Original patch from: gentoo/src/patchsets/glibc/2.9/1020_all_glibc-2.9-strlen-hack.patch -= BEGIN original header =- http://sourceware.org/bugzilla/show_bug.cgi?id=5807 http://www.cl.cam.ac.uk/~am21/progtricks.html -= END original header =- diff -durN glibc-2_9.orig/string/strlen.c glibc-2_9/string/strlen.c --- glibc-2_9.orig/string/strlen.c 2005-12-14 12:09:07.000000000 +0100 +++ glibc-2_9/string/strlen.c 2009-02-02 22:00:51.000000000 +0100 @@ -32,7 +32,7 @@ { const char *char_ptr; const unsigned long int *longword_ptr; - unsigned long int longword, magic_bits, himagic, lomagic; + unsigned long int longword, himagic, lomagic; /* Handle the first few characters by reading one character at a time. Do this until CHAR_PTR is aligned on a longword boundary. */ @@ -42,28 +42,14 @@ if (*char_ptr == '\0') return char_ptr - str; - /* All these elucidatory comments refer to 4-byte longwords, - but the theory applies equally well to 8-byte longwords. */ - longword_ptr = (unsigned long int *) char_ptr; - /* Bits 31, 24, 16, and 8 of this number are zero. Call these bits - the "holes." Note that there is a hole just to the left of - each byte, with an extra at the end: - - bits: 01111110 11111110 11111110 11111111 - bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD - - The 1-bits make sure that carries propagate to the next 0-bit. - The 0-bits provide holes for carries to fall into. */ - magic_bits = 0x7efefeffL; himagic = 0x80808080L; lomagic = 0x01010101L; if (sizeof (longword) > 4) { /* 64-bit version of the magic. */ /* Do the shift in two steps to avoid a warning if long has 32 bits. */ - magic_bits = ((0x7efefefeL << 16) << 16) | 0xfefefeffL; himagic = ((himagic << 16) << 16) | himagic; lomagic = ((lomagic << 16) << 16) | lomagic; } @@ -75,56 +61,12 @@ if *any of the four* bytes in the longword in question are zero. */ for (;;) { - /* We tentatively exit the loop if adding MAGIC_BITS to - LONGWORD fails to change any of the hole bits of LONGWORD. - - 1) Is this safe? Will it catch all the zero bytes? - Suppose there is a byte with all zeros. Any carry bits - propagating from its left will fall into the hole at its - least significant bit and stop. Since there will be no - carry from its most significant bit, the LSB of the - byte to the left will be unchanged, and the zero will be - detected. - - 2) Is this worthwhile? Will it ignore everything except - zero bytes? Suppose every byte of LONGWORD has a bit set - somewhere. There will be a carry into bit 8. If bit 8 - is set, this will carry into bit 16. If bit 8 is clear, - one of bits 9-15 must be set, so there will be a carry - into bit 16. Similarly, there will be a carry into bit - 24. If one of bits 24-30 is set, there will be a carry - into bit 31, so all of the hole bits will be changed. - - The one misfire occurs when bits 24-30 are clear and bit - 31 is set; in this case, the hole at bit 31 is not - changed. If we had access to the processor carry flag, - we could close this loophole by putting the fourth hole - at bit 32! - - So it ignores everything except 128's, when they're aligned - properly. */ - longword = *longword_ptr++; - if ( -#if 0 - /* Add MAGIC_BITS to LONGWORD. */ - (((longword + magic_bits) - - /* Set those bits that were unchanged by the addition. */ - ^ ~longword) - - /* Look at only the hole bits. If any of the hole bits - are unchanged, most likely one of the bytes was a - zero. */ - & ~magic_bits) -#else - ((longword - lomagic) & himagic) -#endif - != 0) + /* This hack taken from Alan Mycroft's HAKMEMC postings. + See: http://www.cl.cam.ac.uk/~am21/progtricks.html */ + if (((longword - lomagic) & ~longword & himagic) != 0) { - /* Which of the bytes was the zero? If none of them were, it was - a misfire; continue the search. */ const char *cp = (const char *) (longword_ptr - 1);