view src/os/unix/ngx_gcc_atomic_amd64.h @ 7534:ac5a741d39cf

Gzip: use zlib to write header and trailer. When nginx is used with zlib patched with [1], which provides integration with the future IBM Z hardware deflate acceleration, it ends up computing CRC32 twice: one time in hardware, which always does this, and one time in software by explicitly calling crc32(). crc32() calls were added in changesets 133:b27548f540ad ("nginx-0.0.1- 2003-09-24-23:51:12 import") and 134:d57c6835225c ("nginx-0.0.1- 2003-09-26-09:45:21 import") as part of gzip wrapping feature - back then zlib did not support it. However, since then gzip wrapping was implemented in zlib v1.2.0.4, and it's already being used by nginx for log compression. This patch replaces hand-written gzip wrapping with the one provided by zlib. It simplifies the code, and makes it avoid computing CRC32 twice when using hardware acceleration. [1] https://github.com/madler/zlib/pull/410
author Ilya Leoshkevich <iii@linux.ibm.com>
date Fri, 12 Jul 2019 12:43:08 +0200
parents d620f497c50f
children
line wrap: on
line source


/*
 * Copyright (C) Igor Sysoev
 * Copyright (C) Nginx, Inc.
 */


#if (NGX_SMP)
#define NGX_SMP_LOCK  "lock;"
#else
#define NGX_SMP_LOCK
#endif


/*
 * "cmpxchgq  r, [m]":
 *
 *     if (rax == [m]) {
 *         zf = 1;
 *         [m] = r;
 *     } else {
 *         zf = 0;
 *         rax = [m];
 *     }
 *
 *
 * The "r" is any register, %rax (%r0) - %r16.
 * The "=a" and "a" are the %rax register.
 * Although we can return result in any register, we use "a" because it is
 * used in cmpxchgq anyway.  The result is actually in %al but not in $rax,
 * however as the code is inlined gcc can test %al as well as %rax.
 *
 * The "cc" means that flags were changed.
 */

static ngx_inline ngx_atomic_uint_t
ngx_atomic_cmp_set(ngx_atomic_t *lock, ngx_atomic_uint_t old,
    ngx_atomic_uint_t set)
{
    u_char  res;

    __asm__ volatile (

         NGX_SMP_LOCK
    "    cmpxchgq  %3, %1;   "
    "    sete      %0;       "

    : "=a" (res) : "m" (*lock), "a" (old), "r" (set) : "cc", "memory");

    return res;
}


/*
 * "xaddq  r, [m]":
 *
 *     temp = [m];
 *     [m] += r;
 *     r = temp;
 *
 *
 * The "+r" is any register, %rax (%r0) - %r16.
 * The "cc" means that flags were changed.
 */

static ngx_inline ngx_atomic_int_t
ngx_atomic_fetch_add(ngx_atomic_t *value, ngx_atomic_int_t add)
{
    __asm__ volatile (

         NGX_SMP_LOCK
    "    xaddq  %0, %1;   "

    : "+r" (add) : "m" (*value) : "cc", "memory");

    return add;
}


#define ngx_memory_barrier()    __asm__ volatile ("" ::: "memory")

#define ngx_cpu_pause()         __asm__ ("pause")