git/grep.h
Ævar Arnfjörð Bjarmason fbaceaac47 grep: add support for the PCRE v1 JIT API
Change the grep PCRE v1 code to use JIT when available. When PCRE
support was initially added in commit 63e7e9d8b6 ("git-grep: Learn
PCRE", 2011-05-09) PCRE had no JIT support, it was integrated into
8.20 released on 2011-10-21.

Enabling JIT support usually improves performance by more than
40%. The pattern compilation times are relatively slower, but those
relative numbers are tiny, and are easily made back in all but the
most trivial cases of grep. Detailed benchmarks & overview of
compilation times is at: http://sljit.sourceforge.net/pcre.html

With this change the difference in a t/perf/p7820-grep-engines.sh run
is, with just the /perl/ tests shown:

    $ GIT_PERF_REPEAT_COUNT=30 GIT_PERF_LARGE_REPO=~/g/linux GIT_PERF_MAKE_OPTS='-j8 USE_LIBPCRE=YesPlease CC=~/perl5/installed/bin/gcc NO_R_TO_GCC_LINKER=YesPlease CFLAGS=-O3 LIBPCREDIR=/home/avar/g/pcre/inst LDFLAGS=-Wl,-rpath,/home/avar/g/pcre/inst/lib' ./run HEAD~ HEAD p7820-grep-engines.sh
    Test                                           HEAD~             HEAD
    ---------------------------------------------------------------------------------------
    7820.3: perl grep 'how.to'                      0.35(1.11+0.43)   0.23(0.42+0.46) -34.3%
    7820.7: perl grep '^how to'                     0.64(2.71+0.36)   0.27(0.66+0.44) -57.8%
    7820.11: perl grep '[how] to'                   0.63(2.51+0.42)   0.33(0.98+0.39) -47.6%
    7820.15: perl grep '(e.t[^ ]*|v.ry) rare'       1.17(5.61+0.35)   0.34(1.08+0.46) -70.9%
    7820.19: perl grep 'm(ú|u)lt.b(æ|y)te'          0.43(1.52+0.44)   0.30(0.88+0.42) -30.2%

The conditional support for JIT is implemented as suggested in the
pcrejit(3) man page. E.g. defining PCRE_STUDY_JIT_COMPILE to 0 if it's
not present.

The implementation is relatively verbose because even if
PCRE_CONFIG_JIT is defined only a call to pcre_config() can determine
if the JIT is available, and if so the faster pcre_jit_exec() function
should be called instead of pcre_exec(), and a different (but not
complimentary!) function needs to be called to free pcre1_extra_info.

There's no graceful fallback if pcre_jit_stack_alloc() fails under
PCRE_CONFIG_JIT, instead the program will simply abort. I don't think
this is worth handling gracefully, it'll only fail in cases where
malloc() doesn't work, in which case we're screwed anyway.

That there's no assignment of `p->pcre1_jit_on = 0` when
PCRE_CONFIG_JIT isn't defined isn't a bug. The create_grep_pat()
function allocates the grep_pat allocates it with calloc(), so it's
guaranteed to be 0 when PCRE_CONFIG_JIT isn't defined.

I you're bisecting and find this change, check that your PCRE isn't
older than 8.32. This change intentionally broke really old versions
of PCRE, but that's fixed in follow-up commits.

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-26 12:59:05 +09:00

221 lines
4.9 KiB
C

#ifndef GREP_H
#define GREP_H
#include "color.h"
#ifdef USE_LIBPCRE1
#include <pcre.h>
#ifndef PCRE_STUDY_JIT_COMPILE
#define PCRE_STUDY_JIT_COMPILE 0
#endif
#else
typedef int pcre;
typedef int pcre_extra;
typedef int pcre_jit_stack;
#endif
#include "kwset.h"
#include "thread-utils.h"
#include "userdiff.h"
enum grep_pat_token {
GREP_PATTERN,
GREP_PATTERN_HEAD,
GREP_PATTERN_BODY,
GREP_AND,
GREP_OPEN_PAREN,
GREP_CLOSE_PAREN,
GREP_NOT,
GREP_OR
};
enum grep_context {
GREP_CONTEXT_HEAD,
GREP_CONTEXT_BODY
};
enum grep_header_field {
GREP_HEADER_FIELD_MIN = 0,
GREP_HEADER_AUTHOR = GREP_HEADER_FIELD_MIN,
GREP_HEADER_COMMITTER,
GREP_HEADER_REFLOG,
/* Must be at the end of the enum */
GREP_HEADER_FIELD_MAX
};
struct grep_pat {
struct grep_pat *next;
const char *origin;
int no;
enum grep_pat_token token;
char *pattern;
size_t patternlen;
enum grep_header_field field;
regex_t regexp;
pcre *pcre1_regexp;
pcre_extra *pcre1_extra_info;
pcre_jit_stack *pcre1_jit_stack;
const unsigned char *pcre1_tables;
int pcre1_jit_on;
kwset_t kws;
unsigned fixed:1;
unsigned ignore_case:1;
unsigned word_regexp:1;
};
enum grep_expr_node {
GREP_NODE_ATOM,
GREP_NODE_NOT,
GREP_NODE_AND,
GREP_NODE_TRUE,
GREP_NODE_OR
};
enum grep_pattern_type {
GREP_PATTERN_TYPE_UNSPECIFIED = 0,
GREP_PATTERN_TYPE_BRE,
GREP_PATTERN_TYPE_ERE,
GREP_PATTERN_TYPE_FIXED,
GREP_PATTERN_TYPE_PCRE
};
struct grep_expr {
enum grep_expr_node node;
unsigned hit;
union {
struct grep_pat *atom;
struct grep_expr *unary;
struct {
struct grep_expr *left;
struct grep_expr *right;
} binary;
} u;
};
struct grep_opt {
struct grep_pat *pattern_list;
struct grep_pat **pattern_tail;
struct grep_pat *header_list;
struct grep_pat **header_tail;
struct grep_expr *pattern_expression;
const char *prefix;
int prefix_length;
regex_t regexp;
int linenum;
int invert;
int ignore_case;
int status_only;
int name_only;
int unmatch_name_only;
int count;
int word_regexp;
int fixed;
int all_match;
int debug;
#define GREP_BINARY_DEFAULT 0
#define GREP_BINARY_NOMATCH 1
#define GREP_BINARY_TEXT 2
int binary;
int allow_textconv;
int extended;
int use_reflog_filter;
int pcre1;
int relative;
int pathname;
int null_following_name;
int color;
int max_depth;
int funcname;
int funcbody;
int extended_regexp_option;
int pattern_type_option;
char color_context[COLOR_MAXLEN];
char color_filename[COLOR_MAXLEN];
char color_function[COLOR_MAXLEN];
char color_lineno[COLOR_MAXLEN];
char color_match_context[COLOR_MAXLEN];
char color_match_selected[COLOR_MAXLEN];
char color_selected[COLOR_MAXLEN];
char color_sep[COLOR_MAXLEN];
int regflags;
unsigned pre_context;
unsigned post_context;
unsigned last_shown;
int show_hunk_mark;
int file_break;
int heading;
void *priv;
void (*output)(struct grep_opt *opt, const void *data, size_t size);
void *output_priv;
};
extern void init_grep_defaults(void);
extern int grep_config(const char *var, const char *value, void *);
extern void grep_init(struct grep_opt *, const char *prefix);
void grep_commit_pattern_type(enum grep_pattern_type, struct grep_opt *opt);
extern void append_grep_pat(struct grep_opt *opt, const char *pat, size_t patlen, const char *origin, int no, enum grep_pat_token t);
extern void append_grep_pattern(struct grep_opt *opt, const char *pat, const char *origin, int no, enum grep_pat_token t);
extern void append_header_grep_pattern(struct grep_opt *, enum grep_header_field, const char *);
extern void compile_grep_patterns(struct grep_opt *opt);
extern void free_grep_patterns(struct grep_opt *opt);
extern int grep_buffer(struct grep_opt *opt, char *buf, unsigned long size);
struct grep_source {
char *name;
enum grep_source_type {
GREP_SOURCE_SHA1,
GREP_SOURCE_FILE,
GREP_SOURCE_BUF,
GREP_SOURCE_SUBMODULE,
} type;
void *identifier;
char *buf;
unsigned long size;
char *path; /* for attribute lookups */
struct userdiff_driver *driver;
};
void grep_source_init(struct grep_source *gs, enum grep_source_type type,
const char *name, const char *path,
const void *identifier);
void grep_source_clear_data(struct grep_source *gs);
void grep_source_clear(struct grep_source *gs);
void grep_source_load_driver(struct grep_source *gs);
int grep_source(struct grep_opt *opt, struct grep_source *gs);
extern struct grep_opt *grep_opt_dup(const struct grep_opt *opt);
extern int grep_threads_ok(const struct grep_opt *opt);
#ifndef NO_PTHREADS
/*
* Mutex used around access to the attributes machinery if
* opt->use_threads. Must be initialized/destroyed by callers!
*/
extern int grep_use_locks;
extern pthread_mutex_t grep_attr_mutex;
extern pthread_mutex_t grep_read_mutex;
static inline void grep_read_lock(void)
{
if (grep_use_locks)
pthread_mutex_lock(&grep_read_mutex);
}
static inline void grep_read_unlock(void)
{
if (grep_use_locks)
pthread_mutex_unlock(&grep_read_mutex);
}
#else
#define grep_read_lock()
#define grep_read_unlock()
#endif
#endif