From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 1791) id 813393858C66; Mon, 6 Feb 2023 20:13:46 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 813393858C66 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1675714426; bh=sOWMdjedFLFD92K68I5gntDACO71YyWk65YnJGLHG60=; h=From:To:Subject:Date:From; b=VIOzQH1UaLkGW2Dgegh2jHa3IVXbr06VO75JItDncF4Tzmf2vN52FdAPUiQOnUH96 1JHQvyvvkoIYDKUo43S1jEjBI7rmoliIdn5voKEFID4PHfI0YoAKsNAhwJFomKbDnG TJ0nVPaIjAxt9vm3z3oBezCbEVuomYlkK5u/MZqQ= Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: Adhemerval Zanella To: glibc-cvs@sourceware.org Subject: [glibc] string: Improve generic stpcpy X-Act-Checkin: glibc X-Git-Author: Adhemerval Zanella X-Git-Refname: refs/heads/master X-Git-Oldrev: 367c31b5d61164db97834917f5487094ebef2f58 X-Git-Newrev: 30c1dfde313fa01e195e0759915f1356effdb7d6 Message-Id: <20230206201346.813393858C66@sourceware.org> Date: Mon, 6 Feb 2023 20:13:46 +0000 (GMT) List-Id: https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=30c1dfde313fa01e195e0759915f1356effdb7d6 commit 30c1dfde313fa01e195e0759915f1356effdb7d6 Author: Adhemerval Zanella Date: Tue Jan 31 15:46:08 2023 -0300 string: Improve generic stpcpy It follows the strategy: - Align the destination on word boundary using byte operations. - If source is also word aligned, read a word per time, check for null (using has_zero from string-fzb.h), and write the remaining bytes. - If source is not word aligned, loop by aligning the source, and merging the result of two reads. Similar to aligned case, check for null with has_zero, and write the remaining bytes if null is found. Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc64-linux-gnu, and powerpc-linux-gnu by removing the arch-specific assembly implementation and disabling multi-arch (it covers both LE and BE for 64 and 32 bits). Reviewed-by: Richard Henderson Reviewed-by: Noah Goldstein Diff: --- string/stpcpy.c | 92 +++++++++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 86 insertions(+), 6 deletions(-) diff --git a/string/stpcpy.c b/string/stpcpy.c index 8df5065cfe..dd0fef12ef 100644 --- a/string/stpcpy.c +++ b/string/stpcpy.c @@ -15,12 +15,12 @@ License along with the GNU C Library; if not, see . */ -#ifdef HAVE_CONFIG_H -# include -#endif - #define NO_MEMPCPY_STPCPY_REDIRECT #include +#include +#include +#include +#include #undef __stpcpy #undef stpcpy @@ -29,12 +29,92 @@ # define STPCPY __stpcpy #endif +static __always_inline char * +write_byte_from_word (op_t *dest, op_t word) +{ + char *d = (char *) dest; + for (size_t i = 0; i < OPSIZ; i++, ++d) + { + char c = extractbyte (word, i); + *d = c; + if (c == '\0') + break; + } + return d; +} + +static __always_inline char * +stpcpy_aligned_loop (op_t *restrict dst, const op_t *restrict src) +{ + op_t word; + while (1) + { + word = *src++; + if (has_zero (word)) + break; + *dst++ = word; + } + + return write_byte_from_word (dst, word); +} + +static __always_inline char * +stpcpy_unaligned_loop (op_t *restrict dst, const op_t *restrict src, + uintptr_t ofs) +{ + op_t w2a = *src++; + uintptr_t sh_1 = ofs * CHAR_BIT; + uintptr_t sh_2 = OPSIZ * CHAR_BIT - sh_1; + + op_t w2 = MERGE (w2a, sh_1, (op_t)-1, sh_2); + if (!has_zero (w2)) + { + op_t w2b; + + /* Unaligned loop. The invariant is that W2B, which is "ahead" of W1, + does not contain end-of-string. Therefore it is safe (and necessary) + to read another word from each while we do not have a difference. */ + while (1) + { + w2b = *src++; + w2 = MERGE (w2a, sh_1, w2b, sh_2); + /* Check if there is zero on w2a. */ + if (has_zero (w2)) + goto out; + *dst++ = w2; + if (has_zero (w2b)) + break; + w2a = w2b; + } + + /* Align the final partial of P2. */ + w2 = MERGE (w2b, sh_1, 0, sh_2); + } + +out: + return write_byte_from_word (dst, w2); +} + + /* Copy SRC to DEST, returning the address of the terminating '\0' in DEST. */ char * STPCPY (char *dest, const char *src) { - size_t len = strlen (src); - return memcpy (dest, src, len + 1) + len; + /* Copy just a few bytes to make DEST aligned. */ + size_t len = (-(uintptr_t) dest) % OPSIZ; + for (; len != 0; len--, ++dest) + { + char c = *src++; + *dest = c; + if (c == '\0') + return dest; + } + + /* DEST is now aligned to op_t, SRC may or may not be. */ + uintptr_t ofs = (uintptr_t) src % OPSIZ; + return ofs == 0 ? stpcpy_aligned_loop ((op_t*) dest, (const op_t *) src) + : stpcpy_unaligned_loop ((op_t*) dest, + (const op_t *) (src - ofs) , ofs); } weak_alias (__stpcpy, stpcpy) libc_hidden_def (__stpcpy)