enum utf8_normalization n, unsigned char *hangul, const char *s,
+ size_t len)
{
- utf8trie_t *trie = NULL;
+ utf8trie_t *trie = utf8data + um->ntab[n]->offset;
int offlen;
int offset;
int mask;
int node;
- if (!data)
- return NULL;
if (len == 0)
return NULL;
- trie = utf8data + data->offset;
node = 1;
while (node) {
offlen = (*trie & OFFLEN) >> OFFLEN_SHIFT;
@@ -385,29 +383,28 @@ static utf8leaf_t *utf8nlookup(const struct utf8data *data,
*
* Forwards to utf8nlookup().
*/
-static utf8leaf_t *utf8lookup(const struct utf8data *data,
- unsigned char *hangul, const char *s)
+static utf8leaf_t *utf8lookup(const struct unicode_map *um,
+ enum utf8_normalization n, unsigned char *hangul, const char *s)
{
- return utf8nlookup(data, hangul, s, (size_t)-1);
+ return utf8nlookup(um, n, hangul, s, (size_t)-1);
}
/*
* Length of the normalization of s, touch at most len bytes.
* Return -1 if s is not valid UTF-8 unicode.
*/
-ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len)
+ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n,
+ const char *s, size_t len)
{
utf8leaf_t *leaf;
size_t ret = 0;
unsigned char hangul[UTF8HANGULLEAF];
- if (!data)
- return -1;
while (len && *s) {
- leaf = utf8nlookup(data, hangul, s, len);
+ leaf = utf8nlookup(um, n, hangul, s, len);
if (!leaf)
return -1;
- if (utf8agetab[LEAF_GEN(leaf)] > data->maxage)
+ if (utf8agetab[LEAF_GEN(leaf)] > um->ntab[n]->maxage)
ret += utf8clen(s);
else if (LEAF_CCC(leaf) == DECOMPOSE)
ret += strlen(LEAF_STR(leaf));
@@ -430,14 +427,13 @@ EXPORT_SYMBOL(utf8nlen);
*
* Returns -1 on error, 0 on success.
*/
-int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
- const char *s, size_t len)
+int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um,
+ enum utf8_normalization n, const char *s, size_t len)
{
- if (!data)
- return -1;
if (!s)
return -1;
- u8c->data = data;
+ u8c->um = um;
+ u8c->n = n;
u8c->s = s;
u8c->p = NULL;
u8c->ss = NULL;
@@ -512,9 +508,9 @@ int utf8byte(struct utf8cursor *u8c)
/* Look up the data for the current character. */
if (u8c->p) {
- leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s);
+ leaf = utf8lookup(u8c->um, u8c->n, u8c->hangul, u8c->s);
} else {
- leaf = utf8nlookup(u8c->data, u8c->hangul,
+ leaf = utf8nlookup(u8c->um, u8c->n, u8c->hangul,
u8c->s, u8c->len);
}
@@ -524,7 +520,8 @@ int utf8byte(struct utf8cursor *u8c)
ccc = LEAF_CCC(leaf);
/* Characters that are too new have CCC 0. */
- if (utf8agetab[LEAF_GEN(leaf)] > u8c->data->maxage) {
+ if (utf8agetab[LEAF_GEN(leaf)] >
+ u8c->um->ntab[u8c->n]->maxage) {
ccc = STOPPER;
} else if (ccc == DECOMPOSE) {
u8c->len -= utf8clen(u8c->s);
@@ -538,7 +535,7 @@ int utf8byte(struct utf8cursor *u8c)
goto ccc_mismatch;
}
- leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s);
+ leaf = utf8lookup(u8c->um, u8c->n, u8c->hangul, u8c->s);
if (!leaf)
return -1;
ccc = LEAF_CCC(leaf);
@@ -611,7 +608,6 @@ const struct utf8data *utf8nfdi(unsigned int maxage)
return NULL;
return &utf8nfdidata[i];
}
-EXPORT_SYMBOL(utf8nfdi);
const struct utf8data *utf8nfdicf(unsigned int maxage)
{
@@ -623,4 +619,3 @@ const struct utf8data *utf8nfdicf(unsigned int maxage)
return NULL;
return &utf8nfdicfdata[i];
}
-EXPORT_SYMBOL(utf8nfdicf);
diff --git a/fs/unicode/utf8-selftest.c b/fs/unicode/utf8-selftest.c
index 04628b50351d..cfa3832b75f4 100644
--- a/fs/unicode/utf8-selftest.c
+++ b/fs/unicode/utf8-selftest.c
@@ -18,9 +18,7 @@ unsigned int failed_tests;
unsigned int total_tests;
/* Tests will be based on this version. */
-#define latest_maj 12
-#define latest_min 1
-#define latest_rev 0
+#define UTF8_LATEST UNICODE_AGE(12, 1, 0)
#define _test(cond, func, line, fmt, ...) do { \
total_tests++; \
@@ -160,29 +158,22 @@ static const struct {
}
};
-static ssize_t utf8len(const struct utf8data *data, const char *s)
+static ssize_t utf8len(const struct unicode_map *um, enum utf8_normalization n,
+ const char *s)
{
- return utf8nlen(data, s, (size_t)-1);
+ return utf8nlen(um, n, s, (size_t)-1);
}
-static int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data,
- const char *s)
+static int utf8cursor(struct utf8cursor *u8c, const struct unicode_map *um,
+ enum utf8_normalization n, const char *s)
{
- return utf8ncursor(u8c, data, s, (unsigned int)-1);
+ return utf8ncursor(u8c, um, n, s, (unsigned int)-1);
}
-static void check_utf8_nfdi(void)
+static void check_utf8_nfdi(struct unicode_map *um)
{
int i;
struct utf8cursor u8c;
- const struct utf8data *data;
-
- data = utf8nfdi(UNICODE_AGE(latest_maj, latest_min, latest_rev));
- if (!data) {
- pr_err("%s: Unable to load utf8-%d.%d.%d. Skipping.\n",
- __func__, latest_maj, latest_min, latest_rev);
- return;
- }
for (i = 0; i < ARRAY_SIZE(nfdi_test_data); i++) {
int len = strlen(nfdi_test_data[i].str);
@@ -190,10 +181,11 @@ static void check_utf8_nfdi(void)
int j = 0;
unsigned char c;
- test((utf8len(data, nfdi_test_data[i].str) == nlen));
- test((utf8nlen(data, nfdi_test_data[i].str, len) == nlen));
+ test((utf8len(um, UTF8_NFDI, nfdi_test_data[i].str) == nlen));
+ test((utf8nlen(um, UTF8_NFDI, nfdi_test_data[i].str, len) ==
+ nlen));
- if (utf8cursor(&u8c, data, nfdi_test_data[i].str) < 0)
+ if (utf8cursor(&u8c, um, UTF8_NFDI, nfdi_test_data[i].str) < 0)
pr_err("can't create cursor\n");
while ((c = utf8byte(&u8c)) > 0) {
@@ -207,18 +199,10 @@ static void check_utf8_nfdi(void)
}
}
-static void check_utf8_nfdicf(void)
+static void check_utf8_nfdicf(struct unicode_map *um)
{
int i;
struct utf8cursor u8c;
- const struct utf8data *data;
-
- data = utf8nfdicf(UNICODE_AGE(latest_maj, latest_min, latest_rev));
- if (!data) {
- pr_err("%s: Unable to load utf8-%d.%d.%d. Skipping.\n",
- __func__, latest_maj, latest_min, latest_rev);
- return;
- }
for (i = 0; i < ARRAY_SIZE(nfdicf_test_data); i++) {
int len = strlen(nfdicf_test_data[i].str);
@@ -226,10 +210,13 @@ static void check_utf8_nfdicf(void)
int j = 0;
unsigned char c;
- test((utf8len(data, nfdicf_test_data[i].str) == nlen));
- test((utf8nlen(data, nfdicf_test_data[i].str, len) == nlen));
+ test((utf8len(um, UTF8_NFDICF, nfdicf_test_data[i].str) ==
+ nlen));
+ test((utf8nlen(um, UTF8_NFDICF, nfdicf_test_data[i].str, len) ==
+ nlen));
- if (utf8cursor(&u8c, data, nfdicf_test_data[i].str) < 0)
+ if (utf8cursor(&u8c, um, UTF8_NFDICF,
+ nfdicf_test_data[i].str) < 0)
pr_err("can't create cursor\n");
while ((c = utf8byte(&u8c)) > 0) {
@@ -243,16 +230,9 @@ static void check_utf8_nfdicf(void)
}
}
-static void check_utf8_comparisons(void)
+static void check_utf8_comparisons(struct unicode_map *table)
{
int i;
- struct unicode_map *table = utf8_load(UNICODE_AGE(12, 1, 0));
-
- if (IS_ERR(table)) {
- pr_err("%s: Unable to load utf8 %d.%d.%d. Skipping.\n",
- __func__, latest_maj, latest_min, latest_rev);
- return;
- }
for (i = 0; i < ARRAY_SIZE(nfdi_test_data); i++) {
const struct qstr s1 = {.name = nfdi_test_data[i].str,
@@ -273,8 +253,6 @@ static void check_utf8_comparisons(void)
test_f(!utf8_strncasecmp(table, &s1, &s2),
"%s %s comparison mismatch\n", s1.name, s2.name);
}
-
- utf8_unload(table);
}
static void check_supported_versions(void)
@@ -286,8 +264,7 @@ static void check_supported_versions(void)
test(utf8version_is_supported(UNICODE_AGE(9, 0, 0)));
/* Unicode 1x.0.0 (the latest version) should be supported. */
- test(utf8version_is_supported(
- UNICODE_AGE(latest_maj, latest_min, latest_rev)));
+ test(utf8version_is_supported(UTF8_LATEST));
/* Next versions don't exist. */
test(!utf8version_is_supported(UNICODE_AGE(13, 0, 0)));
@@ -297,19 +274,28 @@ static void check_supported_versions(void)
static int __init init_test_ucd(void)
{
+ struct unicode_map *um;
+
failed_tests = 0;
total_tests = 0;
+ um = utf8_load(UTF8_LATEST);
+ if (IS_ERR(um)) {
+ pr_err("%s: Unable to load utf8 table.\n", __func__);
+ return PTR_ERR(um);
+ }
+
check_supported_versions();
- check_utf8_nfdi();
- check_utf8_nfdicf();
- check_utf8_comparisons();
+ check_utf8_nfdi(um);
+ check_utf8_nfdicf(um);
+ check_utf8_comparisons(um);
if (!failed_tests)
pr_info("All %u tests passed\n", total_tests);
else
pr_err("%u out of %u tests failed\n", failed_tests,
total_tests);
+ utf8_unload(um);
return 0;
}
diff --git a/fs/unicode/utf8n.h b/fs/unicode/utf8n.h
index 736b6460a38c..206c89f0dbf7 100644
--- a/fs/unicode/utf8n.h
+++ b/fs/unicode/utf8n.h
@@ -39,7 +39,8 @@ extern const struct utf8data *utf8nfdicf(unsigned int maxage);
* Returns 0 if only ignorable code points are present.
* Returns -1 if the input is not valid UTF-8.
*/
-extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len);
+ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n,
+ const char *s, size_t len);
/* Needed in struct utf8cursor below. */
#define UTF8HANGULLEAF (12)
@@ -48,7 +49,8 @@ extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len);
* Cursor structure used by the normalizer.
*/
struct utf8cursor {
- const struct utf8data *data;
+ const struct unicode_map *um;
+ enum utf8_normalization n;
const char *s;
const char *p;
const char *ss;
@@ -65,8 +67,8 @@ struct utf8cursor {
* Returns 0 on success.
* Returns -1 on failure.
*/
-extern int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
- const char *s, size_t len);
+int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um,
+ enum utf8_normalization n, const char *s, size_t len);
/*
* Get the next byte in the normalization.