diff options
Diffstat (limited to 'fs/udf/unicode.c')
| -rw-r--r-- | fs/udf/unicode.c | 208 |
1 files changed, 114 insertions, 94 deletions
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index 9e6099c26c2..44b815e57f9 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -23,7 +23,8 @@ #include <linux/kernel.h> #include <linux/string.h> /* for memset */ #include <linux/nls.h> -#include <linux/udf_fs.h> +#include <linux/crc-itu-t.h> +#include <linux/slab.h> #include "udf_sb.h" @@ -49,14 +50,16 @@ int udf_build_ustr(struct ustr *dest, dstring *ptr, int size) { int usesize; - if ((!dest) || (!ptr) || (!size)) + if (!dest || !ptr || !size) return -1; + BUG_ON(size < 2); - memset(dest, 0, sizeof(struct ustr)); - usesize = (size > UDF_NAME_LEN) ? UDF_NAME_LEN : size; + usesize = min_t(size_t, ptr[size - 1], sizeof(dest->u_name)); + usesize = min(usesize, size - 2); dest->u_cmpID = ptr[0]; - dest->u_len = ptr[size - 1]; - memcpy(dest->u_name, ptr + 1, usesize - 1); + dest->u_len = usesize; + memcpy(dest->u_name, ptr + 1, usesize); + memset(dest->u_name + usesize, 0, sizeof(dest->u_name) - usesize); return 0; } @@ -83,9 +86,6 @@ static int udf_build_ustr_exact(struct ustr *dest, dstring *ptr, int exactsize) * PURPOSE * Convert OSTA Compressed Unicode to the UTF-8 equivalent. * - * DESCRIPTION - * This routine is only called by udf_filldir(). - * * PRE-CONDITIONS * utf Pointer to UTF-8 output buffer. * ocu Pointer to OSTA Compressed Unicode input buffer @@ -99,49 +99,51 @@ static int udf_build_ustr_exact(struct ustr *dest, dstring *ptr, int exactsize) * November 12, 1997 - Andrew E. Mileski * Written, tested, and released. */ -int udf_CS0toUTF8(struct ustr *utf_o, struct ustr *ocu_i) +int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i) { - uint8_t *ocu; - uint32_t c; + const uint8_t *ocu; uint8_t cmp_id, ocu_len; int i; - ocu = ocu_i->u_name; - ocu_len = ocu_i->u_len; - cmp_id = ocu_i->u_cmpID; - utf_o->u_len = 0; - if (ocu_len == 0) { memset(utf_o, 0, sizeof(struct ustr)); - utf_o->u_cmpID = 0; - utf_o->u_len = 0; return 0; } - if ((cmp_id != 8) && (cmp_id != 16)) { - printk(KERN_ERR "udf: unknown compression code (%d) stri=%s\n", + cmp_id = ocu_i->u_cmpID; + if (cmp_id != 8 && cmp_id != 16) { + memset(utf_o, 0, sizeof(struct ustr)); + pr_err("unknown compression code (%d) stri=%s\n", cmp_id, ocu_i->u_name); return 0; } + ocu = ocu_i->u_name; + utf_o->u_len = 0; for (i = 0; (i < ocu_len) && (utf_o->u_len <= (UDF_NAME_LEN - 3));) { /* Expand OSTA compressed Unicode to Unicode */ - c = ocu[i++]; + uint32_t c = ocu[i++]; if (cmp_id == 16) c = (c << 8) | ocu[i++]; /* Compress Unicode to UTF-8 */ - if (c < 0x80U) { + if (c < 0x80U) utf_o->u_name[utf_o->u_len++] = (uint8_t)c; - } else if (c < 0x800U) { - utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xc0 | (c >> 6)); - utf_o->u_name[utf_o->u_len++] = (uint8_t)(0x80 | (c & 0x3f)); + else if (c < 0x800U) { + utf_o->u_name[utf_o->u_len++] = + (uint8_t)(0xc0 | (c >> 6)); + utf_o->u_name[utf_o->u_len++] = + (uint8_t)(0x80 | (c & 0x3f)); } else { - utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xe0 | (c >> 12)); - utf_o->u_name[utf_o->u_len++] = (uint8_t)(0x80 | ((c >> 6) & 0x3f)); - utf_o->u_name[utf_o->u_len++] = (uint8_t)(0x80 | (c & 0x3f)); + utf_o->u_name[utf_o->u_len++] = + (uint8_t)(0xe0 | (c >> 12)); + utf_o->u_name[utf_o->u_len++] = + (uint8_t)(0x80 | + ((c >> 6) & 0x3f)); + utf_o->u_name[utf_o->u_len++] = + (uint8_t)(0x80 | (c & 0x3f)); } } utf_o->u_cmpID = 8; @@ -232,16 +234,15 @@ try_again: goto error_out; } - if (max_val == 0xffffU) { + if (max_val == 0xffffU) ocu[++u_len] = (uint8_t)(utf_char >> 8); - } ocu[++u_len] = (uint8_t)(utf_char & 0xffU); } if (utf_cnt) { error_out: ocu[++u_len] = '?'; - printk(KERN_DEBUG "udf: bad UTF-8 character\n"); + printk(KERN_DEBUG pr_fmt("bad UTF-8 character\n")); } ocu[length - 1] = (uint8_t)u_len + 1; @@ -250,40 +251,42 @@ error_out: } static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o, - struct ustr *ocu_i) + const struct ustr *ocu_i) { - uint8_t *ocu; - uint32_t c; + const uint8_t *ocu; uint8_t cmp_id, ocu_len; - int i; + int i, len; - ocu = ocu_i->u_name; ocu_len = ocu_i->u_len; - cmp_id = ocu_i->u_cmpID; - utf_o->u_len = 0; - if (ocu_len == 0) { memset(utf_o, 0, sizeof(struct ustr)); - utf_o->u_cmpID = 0; - utf_o->u_len = 0; return 0; } - if ((cmp_id != 8) && (cmp_id != 16)) { - printk(KERN_ERR "udf: unknown compression code (%d) stri=%s\n", + cmp_id = ocu_i->u_cmpID; + if (cmp_id != 8 && cmp_id != 16) { + memset(utf_o, 0, sizeof(struct ustr)); + pr_err("unknown compression code (%d) stri=%s\n", cmp_id, ocu_i->u_name); return 0; } + ocu = ocu_i->u_name; + utf_o->u_len = 0; for (i = 0; (i < ocu_len) && (utf_o->u_len <= (UDF_NAME_LEN - 3));) { /* Expand OSTA compressed Unicode to Unicode */ - c = ocu[i++]; + uint32_t c = ocu[i++]; if (cmp_id == 16) c = (c << 8) | ocu[i++]; - utf_o->u_len += nls->uni2char(c, &utf_o->u_name[utf_o->u_len], - UDF_NAME_LEN - utf_o->u_len); + len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len], + UDF_NAME_LEN - utf_o->u_len); + /* Valid character? */ + if (len >= 0) + utf_o->u_len += len; + else + utf_o->u_name[utf_o->u_len++] = '?'; } utf_o->u_cmpID = 8; @@ -293,7 +296,8 @@ static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o, static int udf_NLStoCS0(struct nls_table *nls, dstring *ocu, struct ustr *uni, int length) { - unsigned len, i, max_val; + int len; + unsigned i, max_val; uint16_t uni_char; int u_len; @@ -305,8 +309,13 @@ try_again: u_len = 0U; for (i = 0U; i < uni->u_len; i++) { len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char); - if (len <= 0) + if (!len) continue; + /* Invalid character, deal with it */ + if (len < 0) { + len = 1; + uni_char = '?'; + } if (uni_char > max_val) { max_val = 0xffffU; @@ -327,34 +336,43 @@ try_again: int udf_get_filename(struct super_block *sb, uint8_t *sname, uint8_t *dname, int flen) { - struct ustr filename, unifilename; - int len; + struct ustr *filename, *unifilename; + int len = 0; - if (udf_build_ustr_exact(&unifilename, sname, flen)) { + filename = kmalloc(sizeof(struct ustr), GFP_NOFS); + if (!filename) return 0; - } + + unifilename = kmalloc(sizeof(struct ustr), GFP_NOFS); + if (!unifilename) + goto out1; + + if (udf_build_ustr_exact(unifilename, sname, flen)) + goto out2; if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8)) { - if (!udf_CS0toUTF8(&filename, &unifilename)) { - udf_debug("Failed in udf_get_filename: sname = %s\n", sname); - return 0; + if (!udf_CS0toUTF8(filename, unifilename)) { + udf_debug("Failed in udf_get_filename: sname = %s\n", + sname); + goto out2; } } else if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) { - if (!udf_CS0toNLS(UDF_SB(sb)->s_nls_map, &filename, &unifilename)) { - udf_debug("Failed in udf_get_filename: sname = %s\n", sname); - return 0; + if (!udf_CS0toNLS(UDF_SB(sb)->s_nls_map, filename, + unifilename)) { + udf_debug("Failed in udf_get_filename: sname = %s\n", + sname); + goto out2; } - } else { - return 0; - } - - len = udf_translate_to_linux(dname, filename.u_name, filename.u_len, - unifilename.u_name, unifilename.u_len); - if (len) { - return len; - } - - return 0; + } else + goto out2; + + len = udf_translate_to_linux(dname, filename->u_name, filename->u_len, + unifilename->u_name, unifilename->u_len); +out2: + kfree(unifilename); +out1: + kfree(filename); + return len; } int udf_put_filename(struct super_block *sb, const uint8_t *sname, @@ -363,23 +381,20 @@ int udf_put_filename(struct super_block *sb, const uint8_t *sname, struct ustr unifilename; int namelen; - if (!(udf_char_to_ustr(&unifilename, sname, flen))) { + if (!udf_char_to_ustr(&unifilename, sname, flen)) return 0; - } if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8)) { namelen = udf_UTF8toCS0(dname, &unifilename, UDF_NAME_LEN); - if (!namelen) { + if (!namelen) return 0; - } } else if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) { - namelen = udf_NLStoCS0(UDF_SB(sb)->s_nls_map, dname, &unifilename, UDF_NAME_LEN); - if (!namelen) { + namelen = udf_NLStoCS0(UDF_SB(sb)->s_nls_map, dname, + &unifilename, UDF_NAME_LEN); + if (!namelen) return 0; - } - } else { + } else return 0; - } return namelen; } @@ -389,8 +404,9 @@ int udf_put_filename(struct super_block *sb, const uint8_t *sname, #define CRC_MARK '#' #define EXT_SIZE 5 -static int udf_translate_to_linux(uint8_t *newName, uint8_t *udfName, int udfLen, - uint8_t *fidName, int fidNameLen) +static int udf_translate_to_linux(uint8_t *newName, uint8_t *udfName, + int udfLen, uint8_t *fidName, + int fidNameLen) { int index, newIndex = 0, needsCRC = 0; int extIndex = 0, newExtIndex = 0, hasExt = 0; @@ -409,13 +425,16 @@ static int udf_translate_to_linux(uint8_t *newName, uint8_t *udfName, int udfLen if (curr == '/' || curr == 0) { needsCRC = 1; curr = ILLEGAL_CHAR_MARK; - while (index + 1 < udfLen && (udfName[index + 1] == '/' || - udfName[index + 1] == 0)) + while (index + 1 < udfLen && + (udfName[index + 1] == '/' || + udfName[index + 1] == 0)) index++; - } if (curr == EXT_MARK && (udfLen - index - 1) <= EXT_SIZE) { - if (udfLen == index + 1) { + } + if (curr == EXT_MARK && + (udfLen - index - 1) <= EXT_SIZE) { + if (udfLen == index + 1) hasExt = 0; - } else { + else { hasExt = 1; extIndex = index; newExtIndex = newIndex; @@ -433,16 +452,18 @@ static int udf_translate_to_linux(uint8_t *newName, uint8_t *udfName, int udfLen if (hasExt) { int maxFilenameLen; - for(index = 0; index < EXT_SIZE && extIndex + index + 1 < udfLen; index++) { + for (index = 0; + index < EXT_SIZE && extIndex + index + 1 < udfLen; + index++) { curr = udfName[extIndex + index + 1]; if (curr == '/' || curr == 0) { needsCRC = 1; curr = ILLEGAL_CHAR_MARK; - while(extIndex + index + 2 < udfLen && - (index + 1 < EXT_SIZE - && (udfName[extIndex + index + 2] == '/' || - udfName[extIndex + index + 2] == 0))) + while (extIndex + index + 2 < udfLen && + (index + 1 < EXT_SIZE && + (udfName[extIndex + index + 2] == '/' || + udfName[extIndex + index + 2] == 0))) index++; } ext[localExtIndex++] = curr; @@ -452,11 +473,10 @@ static int udf_translate_to_linux(uint8_t *newName, uint8_t *udfName, int udfLen newIndex = maxFilenameLen; else newIndex = newExtIndex; - } else if (newIndex > 250) { + } else if (newIndex > 250) newIndex = 250; - } newName[newIndex++] = CRC_MARK; - valueCRC = udf_crc(fidName, fidNameLen, 0); + valueCRC = crc_itu_t(0, fidName, fidNameLen); newName[newIndex++] = hexChar[(valueCRC & 0xf000) >> 12]; newName[newIndex++] = hexChar[(valueCRC & 0x0f00) >> 8]; newName[newIndex++] = hexChar[(valueCRC & 0x00f0) >> 4]; |
