git/grep.h
Ævar Arnfjörð Bjarmason 34489239d0 grep: stop "using" a custom JIT stack with PCRE v2
As reported in [1] the code I added in 94da9193a6 ("grep: add support
for PCRE v2", 2017-06-01) to use a custom JIT stack has never
worked. It was incorrectly copy/pasted from code I added in
fbaceaac47 ("grep: add support for the PCRE v1 JIT API", 2017-05-25),
which did work.

Thus our intention of starting with 1 byte of stack at a maximum of 1
MB didn't happen, we'd always use the 32 KB stack provided by PCRE
v2's jit_machine_stack_exec()[2]. The reason I allocated a custom
stack at all was this advice in pcrejit(3) (same in pcre2jit(3)):

    "By default, it uses 32KiB on the machine stack. However, some
    large or complicated patterns need more than this"

Since we've haven't had any reports of users running into
PCRE2_ERROR_JIT_STACKLIMIT in the wild I think we can safely assume
that we can just use the library defaults instead and drop this
code. This won't change with the wider use of PCRE v2 in
ed0479ce3d ("Merge branch 'ab/no-kwset' into next", 2019-07-15), a
fixed string search is not a "large or complicated pattern".

For good measure I ran the performance test noted in 94da9193a6,
although the command is simpler now due to my 0f50c8e32c ("Makefile:
remove the NO_R_TO_GCC_LINKER flag", 2019-05-17):

    GIT_PERF_REPEAT_COUNT=30 GIT_PERF_LARGE_REPO=~/g/linux GIT_PERF_MAKE_OPTS='-j8 USE_LIBPCRE2=Y CFLAGS=-O3 LIBPCREDIR=/home/avar/g/pcre2/inst' ./run HEAD~ HEAD p7820-grep-engines.sh

Just the /perl/ results are:

    Test                                            HEAD~             HEAD
    ---------------------------------------------------------------------------------------
    7820.3: perl grep 'how.to'                      0.17(0.27+0.65)   0.17(0.24+0.68) +0.0%
    7820.7: perl grep '^how to'                     0.16(0.23+0.66)   0.16(0.23+0.67) +0.0%
    7820.11: perl grep '[how] to'                   0.18(0.35+0.62)   0.18(0.33+0.65) +0.0%
    7820.15: perl grep '(e.t[^ ]*|v.ry) rare'       0.17(0.45+0.54)   0.17(0.49+0.50) +0.0%
    7820.19: perl grep 'm(ú|u)lt.b(æ|y)te'          0.16(0.33+0.58)   0.16(0.29+0.62) +0.0%

So, as expected there's no change, and running with valgrind reveals
that we have fewer allocations now.

As noted in [3] there are known regexes that will fail with the lower
stack limit, the way GNU grep fixed it is interesting, although I
believe the implementation is overly verbose, they could make PCRE v2
handle that gradual re-allocation, that's what min/max memory is
for.

So we might end up bringing this back, I'm more inclined to just kick
such cases upstairs to PCRE maintainers as a bug, perhaps they'll add
some overall "just allocate more then" flag to make this easier. In
any case there's no functional change here, we didn't have a custom
stack, so let's apply this first, we can always revert it later.

1. https://public-inbox.org/git/20190721194052.15440-1-carenas@gmail.com/
2. I didn't really intend to start with 1 byte, looking at the PCRE v2
   code again what happened is that I cargo-culted some of PCRE v2's
   own test code which was meant to test re-allocations. It's more
   sane to start with say 32 KB with a max of 1 MB, as pcre2grep.c
   does.
3. https://public-inbox.org/git/CAPUEspjj+fG8QDmf=bZXktfpLgkgiu34HTjKLhm-cmEE04FE-A@mail.gmail.com/

Reported-by: Carlo Marcelo Arenas Belón <carenas@gmail.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-07-26 13:56:40 -07:00

248 lines
5.4 KiB
C

#ifndef GREP_H
#define GREP_H
#include "color.h"
#ifdef USE_LIBPCRE1
#include <pcre.h>
#ifdef PCRE_CONFIG_JIT
#if PCRE_MAJOR >= 8 && PCRE_MINOR >= 32
#ifndef NO_LIBPCRE1_JIT
#define GIT_PCRE1_USE_JIT
#define GIT_PCRE_STUDY_JIT_COMPILE PCRE_STUDY_JIT_COMPILE
#endif
#endif
#endif
#ifndef GIT_PCRE_STUDY_JIT_COMPILE
#define GIT_PCRE_STUDY_JIT_COMPILE 0
#endif
#if PCRE_MAJOR <= 8 && PCRE_MINOR < 20
typedef int pcre_jit_stack;
#endif
#else
typedef int pcre;
typedef int pcre_extra;
typedef int pcre_jit_stack;
#endif
#ifdef USE_LIBPCRE2
#define PCRE2_CODE_UNIT_WIDTH 8
#include <pcre2.h>
#else
typedef int pcre2_code;
typedef int pcre2_match_data;
typedef int pcre2_compile_context;
#endif
#include "thread-utils.h"
#include "userdiff.h"
struct repository;
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
};
enum grep_color {
GREP_COLOR_CONTEXT,
GREP_COLOR_FILENAME,
GREP_COLOR_FUNCTION,
GREP_COLOR_LINENO,
GREP_COLOR_COLUMNNO,
GREP_COLOR_MATCH_CONTEXT,
GREP_COLOR_MATCH_SELECTED,
GREP_COLOR_SELECTED,
GREP_COLOR_SEP,
NR_GREP_COLORS
};
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;
pcre2_code *pcre2_pattern;
pcre2_match_data *pcre2_match_data;
pcre2_compile_context *pcre2_compile_context;
uint32_t pcre2_jit_on;
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;
struct repository *repo;
const char *prefix;
int prefix_length;
regex_t regexp;
int linenum;
int columnnum;
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 pcre2;
int relative;
int pathname;
int null_following_name;
int only_matching;
int color;
int max_depth;
int funcname;
int funcbody;
int extended_regexp_option;
int pattern_type_option;
int ignore_locale;
char colors[NR_GREP_COLORS][COLOR_MAXLEN];
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;
};
void init_grep_defaults(struct repository *);
int grep_config(const char *var, const char *value, void *);
void grep_init(struct grep_opt *, struct repository *repo, const char *prefix);
void grep_commit_pattern_type(enum grep_pattern_type, struct grep_opt *opt);
void append_grep_pat(struct grep_opt *opt, const char *pat, size_t patlen, const char *origin, int no, enum grep_pat_token t);
void append_grep_pattern(struct grep_opt *opt, const char *pat, const char *origin, int no, enum grep_pat_token t);
void append_header_grep_pattern(struct grep_opt *, enum grep_header_field, const char *);
void compile_grep_patterns(struct grep_opt *opt);
void free_grep_patterns(struct grep_opt *opt);
int grep_buffer(struct grep_opt *opt, char *buf, unsigned long size);
struct grep_source {
char *name;
enum grep_source_type {
GREP_SOURCE_OID,
GREP_SOURCE_FILE,
GREP_SOURCE_BUF,
} 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,
struct index_state *istate);
int grep_source(struct grep_opt *opt, struct grep_source *gs);
struct grep_opt *grep_opt_dup(const struct grep_opt *opt);
int grep_threads_ok(const struct grep_opt *opt);
/*
* 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);
}
#endif