summaryrefslogtreecommitdiff
path: root/sha1_file.c
diff options
context:
space:
mode:
Diffstat (limited to 'sha1_file.c')
-rw-r--r--sha1_file.c254
1 files changed, 144 insertions, 110 deletions
diff --git a/sha1_file.c b/sha1_file.c
index 77dbb56946..6f18c22ab1 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -36,9 +36,6 @@ static inline uintmax_t sz_fmt(size_t s) { return s; }
const unsigned char null_sha1[20];
-static const char *no_log_pack_access = "no_log_pack_access";
-static const char *log_pack_access;
-
/*
* This is meant to hold a *small* number of objects that you would
* want read_sha1_file() to be able to return, but yet you do not want
@@ -60,6 +57,12 @@ static struct cached_object empty_tree = {
0
};
+/*
+ * A pointer to the last packed_git in which an object was found.
+ * When an object is sought, we look in this packfile first, because
+ * objects that are looked up at similar times are often in the same
+ * packfile as one another.
+ */
static struct packed_git *last_found_pack;
static struct cached_object *find_cached_object(const unsigned char *sha1)
@@ -178,17 +181,7 @@ static void fill_sha1_path(char *pathbuf, const unsigned char *sha1)
}
}
-/*
- * NOTE! This returns a statically allocated buffer, so you have to be
- * careful about using it. Do an "xstrdup()" if you need to save the
- * filename.
- *
- * Also note that this returns the location for creating. Reading
- * SHA1 file can happen from any alternate directory listed in the
- * DB_ENVIRONMENT environment variable if it is not found in
- * the primary object database.
- */
-char *sha1_file_name(const unsigned char *sha1)
+const char *sha1_file_name(const unsigned char *sha1)
{
static char buf[PATH_MAX];
const char *objdir;
@@ -208,6 +201,11 @@ char *sha1_file_name(const unsigned char *sha1)
return buf;
}
+/*
+ * Return the name of the pack or index file with the specified sha1
+ * in its filename. *base and *name are scratch space that must be
+ * provided by the caller. which should be "pack" or "idx".
+ */
static char *sha1_get_pack_name(const unsigned char *sha1,
char **name, char **base, const char *which)
{
@@ -252,8 +250,6 @@ char *sha1_pack_index_name(const unsigned char *sha1)
struct alternate_object_database *alt_odb_list;
static struct alternate_object_database **alt_odb_tail;
-static int git_open_noatime(const char *name);
-
/*
* Prepare alternate object database registry.
*
@@ -269,9 +265,9 @@ static int git_open_noatime(const char *name);
* SHA1, an extra slash for the first level indirection, and the
* terminating NUL.
*/
-static int link_alt_odb_entry(const char *entry, const char *relative_base, int depth)
+static int link_alt_odb_entry(const char *entry, const char *relative_base,
+ int depth, const char *normalized_objdir)
{
- const char *objdir = get_object_directory();
struct alternate_object_database *ent;
struct alternate_object_database *alt;
int pfxlen, entlen;
@@ -316,12 +312,13 @@ static int link_alt_odb_entry(const char *entry, const char *relative_base, int
* thing twice, or object directory itself.
*/
for (alt = alt_odb_list; alt; alt = alt->next) {
- if (!memcmp(ent->base, alt->base, pfxlen)) {
+ if (pfxlen == alt->name - alt->base - 1 &&
+ !memcmp(ent->base, alt->base, pfxlen)) {
free(ent);
return -1;
}
}
- if (!strcmp(ent->base, objdir)) {
+ if (!strcmp_icase(ent->base, normalized_objdir)) {
free(ent);
return -1;
}
@@ -345,6 +342,7 @@ static void link_alt_odb_entries(const char *alt, int len, int sep,
struct string_list entries = STRING_LIST_INIT_NODUP;
char *alt_copy;
int i;
+ struct strbuf objdirbuf = STRBUF_INIT;
if (depth > 5) {
error("%s: ignoring alternate object stores, nesting too deep.",
@@ -352,6 +350,9 @@ static void link_alt_odb_entries(const char *alt, int len, int sep,
return;
}
+ strbuf_add_absolute_path(&objdirbuf, get_object_directory());
+ normalize_path_copy(objdirbuf.buf, objdirbuf.buf);
+
alt_copy = xmemdupz(alt, len);
string_list_split_in_place(&entries, alt_copy, sep, -1);
for (i = 0; i < entries.nr; i++) {
@@ -362,11 +363,12 @@ static void link_alt_odb_entries(const char *alt, int len, int sep,
error("%s: ignoring relative alternate object store %s",
relative_base, entry);
} else {
- link_alt_odb_entry(entry, relative_base, depth);
+ link_alt_odb_entry(entry, relative_base, depth, objdirbuf.buf);
}
}
string_list_clear(&entries, 0);
free(alt_copy);
+ strbuf_release(&objdirbuf);
}
void read_info_alternates(const char * relative_base, int depth)
@@ -438,8 +440,7 @@ void prepare_alt_odb(void)
static int has_loose_object_local(const unsigned char *sha1)
{
- char *name = sha1_file_name(sha1);
- return !access(name, F_OK);
+ return !access(sha1_file_name(sha1), F_OK);
}
int has_loose_object_nonlocal(const unsigned char *sha1)
@@ -491,7 +492,12 @@ void pack_report(void)
sz_fmt(pack_mapped), sz_fmt(peak_pack_mapped));
}
-static int check_packed_git_idx(const char *path, struct packed_git *p)
+/*
+ * Open and mmap the index file at path, perform a couple of
+ * consistency checks, then record its information to p. Return 0 on
+ * success.
+ */
+static int check_packed_git_idx(const char *path, struct packed_git *p)
{
void *idx_map;
struct pack_idx_header *hdr;
@@ -657,10 +663,26 @@ void release_pack_memory(size_t need)
; /* nothing */
}
+static void mmap_limit_check(size_t length)
+{
+ static size_t limit = 0;
+ if (!limit) {
+ limit = git_env_ulong("GIT_MMAP_LIMIT", 0);
+ if (!limit)
+ limit = SIZE_MAX;
+ }
+ if (length > limit)
+ die("attempting to mmap %"PRIuMAX" over limit %"PRIuMAX,
+ (uintmax_t)length, (uintmax_t)limit);
+}
+
void *xmmap(void *start, size_t length,
int prot, int flags, int fd, off_t offset)
{
- void *ret = mmap(start, length, prot, flags, fd, offset);
+ void *ret;
+
+ mmap_limit_check(length);
+ ret = mmap(start, length, prot, flags, fd, offset);
if (ret == MAP_FAILED) {
if (!length)
return NULL;
@@ -1174,48 +1196,42 @@ static void report_pack_garbage(struct string_list *list)
static void prepare_packed_git_one(char *objdir, int local)
{
- /* Ensure that this buffer is large enough so that we can
- append "/pack/" without clobbering the stack even if
- strlen(objdir) were PATH_MAX. */
- char path[PATH_MAX + 1 + 4 + 1 + 1];
- int len;
+ struct strbuf path = STRBUF_INIT;
+ size_t dirnamelen;
DIR *dir;
struct dirent *de;
struct string_list garbage = STRING_LIST_INIT_DUP;
- sprintf(path, "%s/pack", objdir);
- len = strlen(path);
- dir = opendir(path);
+ strbuf_addstr(&path, objdir);
+ strbuf_addstr(&path, "/pack");
+ dir = opendir(path.buf);
if (!dir) {
if (errno != ENOENT)
error("unable to open object pack directory: %s: %s",
- path, strerror(errno));
+ path.buf, strerror(errno));
+ strbuf_release(&path);
return;
}
- path[len++] = '/';
+ strbuf_addch(&path, '/');
+ dirnamelen = path.len;
while ((de = readdir(dir)) != NULL) {
- int namelen = strlen(de->d_name);
struct packed_git *p;
-
- if (len + namelen + 1 > sizeof(path)) {
- if (report_garbage) {
- struct strbuf sb = STRBUF_INIT;
- strbuf_addf(&sb, "%.*s/%s", len - 1, path, de->d_name);
- report_garbage("path too long", sb.buf);
- strbuf_release(&sb);
- }
- continue;
- }
+ size_t base_len;
if (is_dot_or_dotdot(de->d_name))
continue;
- strcpy(path + len, de->d_name);
+ strbuf_setlen(&path, dirnamelen);
+ strbuf_addstr(&path, de->d_name);
- if (has_extension(de->d_name, ".idx")) {
+ base_len = path.len;
+ if (strip_suffix_mem(path.buf, &base_len, ".idx")) {
/* Don't reopen a pack we already have. */
for (p = packed_git; p; p = p->next) {
- if (!memcmp(path, p->pack_name, len + namelen - 4))
+ size_t len;
+ if (strip_suffix(p->pack_name, ".pack", &len) &&
+ len == base_len &&
+ !memcmp(p->pack_name, path.buf, len))
break;
}
if (p == NULL &&
@@ -1223,23 +1239,25 @@ static void prepare_packed_git_one(char *objdir, int local)
* See if it really is a valid .idx file with
* corresponding .pack file that we can map.
*/
- (p = add_packed_git(path, len + namelen, local)) != NULL)
+ (p = add_packed_git(path.buf, path.len, local)) != NULL)
install_packed_git(p);
}
if (!report_garbage)
continue;
- if (has_extension(de->d_name, ".idx") ||
- has_extension(de->d_name, ".pack") ||
- has_extension(de->d_name, ".keep"))
- string_list_append(&garbage, path);
+ if (ends_with(de->d_name, ".idx") ||
+ ends_with(de->d_name, ".pack") ||
+ ends_with(de->d_name, ".bitmap") ||
+ ends_with(de->d_name, ".keep"))
+ string_list_append(&garbage, path.buf);
else
- report_garbage("garbage found", path);
+ report_garbage("garbage found", path.buf);
}
closedir(dir);
report_pack_garbage(&garbage);
string_list_clear(&garbage, 0);
+ strbuf_release(&path);
}
static int sort_pack(const void *a_, const void *b_)
@@ -1316,7 +1334,6 @@ void prepare_packed_git(void)
void reprepare_packed_git(void)
{
- discard_revindex();
prepare_packed_git_run_once = 0;
prepare_packed_git();
}
@@ -1393,7 +1410,7 @@ int check_sha1_signature(const unsigned char *sha1, void *map,
return hashcmp(sha1, real_sha1) ? -1 : 0;
}
-static int git_open_noatime(const char *name)
+int git_open_noatime(const char *name)
{
static int sha1_file_open_flag = O_NOATIME;
@@ -1414,17 +1431,15 @@ static int git_open_noatime(const char *name)
static int stat_sha1_file(const unsigned char *sha1, struct stat *st)
{
- char *name = sha1_file_name(sha1);
struct alternate_object_database *alt;
- if (!lstat(name, st))
+ if (!lstat(sha1_file_name(sha1), st))
return 0;
prepare_alt_odb();
errno = ENOENT;
for (alt = alt_odb_list; alt; alt = alt->next) {
- name = alt->name;
- fill_sha1_path(name, sha1);
+ fill_sha1_path(alt->name, sha1);
if (!lstat(alt->base, st))
return 0;
}
@@ -1435,22 +1450,24 @@ static int stat_sha1_file(const unsigned char *sha1, struct stat *st)
static int open_sha1_file(const unsigned char *sha1)
{
int fd;
- char *name = sha1_file_name(sha1);
struct alternate_object_database *alt;
+ int most_interesting_errno;
- fd = git_open_noatime(name);
+ fd = git_open_noatime(sha1_file_name(sha1));
if (fd >= 0)
return fd;
+ most_interesting_errno = errno;
prepare_alt_odb();
- errno = ENOENT;
for (alt = alt_odb_list; alt; alt = alt->next) {
- name = alt->name;
- fill_sha1_path(name, sha1);
+ fill_sha1_path(alt->name, sha1);
fd = git_open_noatime(alt->base);
if (fd >= 0)
return fd;
+ if (most_interesting_errno == ENOENT)
+ most_interesting_errno = errno;
}
+ errno = most_interesting_errno;
return -1;
}
@@ -1922,7 +1939,9 @@ static void *unpack_compressed_entry(struct packed_git *p,
git_zstream stream;
unsigned char *buffer, *in;
- buffer = xmallocz(size);
+ buffer = xmallocz_gently(size);
+ if (!buffer)
+ return NULL;
memset(&stream, 0, sizeof(stream));
stream.next_out = buffer;
stream.avail_out = size + 1;
@@ -2082,27 +2101,9 @@ static void *read_object(const unsigned char *sha1, enum object_type *type,
static void write_pack_access_log(struct packed_git *p, off_t obj_offset)
{
- static FILE *log_file;
-
- if (!log_pack_access)
- log_pack_access = getenv("GIT_TRACE_PACK_ACCESS");
- if (!log_pack_access)
- log_pack_access = no_log_pack_access;
- if (log_pack_access == no_log_pack_access)
- return;
-
- if (!log_file) {
- log_file = fopen(log_pack_access, "w");
- if (!log_file) {
- error("cannot open pack access log '%s' for writing: %s",
- log_pack_access, strerror(errno));
- log_pack_access = no_log_pack_access;
- return;
- }
- }
- fprintf(log_file, "%s %"PRIuMAX"\n",
- p->pack_name, (uintmax_t)obj_offset);
- fflush(log_file);
+ static struct trace_key pack_access = TRACE_KEY_INIT(PACK_ACCESS);
+ trace_printf_key(&pack_access, "%s %"PRIuMAX"\n",
+ p->pack_name, (uintmax_t)obj_offset);
}
int do_check_packed_object_crc;
@@ -2127,8 +2128,7 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset,
int delta_stack_nr = 0, delta_stack_alloc = UNPACK_ENTRY_STACK_PREALLOC;
int base_from_cache = 0;
- if (log_pack_access != no_log_pack_access)
- write_pack_access_log(p, obj_offset);
+ write_pack_access_log(p, obj_offset);
/* PHASE 1: drill down to the innermost base object */
for (;;) {
@@ -2289,6 +2289,10 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset,
*final_size = size;
unuse_pack(&w_curs);
+
+ if (delta_stack != small_delta_stack)
+ free(delta_stack);
+
return data;
}
@@ -2448,6 +2452,10 @@ static int fill_pack_entry(const unsigned char *sha1,
return 1;
}
+/*
+ * Iff a pack file contains the object named by sha1, return true and
+ * store its location to e.
+ */
static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
{
struct packed_git *p;
@@ -2460,11 +2468,13 @@ static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
return 1;
for (p = packed_git; p; p = p->next) {
- if (p == last_found_pack || !fill_pack_entry(sha1, e, p))
- continue;
+ if (p == last_found_pack)
+ continue; /* we already checked this one */
- last_found_pack = p;
- return 1;
+ if (fill_pack_entry(sha1, e, p)) {
+ last_found_pack = p;
+ return 1;
+ }
}
return 0;
}
@@ -2626,12 +2636,7 @@ int pretend_sha1_file(void *buf, unsigned long len, enum object_type type,
hash_sha1_file(buf, len, typename(type), sha1);
if (has_sha1_file(sha1) || find_cached_object(sha1))
return 0;
- if (cached_object_alloc <= cached_object_nr) {
- cached_object_alloc = alloc_nr(cached_object_alloc);
- cached_objects = xrealloc(cached_objects,
- sizeof(*cached_objects) *
- cached_object_alloc);
- }
+ ALLOC_GROW(cached_objects, cached_object_nr + 1, cached_object_alloc);
co = &cached_objects[cached_object_nr++];
co->size = len;
co->type = type;
@@ -2679,7 +2684,6 @@ void *read_sha1_file_extended(const unsigned char *sha1,
unsigned flag)
{
void *data;
- char *path;
const struct packed_git *p;
const unsigned char *repl = lookup_replace_object_extended(sha1, flag);
@@ -2697,7 +2701,8 @@ void *read_sha1_file_extended(const unsigned char *sha1,
sha1_to_hex(repl), sha1_to_hex(sha1));
if (has_loose_object(repl)) {
- path = sha1_file_name(sha1);
+ const char *path = sha1_file_name(sha1);
+
die("loose object %s (stored in %s) is corrupt",
sha1_to_hex(repl), path);
}
@@ -2895,10 +2900,9 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
git_zstream stream;
git_SHA_CTX c;
unsigned char parano_sha1[20];
- char *filename;
static char tmp_file[PATH_MAX];
+ const char *filename = sha1_file_name(sha1);
- filename = sha1_file_name(sha1);
fd = create_tmpfile(tmp_file, sizeof(tmp_file), filename);
if (fd < 0) {
if (errno == EACCES)
@@ -3088,6 +3092,29 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
return ret;
}
+static int index_stream_convert_blob(unsigned char *sha1, int fd,
+ const char *path, unsigned flags)
+{
+ int ret;
+ const int write_object = flags & HASH_WRITE_OBJECT;
+ struct strbuf sbuf = STRBUF_INIT;
+
+ assert(path);
+ assert(would_convert_to_git_filter_fd(path));
+
+ convert_to_git_filter_fd(path, fd, &sbuf,
+ write_object ? safe_crlf : SAFE_CRLF_FALSE);
+
+ if (write_object)
+ ret = write_sha1_file(sbuf.buf, sbuf.len, typename(OBJ_BLOB),
+ sha1);
+ else
+ ret = hash_sha1_file(sbuf.buf, sbuf.len, typename(OBJ_BLOB),
+ sha1);
+ strbuf_release(&sbuf);
+ return ret;
+}
+
static int index_pipe(unsigned char *sha1, int fd, enum object_type type,
const char *path, unsigned flags)
{
@@ -3153,15 +3180,22 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st,
enum object_type type, const char *path, unsigned flags)
{
int ret;
- size_t size = xsize_t(st->st_size);
- if (!S_ISREG(st->st_mode))
+ /*
+ * Call xsize_t() only when needed to avoid potentially unnecessary
+ * die() for large files.
+ */
+ if (type == OBJ_BLOB && path && would_convert_to_git_filter_fd(path))
+ ret = index_stream_convert_blob(sha1, fd, path, flags);
+ else if (!S_ISREG(st->st_mode))
ret = index_pipe(sha1, fd, type, path, flags);
- else if (size <= big_file_threshold || type != OBJ_BLOB ||
- (path && would_convert_to_git(path, NULL, 0, 0)))
- ret = index_core(sha1, fd, size, type, path, flags);
+ else if (st->st_size <= big_file_threshold || type != OBJ_BLOB ||
+ (path && would_convert_to_git(path)))
+ ret = index_core(sha1, fd, xsize_t(st->st_size), type, path,
+ flags);
else
- ret = index_stream(sha1, fd, size, type, path, flags);
+ ret = index_stream(sha1, fd, xsize_t(st->st_size), type, path,
+ flags);
close(fd);
return ret;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-11 15:01:46 +0000