summaryrefslogtreecommitdiff
path: root/sha1_file.c
diff options
context:
space:
mode:
Diffstat (limited to 'sha1_file.c')
-rw-r--r--sha1_file.c1422
1 files changed, 919 insertions, 503 deletions
diff --git a/sha1_file.c b/sha1_file.c
index 191f814e09..f615fc7206 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -11,11 +11,14 @@
#include "pack.h"
#include "blob.h"
#include "commit.h"
+#include "run-command.h"
#include "tag.h"
#include "tree.h"
+#include "tree-walk.h"
#include "refs.h"
#include "pack-revindex.h"
#include "sha1-lookup.h"
+#include "bulk-checkin.h"
#ifndef O_NOATIME
#if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
@@ -25,77 +28,91 @@
#endif
#endif
-#ifdef NO_C99_FORMAT
-#define SZ_FMT "lu"
-static unsigned long sz_fmt(size_t s) { return (unsigned long)s; }
-#else
-#define SZ_FMT "zu"
-static size_t sz_fmt(size_t s) { return s; }
-#endif
+#define SZ_FMT PRIuMAX
+static inline uintmax_t sz_fmt(size_t s) { return s; }
const unsigned char null_sha1[20];
-const signed char hexval_table[256] = {
- -1, -1, -1, -1, -1, -1, -1, -1, /* 00-07 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 08-0f */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 10-17 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 18-1f */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 20-27 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 28-2f */
- 0, 1, 2, 3, 4, 5, 6, 7, /* 30-37 */
- 8, 9, -1, -1, -1, -1, -1, -1, /* 38-3f */
- -1, 10, 11, 12, 13, 14, 15, -1, /* 40-47 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 48-4f */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 50-57 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 58-5f */
- -1, 10, 11, 12, 13, 14, 15, -1, /* 60-67 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 68-67 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 70-77 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 78-7f */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 80-87 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 88-8f */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 90-97 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* 98-9f */
- -1, -1, -1, -1, -1, -1, -1, -1, /* a0-a7 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* a8-af */
- -1, -1, -1, -1, -1, -1, -1, -1, /* b0-b7 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* b8-bf */
- -1, -1, -1, -1, -1, -1, -1, -1, /* c0-c7 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* c8-cf */
- -1, -1, -1, -1, -1, -1, -1, -1, /* d0-d7 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* d8-df */
- -1, -1, -1, -1, -1, -1, -1, -1, /* e0-e7 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* e8-ef */
- -1, -1, -1, -1, -1, -1, -1, -1, /* f0-f7 */
- -1, -1, -1, -1, -1, -1, -1, -1, /* f8-ff */
+/*
+ * 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
+ * to write them into the object store (e.g. a browse-only
+ * application).
+ */
+static struct cached_object {
+ unsigned char sha1[20];
+ enum object_type type;
+ void *buf;
+ unsigned long size;
+} *cached_objects;
+static int cached_object_nr, cached_object_alloc;
+
+static struct cached_object empty_tree = {
+ EMPTY_TREE_SHA1_BIN_LITERAL,
+ OBJ_TREE,
+ "",
+ 0
};
-int get_sha1_hex(const char *hex, unsigned char *sha1)
+static struct packed_git *last_found_pack;
+
+static struct cached_object *find_cached_object(const unsigned char *sha1)
{
int i;
- for (i = 0; i < 20; i++) {
- unsigned int val = (hexval(hex[0]) << 4) | hexval(hex[1]);
- if (val & ~0xff)
+ struct cached_object *co = cached_objects;
+
+ for (i = 0; i < cached_object_nr; i++, co++) {
+ if (!hashcmp(co->sha1, sha1))
+ return co;
+ }
+ if (!hashcmp(sha1, empty_tree.sha1))
+ return &empty_tree;
+ return NULL;
+}
+
+int mkdir_in_gitdir(const char *path)
+{
+ if (mkdir(path, 0777)) {
+ int saved_errno = errno;
+ struct stat st;
+ struct strbuf sb = STRBUF_INIT;
+
+ if (errno != EEXIST)
+ return -1;
+ /*
+ * Are we looking at a path in a symlinked worktree
+ * whose original repository does not yet have it?
+ * e.g. .git/rr-cache pointing at its original
+ * repository in which the user hasn't performed any
+ * conflict resolution yet?
+ */
+ if (lstat(path, &st) || !S_ISLNK(st.st_mode) ||
+ strbuf_readlink(&sb, path, st.st_size) ||
+ !is_absolute_path(sb.buf) ||
+ mkdir(sb.buf, 0777)) {
+ strbuf_release(&sb);
+ errno = saved_errno;
return -1;
- *sha1++ = val;
- hex += 2;
+ }
+ strbuf_release(&sb);
}
- return 0;
+ return adjust_shared_perm(path);
}
int safe_create_leading_directories(char *path)
{
- char *pos = path;
+ char *pos = path + offset_1st_component(path);
struct stat st;
- if (is_absolute_path(path))
- pos++;
-
while (pos) {
pos = strchr(pos, '/');
if (!pos)
break;
- *pos = 0;
+ while (*++pos == '/')
+ ;
+ if (!*pos)
+ break;
+ *--pos = '\0';
if (!stat(path, &st)) {
/* path exists */
if (!S_ISDIR(st.st_mode)) {
@@ -116,22 +133,13 @@ int safe_create_leading_directories(char *path)
return 0;
}
-char *sha1_to_hex(const unsigned char *sha1)
+int safe_create_leading_directories_const(const char *path)
{
- static int bufno;
- static char hexbuffer[4][50];
- static const char hex[] = "0123456789abcdef";
- char *buffer = hexbuffer[3 & ++bufno], *buf = buffer;
- int i;
-
- for (i = 0; i < 20; i++) {
- unsigned int val = *sha1++;
- *buf++ = hex[val >> 4];
- *buf++ = hex[val & 0xf];
- }
- *buf = '\0';
-
- return buffer;
+ /* path points to cache entries, so xstrdup before messing with it */
+ char *buf = xstrdup(path);
+ int result = safe_create_leading_directories(buf);
+ free(buf);
+ return result;
}
static void fill_sha1_path(char *pathbuf, const unsigned char *sha1)
@@ -158,20 +166,22 @@ static void fill_sha1_path(char *pathbuf, const unsigned char *sha1)
*/
char *sha1_file_name(const unsigned char *sha1)
{
- static char *name, *base;
+ static char buf[PATH_MAX];
+ const char *objdir;
+ int len;
- if (!base) {
- const char *sha1_file_directory = get_object_directory();
- int len = strlen(sha1_file_directory);
- base = xmalloc(len + 60);
- memcpy(base, sha1_file_directory, len);
- memset(base+len, 0, 60);
- base[len] = '/';
- base[len+3] = '/';
- name = base + len + 1;
- }
- fill_sha1_path(name, sha1);
- return base;
+ objdir = get_object_directory();
+ len = strlen(objdir);
+
+ /* '/' + sha1(2) + '/' + sha1(38) + '\0' */
+ if (len + 43 > PATH_MAX)
+ die("insanely long object directory %s", objdir);
+ memcpy(buf, objdir, len);
+ buf[len] = '/';
+ buf[len+3] = '/';
+ buf[len+42] = '\0';
+ fill_sha1_path(buf + len + 1, sha1);
+ return buf;
}
static char *sha1_get_pack_name(const unsigned char *sha1,
@@ -218,7 +228,7 @@ 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 void read_info_alternates(const char * alternates, int depth);
+static int git_open_noatime(const char *name);
/*
* Prepare alternate object database registry.
@@ -237,38 +247,40 @@ static void read_info_alternates(const char * alternates, int depth);
*/
static int link_alt_odb_entry(const char * entry, int len, const char * relative_base, int depth)
{
- struct stat st;
const char *objdir = get_object_directory();
struct alternate_object_database *ent;
struct alternate_object_database *alt;
- /* 43 = 40-byte + 2 '/' + terminating NUL */
- int pfxlen = len;
- int entlen = pfxlen + 43;
- int base_len = -1;
+ int pfxlen, entlen;
+ struct strbuf pathbuf = STRBUF_INIT;
if (!is_absolute_path(entry) && relative_base) {
- /* Relative alt-odb */
- if (base_len < 0)
- base_len = strlen(relative_base) + 1;
- entlen += base_len;
- pfxlen += base_len;
+ strbuf_addstr(&pathbuf, real_path(relative_base));
+ strbuf_addch(&pathbuf, '/');
}
- ent = xmalloc(sizeof(*ent) + entlen);
+ strbuf_add(&pathbuf, entry, len);
- if (!is_absolute_path(entry) && relative_base) {
- memcpy(ent->base, relative_base, base_len - 1);
- ent->base[base_len - 1] = '/';
- memcpy(ent->base + base_len, entry, len);
- }
- else
- memcpy(ent->base, entry, pfxlen);
+ normalize_path_copy(pathbuf.buf, pathbuf.buf);
+
+ pfxlen = strlen(pathbuf.buf);
+
+ /*
+ * The trailing slash after the directory name is given by
+ * this function at the end. Remove duplicates.
+ */
+ while (pfxlen && pathbuf.buf[pfxlen-1] == '/')
+ pfxlen -= 1;
+
+ entlen = pfxlen + 43; /* '/' + 2 hex + '/' + 38 hex + NUL */
+ ent = xmalloc(sizeof(*ent) + entlen);
+ memcpy(ent->base, pathbuf.buf, pfxlen);
+ strbuf_release(&pathbuf);
ent->name = ent->base + pfxlen + 1;
ent->base[pfxlen + 3] = '/';
ent->base[pfxlen] = ent->base[entlen-1] = 0;
/* Detect cases where alternate disappeared */
- if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) {
+ if (!is_directory(ent->base)) {
error("object directory %s does not exist; "
"check .git/objects/info/alternates.",
ent->base);
@@ -340,7 +352,7 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
}
}
-static void read_info_alternates(const char * relative_base, int depth)
+void read_info_alternates(const char * relative_base, int depth)
{
char *map;
size_t mapsz;
@@ -353,7 +365,7 @@ static void read_info_alternates(const char * relative_base, int depth)
int fd;
sprintf(path, "%s/%s", relative_base, alt_file_name);
- fd = open(path, O_RDONLY);
+ fd = git_open_noatime(path);
if (fd < 0)
return;
if (fstat(fd, &st) || (st.st_size == 0)) {
@@ -372,8 +384,8 @@ static void read_info_alternates(const char * relative_base, int depth)
void add_to_alternates_file(const char *reference)
{
struct lock_file *lock = xcalloc(1, sizeof(struct lock_file));
- int fd = hold_lock_file_for_append(lock, git_path("objects/info/alternates"), 1);
- char *alt = mkpath("%s/objects\n", reference);
+ int fd = hold_lock_file_for_append(lock, git_path("objects/info/alternates"), LOCK_DIE_ON_ERROR);
+ char *alt = mkpath("%s\n", reference);
write_or_die(fd, alt, strlen(alt));
if (commit_lock_file(lock))
die("could not close alternates file");
@@ -381,6 +393,16 @@ void add_to_alternates_file(const char *reference)
link_alt_odb_entries(alt, alt + strlen(alt), '\n', NULL, 0);
}
+void foreach_alt_odb(alt_odb_fn fn, void *cb)
+{
+ struct alternate_object_database *ent;
+
+ prepare_alt_odb();
+ for (ent = alt_odb_list; ent; ent = ent->next)
+ if (fn(ent, cb))
+ return;
+}
+
void prepare_alt_odb(void)
{
const char *alt;
@@ -392,32 +414,41 @@ void prepare_alt_odb(void)
if (!alt) alt = "";
alt_odb_tail = &alt_odb_list;
- link_alt_odb_entries(alt, alt + strlen(alt), ':', NULL, 0);
+ link_alt_odb_entries(alt, alt + strlen(alt), PATH_SEP, NULL, 0);
read_info_alternates(get_object_directory(), 0);
}
-static int has_loose_object(const unsigned char *sha1)
+static int has_loose_object_local(const unsigned char *sha1)
{
char *name = sha1_file_name(sha1);
- struct alternate_object_database *alt;
+ return !access(name, F_OK);
+}
- if (!access(name, F_OK))
- return 1;
+int has_loose_object_nonlocal(const unsigned char *sha1)
+{
+ struct alternate_object_database *alt;
prepare_alt_odb();
for (alt = alt_odb_list; alt; alt = alt->next) {
- name = alt->name;
- fill_sha1_path(name, sha1);
+ fill_sha1_path(alt->name, sha1);
if (!access(alt->base, F_OK))
return 1;
}
return 0;
}
+static int has_loose_object(const unsigned char *sha1)
+{
+ return has_loose_object_local(sha1) ||
+ has_loose_object_nonlocal(sha1);
+}
+
static unsigned int pack_used_ctr;
static unsigned int pack_mmap_calls;
static unsigned int peak_pack_open_windows;
static unsigned int pack_open_windows;
+static unsigned int pack_open_fds;
+static unsigned int pack_max_fds;
static size_t peak_pack_mapped;
static size_t pack_mapped;
struct packed_git *packed_git;
@@ -449,7 +480,7 @@ static int check_packed_git_idx(const char *path, struct packed_git *p)
struct pack_idx_header *hdr;
size_t idx_size;
uint32_t version, nr, i, *index;
- int fd = open(path, O_RDONLY);
+ int fd = git_open_noatime(path);
struct stat st;
if (fd < 0)
@@ -471,7 +502,7 @@ static int check_packed_git_idx(const char *path, struct packed_git *p)
version = ntohl(hdr->idx_version);
if (version < 2 || version > 2) {
munmap(idx_map, idx_size);
- return error("index file %s is version %d"
+ return error("index file %s is version %"PRIu32
" and is not supported by this binary"
" (try upgrading GIT to a newer version)",
path, version);
@@ -595,8 +626,10 @@ static int unuse_one_window(struct packed_git *current, int keep_fd)
lru_l->next = lru_w->next;
else {
lru_p->windows = lru_w->next;
- if (!lru_p->windows && lru_p->pack_fd != keep_fd) {
+ if (!lru_p->windows && lru_p->pack_fd != -1
+ && lru_p->pack_fd != keep_fd) {
close(lru_p->pack_fd);
+ pack_open_fds--;
lru_p->pack_fd = -1;
}
}
@@ -614,6 +647,21 @@ void release_pack_memory(size_t need, int fd)
; /* nothing */
}
+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);
+ if (ret == MAP_FAILED) {
+ if (!length)
+ return NULL;
+ release_pack_memory(length, fd);
+ ret = mmap(start, length, prot, flags, fd, offset);
+ if (ret == MAP_FAILED)
+ die_errno("Out of memory? mmap failed");
+ }
+ return ret;
+}
+
void close_pack_windows(struct packed_git *p)
{
while (p->windows) {
@@ -639,6 +687,49 @@ void unuse_pack(struct pack_window **w_cursor)
}
}
+void close_pack_index(struct packed_git *p)
+{
+ if (p->index_data) {
+ munmap((void *)p->index_data, p->index_size);
+ p->index_data = NULL;
+ }
+}
+
+/*
+ * This is used by git-repack in case a newly created pack happens to
+ * contain the same set of objects as an existing one. In that case
+ * the resulting file might be different even if its name would be the
+ * same. It is best to close any reference to the old pack before it is
+ * replaced on disk. Of course no index pointers nor windows for given pack
+ * must subsist at this point. If ever objects from this pack are requested
+ * again, the new version of the pack will be reinitialized through
+ * reprepare_packed_git().
+ */
+void free_pack_by_name(const char *pack_name)
+{
+ struct packed_git *p, **pp = &packed_git;
+
+ while (*pp) {
+ p = *pp;
+ if (strcmp(pack_name, p->pack_name) == 0) {
+ clear_delta_base_cache();
+ close_pack_windows(p);
+ if (p->pack_fd != -1) {
+ close(p->pack_fd);
+ pack_open_fds--;
+ }
+ close_pack_index(p);
+ free(p->bad_object_sha1);
+ *pp = p->next;
+ if (last_found_pack == p)
+ last_found_pack = NULL;
+ free(p);
+ return;
+ }
+ pp = &p->next;
+ }
+}
+
/*
* Do not call this directly as this leaks p->pack_fd on error return;
* call open_packed_git() instead.
@@ -654,9 +745,29 @@ static int open_packed_git_1(struct packed_git *p)
if (!p->index_data && open_pack_index(p))
return error("packfile %s index unavailable", p->pack_name);
- p->pack_fd = open(p->pack_name, O_RDONLY);
+ if (!pack_max_fds) {
+ struct rlimit lim;
+ unsigned int max_fds;
+
+ if (getrlimit(RLIMIT_NOFILE, &lim))
+ die_errno("cannot get RLIMIT_NOFILE");
+
+ max_fds = lim.rlim_cur;
+
+ /* Save 3 for stdin/stdout/stderr, 22 for work */
+ if (25 < max_fds)
+ pack_max_fds = max_fds - 25;
+ else
+ pack_max_fds = 1;
+ }
+
+ while (pack_max_fds <= pack_open_fds && unuse_one_window(NULL, -1))
+ ; /* nothing */
+
+ p->pack_fd = git_open_noatime(p->pack_name);
if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
return -1;
+ pack_open_fds++;
/* If we created the struct before we had the pack we lack size. */
if (!p->pack_size) {
@@ -682,14 +793,14 @@ static int open_packed_git_1(struct packed_git *p)
if (hdr.hdr_signature != htonl(PACK_SIGNATURE))
return error("file %s is not a GIT packfile", p->pack_name);
if (!pack_version_ok(hdr.hdr_version))
- return error("packfile %s is version %u and not supported"
- " (try upgrading GIT to a newer version)",
+ return error("packfile %s is version %"PRIu32" and not"
+ " supported (try upgrading GIT to a newer version)",
p->pack_name, ntohl(hdr.hdr_version));
/* Verify the pack matches its index. */
if (p->num_objects != ntohl(hdr.hdr_entries))
- return error("packfile %s claims to have %u objects"
- " while index indicates %u objects",
+ return error("packfile %s claims to have %"PRIu32" objects"
+ " while index indicates %"PRIu32" objects",
p->pack_name, ntohl(hdr.hdr_entries),
p->num_objects);
if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1)
@@ -708,6 +819,7 @@ static int open_packed_git(struct packed_git *p)
return 0;
if (p->pack_fd != -1) {
close(p->pack_fd);
+ pack_open_fds--;
p->pack_fd = -1;
}
return -1;
@@ -726,21 +838,20 @@ static int in_window(struct pack_window *win, off_t offset)
&& (offset + 20) <= (win_off + win->len);
}
-unsigned char* use_pack(struct packed_git *p,
+unsigned char *use_pack(struct packed_git *p,
struct pack_window **w_cursor,
off_t offset,
- unsigned int *left)
+ unsigned long *left)
{
struct pack_window *win = *w_cursor;
- if (p->pack_fd == -1 && open_packed_git(p))
- die("packfile %s cannot be accessed", p->pack_name);
-
- /* Since packfiles end in a hash of their content and its
+ /* Since packfiles end in a hash of their content and it's
* pointless to ask for an offset into the middle of that
* hash, and the in_window function above wouldn't match
* don't allow an offset too close to the end of the file.
*/
+ if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p))
+ die("packfile %s cannot be accessed", p->pack_name);
if (offset > (p->pack_size - 20))
die("offset beyond end of packfile (truncated pack?)");
@@ -754,6 +865,10 @@ unsigned char* use_pack(struct packed_git *p,
if (!win) {
size_t window_align = packed_git_window_size / 2;
off_t len;
+
+ if (p->pack_fd == -1 && open_packed_git(p))
+ die("packfile %s cannot be accessed", p->pack_name);
+
win = xcalloc(1, sizeof(*win));
win->offset = (offset / window_align) * window_align;
len = p->pack_size - win->offset;
@@ -771,6 +886,12 @@ unsigned char* use_pack(struct packed_git *p,
die("packfile %s cannot be mapped: %s",
p->pack_name,
strerror(errno));
+ if (!win->offset && win->len == p->pack_size
+ && !p->do_not_close) {
+ close(p->pack_fd);
+ pack_open_fds--;
+ p->pack_fd = -1;
+ }
pack_mmap_calls++;
pack_open_windows++;
if (pack_mapped > peak_pack_mapped)
@@ -792,19 +913,45 @@ unsigned char* use_pack(struct packed_git *p,
return win->base + offset;
}
+static struct packed_git *alloc_packed_git(int extra)
+{
+ struct packed_git *p = xmalloc(sizeof(*p) + extra);
+ memset(p, 0, sizeof(*p));
+ p->pack_fd = -1;
+ return p;
+}
+
+static void try_to_free_pack_memory(size_t size)
+{
+ release_pack_memory(size, -1);
+}
+
struct packed_git *add_packed_git(const char *path, int path_len, int local)
{
+ static int have_set_try_to_free_routine;
struct stat st;
- struct packed_git *p = xmalloc(sizeof(*p) + path_len + 2);
+ struct packed_git *p = alloc_packed_git(path_len + 2);
+
+ if (!have_set_try_to_free_routine) {
+ have_set_try_to_free_routine = 1;
+ set_try_to_free_routine(try_to_free_pack_memory);
+ }
/*
* Make sure a corresponding .pack file exists and that
* the index looks sane.
*/
path_len -= strlen(".idx");
- if (path_len < 1)
+ if (path_len < 1) {
+ free(p);
return NULL;
+ }
memcpy(p->pack_name, path, path_len);
+
+ strcpy(p->pack_name + path_len, ".keep");
+ if (!access(p->pack_name, F_OK))
+ p->pack_keep = 1;
+
strcpy(p->pack_name + path_len, ".pack");
if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) {
free(p);
@@ -814,14 +961,7 @@ struct packed_git *add_packed_git(const char *path, int path_len, int local)
/* ok, it looks sane as far as we can check without
* actually mapping the pack file.
*/
- p->index_version = 0;
- p->index_data = NULL;
- p->index_size = 0;
- p->num_objects = 0;
p->pack_size = st.st_size;
- p->next = NULL;
- p->windows = NULL;
- p->pack_fd = -1;
p->pack_local = local;
p->mtime = st.st_mtime;
if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1))
@@ -829,28 +969,26 @@ struct packed_git *add_packed_git(const char *path, int path_len, int local)
return p;
}
-struct packed_git *parse_pack_index(unsigned char *sha1)
+struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path)
{
- const char *idx_path = sha1_pack_index_name(sha1);
const char *path = sha1_pack_name(sha1);
- struct packed_git *p = xmalloc(sizeof(*p) + strlen(path) + 2);
+ struct packed_git *p = alloc_packed_git(strlen(path) + 1);
+ strcpy(p->pack_name, path);
+ hashcpy(p->sha1, sha1);
if (check_packed_git_idx(idx_path, p)) {
free(p);
return NULL;
}
- strcpy(p->pack_name, path);
- p->pack_size = 0;
- p->next = NULL;
- p->windows = NULL;
- p->pack_fd = -1;
- hashcpy(p->sha1, sha1);
return p;
}
void install_packed_git(struct packed_git *pack)
{
+ if (pack->pack_fd != -1)
+ pack_open_fds++;
+
pack->next = packed_git;
packed_git = pack;
}
@@ -978,10 +1116,35 @@ void prepare_packed_git(void)
void reprepare_packed_git(void)
{
+ discard_revindex();
prepare_packed_git_run_once = 0;
prepare_packed_git();
}
+static void mark_bad_packed_object(struct packed_git *p,
+ const unsigned char *sha1)
+{
+ unsigned i;
+ for (i = 0; i < p->num_bad_objects; i++)
+ if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
+ return;
+ p->bad_object_sha1 = xrealloc(p->bad_object_sha1, 20 * (p->num_bad_objects + 1));
+ hashcpy(p->bad_object_sha1 + 20 * p->num_bad_objects, sha1);
+ p->num_bad_objects++;
+}
+
+static const struct packed_git *has_packed_and_bad(const unsigned char *sha1)
+{
+ struct packed_git *p;
+ unsigned i;
+
+ for (p = packed_git; p; p = p->next)
+ for (i = 0; i < p->num_bad_objects; i++)
+ if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
+ return p;
+ return NULL;
+}
+
int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type)
{
unsigned char real_sha1[20];
@@ -992,15 +1155,20 @@ int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long siz
static int git_open_noatime(const char *name)
{
static int sha1_file_open_flag = O_NOATIME;
- int fd = open(name, O_RDONLY | sha1_file_open_flag);
- /* Might the failure be due to O_NOATIME? */
- if (fd < 0 && errno != ENOENT && sha1_file_open_flag) {
- fd = open(name, O_RDONLY);
+ for (;;) {
+ int fd = open(name, O_RDONLY | sha1_file_open_flag);
if (fd >= 0)
+ return fd;
+
+ /* Might the failure be due to O_NOATIME? */
+ if (errno != ENOENT && sha1_file_open_flag) {
sha1_file_open_flag = 0;
+ continue;
+ }
+
+ return -1;
}
- return fd;
}
static int open_sha1_file(const unsigned char *sha1)
@@ -1025,7 +1193,7 @@ static int open_sha1_file(const unsigned char *sha1)
return -1;
}
-static void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
+void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
{
void *map;
int fd;
@@ -1037,6 +1205,11 @@ static void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
if (!fstat(fd, &st)) {
*size = xsize_t(st.st_size);
+ if (!*size) {
+ /* mmap() is forbidden on empty files */
+ error("object file %s is empty", sha1_file_name(sha1));
+ return NULL;
+ }
map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0);
}
close(fd);
@@ -1044,27 +1217,56 @@ static void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
return map;
}
-static int legacy_loose_object(unsigned char *map)
+/*
+ * There used to be a second loose object header format which
+ * was meant to mimic the in-pack format, allowing for direct
+ * copy of the object data. This format turned up not to be
+ * really worth it and we no longer write loose objects in that
+ * format.
+ */
+static int experimental_loose_object(unsigned char *map)
{
unsigned int word;
/*
- * Is it a zlib-compressed buffer? If so, the first byte
- * must be 0x78 (15-bit window size, deflated), and the
- * first 16-bit word is evenly divisible by 31
+ * We must determine if the buffer contains the standard
+ * zlib-deflated stream or the experimental format based
+ * on the in-pack object format. Compare the header byte
+ * for each format:
+ *
+ * RFC1950 zlib w/ deflate : 0www1000 : 0 <= www <= 7
+ * Experimental pack-based : Stttssss : ttt = 1,2,3,4
+ *
+ * If bit 7 is clear and bits 0-3 equal 8, the buffer MUST be
+ * in standard loose-object format, UNLESS it is a Git-pack
+ * format object *exactly* 8 bytes in size when inflated.
+ *
+ * However, RFC1950 also specifies that the 1st 16-bit word
+ * must be divisible by 31 - this checksum tells us our buffer
+ * is in the standard format, giving a false positive only if
+ * the 1st word of the Git-pack format object happens to be
+ * divisible by 31, ie:
+ * ((byte0 * 256) + byte1) % 31 = 0
+ * => 0ttt10000www1000 % 31 = 0
+ *
+ * As it happens, this case can only arise for www=3 & ttt=1
+ * - ie, a Commit object, which would have to be 8 bytes in
+ * size. As no Commit can be that small, we find that the
+ * combination of these two criteria (bitmask & checksum)
+ * can always correctly determine the buffer format.
*/
word = (map[0] << 8) + map[1];
- if (map[0] == 0x78 && !(word % 31))
- return 1;
- else
+ if ((map[0] & 0x8F) == 0x08 && !(word % 31))
return 0;
+ else
+ return 1;
}
-unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep)
+unsigned long unpack_object_header_buffer(const unsigned char *buf,
+ unsigned long len, enum object_type *type, unsigned long *sizep)
{
unsigned shift;
- unsigned char c;
- unsigned long size;
+ unsigned long size, c;
unsigned long used = 0;
c = buf[used++];
@@ -1072,10 +1274,11 @@ unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned lon
size = c & 15;
shift = 4;
while (c & 0x80) {
- if (len <= used)
- return 0;
- if (sizeof(long) * 8 <= shift)
- return 0;
+ if (len <= used || bitsizeof(long) <= shift) {
+ error("bad object header");
+ size = used = 0;
+ break;
+ }
c = buf[used++];
size += (c & 0x7f) << shift;
shift += 7;
@@ -1084,7 +1287,7 @@ unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned lon
return used;
}
-static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
+int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
{
unsigned long size, used;
static const char valid_loose_object_type[8] = {
@@ -1101,40 +1304,35 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon
stream->next_out = buffer;
stream->avail_out = bufsiz;
- if (legacy_loose_object(map)) {
- inflateInit(stream);
- return inflate(stream, 0);
- }
-
-
- /*
- * There used to be a second loose object header format which
- * was meant to mimic the in-pack format, allowing for direct
- * copy of the object data. This format turned up not to be
- * really worth it and we don't write it any longer. But we
- * can still read it.
- */
- used = unpack_object_header_gently(map, mapsize, &type, &size);
- if (!used || !valid_loose_object_type[type])
- return -1;
- map += used;
- mapsize -= used;
+ if (experimental_loose_object(map)) {
+ /*
+ * The old experimental format we no longer produce;
+ * we can still read it.
+ */
+ used = unpack_object_header_buffer(map, mapsize, &type, &size);
+ if (!used || !valid_loose_object_type[type])
+ return -1;
+ map += used;
+ mapsize -= used;
- /* Set up the stream for the rest.. */
- stream->next_in = map;
- stream->avail_in = mapsize;
- inflateInit(stream);
+ /* Set up the stream for the rest.. */
+ stream->next_in = map;
+ stream->avail_in = mapsize;
+ git_inflate_init(stream);
- /* And generate the fake traditional header */
- stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
- typename(type), size);
- return 0;
+ /* And generate the fake traditional header */
+ stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
+ typename(type), size);
+ return 0;
+ }
+ git_inflate_init(stream);
+ return git_inflate(stream, 0);
}
-static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
+static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
{
int bytes = strlen(buffer) + 1;
- unsigned char *buf = xmalloc(1+size);
+ unsigned char *buf = xmallocz(size);
unsigned long n;
int status = Z_OK;
@@ -1147,7 +1345,7 @@ static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size
/*
* The above condition must be (bytes <= size), not
* (bytes < size). In other words, even though we
- * expect no more output and set avail_out to zer0,
+ * expect no more output and set avail_out to zero,
* the input zlib stream may have bytes that express
* "this concludes the stream", and we *do* want to
* eat that input.
@@ -1160,11 +1358,10 @@ static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size
stream->next_out = buf + bytes;
stream->avail_out = size - bytes;
while (status == Z_OK)
- status = inflate(stream, Z_FINISH);
+ status = git_inflate(stream, Z_FINISH);
}
- buf[size] = 0;
if (status == Z_STREAM_END && !stream->avail_in) {
- inflateEnd(stream);
+ git_inflate_end(stream);
return buf;
}
@@ -1182,7 +1379,7 @@ static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size
* too permissive for what we want to check. So do an anal
* object header parse by hand.
*/
-static int parse_sha1_header(const char *hdr, unsigned long *sizep)
+int parse_sha1_header(const char *hdr, unsigned long *sizep)
{
char type[10];
int i;
@@ -1231,7 +1428,7 @@ static int parse_sha1_header(const char *hdr, unsigned long *sizep)
static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)
{
int ret;
- z_stream stream;
+ git_zstream stream;
char hdr[8192];
ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr));
@@ -1247,24 +1444,26 @@ unsigned long get_size_from_delta(struct packed_git *p,
{
const unsigned char *data;
unsigned char delta_head[20], *in;
- z_stream stream;
+ git_zstream stream;
int st;
memset(&stream, 0, sizeof(stream));
stream.next_out = delta_head;
stream.avail_out = sizeof(delta_head);
- inflateInit(&stream);
+ git_inflate_init(&stream);
do {
in = use_pack(p, w_curs, curpos, &stream.avail_in);
stream.next_in = in;
- st = inflate(&stream, Z_FINISH);
+ st = git_inflate(&stream, Z_FINISH);
curpos += stream.next_in - in;
} while ((st == Z_OK || st == Z_BUF_ERROR) &&
stream.total_out < sizeof(delta_head));
- inflateEnd(&stream);
- if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head))
- die("delta data unpack-initial failed");
+ git_inflate_end(&stream);
+ if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) {
+ error("delta data unpack-initial failed");
+ return 0;
+ }
/* Examine the initial part of the delta to figure out
* the result size.
@@ -1300,20 +1499,17 @@ static off_t get_delta_base(struct packed_git *p,
while (c & 128) {
base_offset += 1;
if (!base_offset || MSB(base_offset, 7))
- die("offset value overflow for delta base object");
+ return 0; /* overflow */
c = base_info[used++];
base_offset = (base_offset << 7) + (c & 127);
}
base_offset = delta_obj_offset - base_offset;
- if (base_offset >= delta_obj_offset)
- die("delta base offset out of bound");
+ if (base_offset <= 0 || base_offset >= delta_obj_offset)
+ return 0; /* out of bound */
*curpos += used;
} else if (type == OBJ_REF_DELTA) {
/* The base entry _must_ be in the same pack */
base_offset = find_pack_entry_one(base_info, p);
- if (!base_offset)
- die("failed to find delta-pack base object %s",
- sha1_to_hex(base_info));
*curpos += 20;
} else
die("I am totally screwed");
@@ -1322,7 +1518,7 @@ static off_t get_delta_base(struct packed_git *p,
/* forward declaration for a mutually recursive function */
static int packed_object_info(struct packed_git *p, off_t offset,
- unsigned long *sizep);
+ unsigned long *sizep, int *rtype);
static int packed_delta_info(struct packed_git *p,
struct pack_window **w_curs,
@@ -1334,98 +1530,64 @@ static int packed_delta_info(struct packed_git *p,
off_t base_offset;
base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset);
- type = packed_object_info(p, base_offset, NULL);
+ if (!base_offset)
+ return OBJ_BAD;
+ type = packed_object_info(p, base_offset, NULL, NULL);
+ if (type <= OBJ_NONE) {
+ struct revindex_entry *revidx;
+ const unsigned char *base_sha1;
+ revidx = find_pack_revindex(p, base_offset);
+ if (!revidx)
+ return OBJ_BAD;
+ base_sha1 = nth_packed_object_sha1(p, revidx->nr);
+ mark_bad_packed_object(p, base_sha1);
+ type = sha1_object_info(base_sha1, NULL);
+ if (type <= OBJ_NONE)
+ return OBJ_BAD;
+ }
/* We choose to only get the type of the base object and
* ignore potentially corrupt pack file that expects the delta
* based on a base with a wrong size. This saves tons of
* inflate() calls.
*/
- if (sizep)
+ if (sizep) {
*sizep = get_size_from_delta(p, w_curs, curpos);
+ if (*sizep == 0)
+ type = OBJ_BAD;
+ }
return type;
}
-static int unpack_object_header(struct packed_git *p,
- struct pack_window **w_curs,
- off_t *curpos,
- unsigned long *sizep)
+int unpack_object_header(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t *curpos,
+ unsigned long *sizep)
{
unsigned char *base;
- unsigned int left;
+ unsigned long left;
unsigned long used;
enum object_type type;
/* use_pack() assures us we have [base, base + 20) available
- * as a range that we can look at at. (Its actually the hash
+ * as a range that we can look at. (Its actually the hash
* size that is assured.) With our object header encoding
* the maximum deflated object size is 2^137, which is just
* insane, so we know won't exceed what we have been given.
*/
base = use_pack(p, w_curs, *curpos, &left);
- used = unpack_object_header_gently(base, left, &type, sizep);
- if (!used)
- die("object offset outside of pack file");
- *curpos += used;
+ used = unpack_object_header_buffer(base, left, &type, sizep);
+ if (!used) {
+ type = OBJ_BAD;
+ } else
+ *curpos += used;
return type;
}
-const char *packed_object_info_detail(struct packed_git *p,
- off_t obj_offset,
- unsigned long *size,
- unsigned long *store_size,
- unsigned int *delta_chain_length,
- unsigned char *base_sha1)
-{
- struct pack_window *w_curs = NULL;
- off_t curpos;
- unsigned long dummy;
- unsigned char *next_sha1;
- enum object_type type;
- struct revindex_entry *revidx;
-
- *delta_chain_length = 0;
- curpos = obj_offset;
- type = unpack_object_header(p, &w_curs, &curpos, size);
-
- revidx = find_pack_revindex(p, obj_offset);
- *store_size = revidx[1].offset - obj_offset;
-
- for (;;) {
- switch (type) {
- default:
- die("pack %s contains unknown object type %d",
- p->pack_name, type);
- case OBJ_COMMIT:
- case OBJ_TREE:
- case OBJ_BLOB:
- case OBJ_TAG:
- unuse_pack(&w_curs);
- return typename(type);
- case OBJ_OFS_DELTA:
- obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset);
- if (*delta_chain_length == 0) {
- revidx = find_pack_revindex(p, obj_offset);
- hashcpy(base_sha1, nth_packed_object_sha1(p, revidx->nr));
- }
- break;
- case OBJ_REF_DELTA:
- next_sha1 = use_pack(p, &w_curs, curpos, NULL);
- if (*delta_chain_length == 0)
- hashcpy(base_sha1, next_sha1);
- obj_offset = find_pack_entry_one(next_sha1, p);
- break;
- }
- (*delta_chain_length)++;
- curpos = obj_offset;
- type = unpack_object_header(p, &w_curs, &curpos, &dummy);
- }
-}
-
static int packed_object_info(struct packed_git *p, off_t obj_offset,
- unsigned long *sizep)
+ unsigned long *sizep, int *rtype)
{
struct pack_window *w_curs = NULL;
unsigned long size;
@@ -1433,6 +1595,8 @@ static int packed_object_info(struct packed_git *p, off_t obj_offset,
enum object_type type;
type = unpack_object_header(p, &w_curs, &curpos, &size);
+ if (rtype)
+ *rtype = type; /* representation type */
switch (type) {
case OBJ_OFS_DELTA:
@@ -1448,8 +1612,9 @@ static int packed_object_info(struct packed_git *p, off_t obj_offset,
*sizep = size;
break;
default:
- die("pack %s contains unknown object type %d",
- p->pack_name, type);
+ error("unknown object type %i at offset %"PRIuMAX" in %s",
+ type, (uintmax_t)obj_offset, p->pack_name);
+ type = OBJ_BAD;
}
unuse_pack(&w_curs);
return type;
@@ -1461,23 +1626,24 @@ static void *unpack_compressed_entry(struct packed_git *p,
unsigned long size)
{
int st;
- z_stream stream;
+ git_zstream stream;
unsigned char *buffer, *in;
- buffer = xmalloc(size + 1);
- buffer[size] = 0;
+ buffer = xmallocz(size);
memset(&stream, 0, sizeof(stream));
stream.next_out = buffer;
- stream.avail_out = size;
+ stream.avail_out = size + 1;
- inflateInit(&stream);
+ git_inflate_init(&stream);
do {
in = use_pack(p, w_curs, curpos, &stream.avail_in);
stream.next_in = in;
- st = inflate(&stream, Z_FINISH);
+ st = git_inflate(&stream, Z_FINISH);
+ if (!stream.avail_out)
+ break; /* the payload is larger than it should be */
curpos += stream.next_in - in;
} while (st == Z_OK || st == Z_BUF_ERROR);
- inflateEnd(&stream);
+ git_inflate_end(&stream);
if ((st != Z_STREAM_END) || stream.total_out != size) {
free(buffer);
return NULL;
@@ -1513,6 +1679,13 @@ static unsigned long pack_entry_hash(struct packed_git *p, off_t base_offset)
return hash % MAX_DELTA_CACHE;
}
+static int in_delta_base_cache(struct packed_git *p, off_t base_offset)
+{
+ unsigned long hash = pack_entry_hash(p, base_offset);
+ struct delta_base_cache_entry *ent = delta_base_cache + hash;
+ return (ent->data && ent->p == p && ent->base_offset == base_offset);
+}
+
static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset,
unsigned long *base_size, enum object_type *type, int keep_cache)
{
@@ -1521,11 +1694,9 @@ static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset,
struct delta_base_cache_entry *ent = delta_base_cache + hash;
ret = ent->data;
- if (ret && ent->p == p && ent->base_offset == base_offset)
- goto found_cache_entry;
- return unpack_entry(p, base_offset, type, base_size);
+ if (!ret || ent->p != p || ent->base_offset != base_offset)
+ return unpack_entry(p, base_offset, type, base_size);
-found_cache_entry:
if (!keep_cache) {
ent->data = NULL;
ent->lru.next->prev = ent->lru.prev;
@@ -1550,6 +1721,13 @@ static inline void release_delta_base_cache(struct delta_base_cache_entry *ent)
}
}
+void clear_delta_base_cache(void)
+{
+ unsigned long p;
+ for (p = 0; p < MAX_DELTA_CACHE; p++)
+ release_delta_base_cache(&delta_base_cache[p]);
+}
+
static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
void *base, unsigned long base_size, enum object_type type)
{
@@ -1587,6 +1765,9 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
delta_base_cache_lru.prev = &ent->lru;
}
+static void *read_object(const unsigned char *sha1, enum object_type *type,
+ unsigned long *size);
+
static void *unpack_delta_entry(struct packed_git *p,
struct pack_window **w_curs,
off_t curpos,
@@ -1600,17 +1781,45 @@ static void *unpack_delta_entry(struct packed_git *p,
off_t base_offset;
base_offset = get_delta_base(p, w_curs, &curpos, *type, obj_offset);
+ if (!base_offset) {
+ error("failed to validate delta base reference "
+ "at offset %"PRIuMAX" from %s",
+ (uintmax_t)curpos, p->pack_name);
+ return NULL;
+ }
+ unuse_pack(w_curs);
base = cache_or_unpack_entry(p, base_offset, &base_size, type, 0);
- if (!base)
- die("failed to read delta base object"
- " at %"PRIuMAX" from %s",
- (uintmax_t)base_offset, p->pack_name);
+ if (!base) {
+ /*
+ * We're probably in deep shit, but let's try to fetch
+ * the required base anyway from another pack or loose.
+ * This is costly but should happen only in the presence
+ * of a corrupted pack, and is better than failing outright.
+ */
+ struct revindex_entry *revidx;
+ const unsigned char *base_sha1;
+ revidx = find_pack_revindex(p, base_offset);
+ if (!revidx)
+ return NULL;
+ base_sha1 = nth_packed_object_sha1(p, revidx->nr);
+ error("failed to read delta base object %s"
+ " at offset %"PRIuMAX" from %s",
+ sha1_to_hex(base_sha1), (uintmax_t)base_offset,
+ p->pack_name);
+ mark_bad_packed_object(p, base_sha1);
+ base = read_object(base_sha1, type, &base_size);
+ if (!base)
+ return NULL;
+ }
delta_data = unpack_compressed_entry(p, w_curs, curpos, delta_size);
- if (!delta_data)
- die("failed to unpack compressed delta"
- " at %"PRIuMAX" from %s",
- (uintmax_t)curpos, p->pack_name);
+ if (!delta_data) {
+ error("failed to unpack compressed delta "
+ "at offset %"PRIuMAX" from %s",
+ (uintmax_t)curpos, p->pack_name);
+ free(base);
+ return NULL;
+ }
result = patch_delta(base, base_size,
delta_data, delta_size,
sizep);
@@ -1621,6 +1830,26 @@ static void *unpack_delta_entry(struct packed_git *p,
return result;
}
+static void write_pack_access_log(struct packed_git *p, off_t obj_offset)
+{
+ static FILE *log_file;
+
+ 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 = NULL;
+ return;
+ }
+ }
+ fprintf(log_file, "%s %"PRIuMAX"\n",
+ p->pack_name, (uintmax_t)obj_offset);
+ fflush(log_file);
+}
+
+int do_check_packed_object_crc;
+
void *unpack_entry(struct packed_git *p, off_t obj_offset,
enum object_type *type, unsigned long *sizep)
{
@@ -1628,6 +1857,23 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset,
off_t curpos = obj_offset;
void *data;
+ if (log_pack_access)
+ write_pack_access_log(p, obj_offset);
+
+ if (do_check_packed_object_crc && p->index_version > 1) {
+ struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
+ unsigned long len = revidx[1].offset - obj_offset;
+ if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) {
+ const unsigned char *sha1 =
+ nth_packed_object_sha1(p, revidx->nr);
+ error("bad packed object CRC for %s",
+ sha1_to_hex(sha1));
+ mark_bad_packed_object(p, sha1);
+ unuse_pack(&w_curs);
+ return NULL;
+ }
+ }
+
*type = unpack_object_header(p, &w_curs, &curpos, sizep);
switch (*type) {
case OBJ_OFS_DELTA:
@@ -1642,7 +1888,9 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset,
data = unpack_compressed_entry(p, &w_curs, curpos, *sizep);
break;
default:
- die("unknown object type %i in %s", *type, p->pack_name);
+ data = NULL;
+ error("unknown object type %i at offset %"PRIuMAX" in %s",
+ *type, (uintmax_t)obj_offset, p->pack_name);
}
unuse_pack(&w_curs);
return data;
@@ -1668,7 +1916,7 @@ const unsigned char *nth_packed_object_sha1(struct packed_git *p,
}
}
-static off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n)
+off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n)
{
const unsigned char *index = p->index_data;
index += 4 * 256;
@@ -1719,7 +1967,7 @@ off_t find_pack_entry_one(const unsigned char *sha1,
}
if (debug_lookup)
- printf("%02x%02x%02x... lo %u hi %u nr %u\n",
+ printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n",
sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects);
if (use_lookup < 0)
@@ -1749,74 +1997,79 @@ off_t find_pack_entry_one(const unsigned char *sha1,
return 0;
}
-int matches_pack_name(struct packed_git *p, const char *name)
+int is_pack_valid(struct packed_git *p)
{
- const char *last_c, *c;
-
- if (!strcmp(p->pack_name, name))
+ /* An already open pack is known to be valid. */
+ if (p->pack_fd != -1)
return 1;
- for (c = p->pack_name, last_c = c; *c;)
- if (*c == '/')
- last_c = ++c;
- else
- ++c;
- if (!strcmp(last_c, name))
- return 1;
+ /* If the pack has one window completely covering the
+ * file size, the pack is known to be valid even if
+ * the descriptor is not currently open.
+ */
+ if (p->windows) {
+ struct pack_window *w = p->windows;
- return 0;
+ if (!w->offset && w->len == p->pack_size)
+ return 1;
+ }
+
+ /* Force the pack to open to prove its valid. */
+ return !open_packed_git(p);
}
-static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e, const char **ignore_packed)
+static int fill_pack_entry(const unsigned char *sha1,
+ struct pack_entry *e,
+ struct packed_git *p)
{
- static struct packed_git *last_found = (void *)1;
- struct packed_git *p;
off_t offset;
+ if (p->num_bad_objects) {
+ unsigned i;
+ for (i = 0; i < p->num_bad_objects; i++)
+ if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
+ return 0;
+ }
+
+ offset = find_pack_entry_one(sha1, p);
+ if (!offset)
+ return 0;
+
+ /*
+ * We are about to tell the caller where they can locate the
+ * requested object. We better make sure the packfile is
+ * still here and can be accessed before supplying that
+ * answer, as it may have been deleted since the index was
+ * loaded!
+ */
+ if (!is_pack_valid(p)) {
+ warning("packfile %s cannot be accessed", p->pack_name);
+ return 0;
+ }
+ e->offset = offset;
+ e->p = p;
+ hashcpy(e->sha1, sha1);
+ return 1;
+}
+
+static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
+{
+ struct packed_git *p;
+
prepare_packed_git();
if (!packed_git)
return 0;
- p = (last_found == (void *)1) ? packed_git : last_found;
- do {
- if (ignore_packed) {
- const char **ig;
- for (ig = ignore_packed; *ig; ig++)
- if (matches_pack_name(p, *ig))
- break;
- if (*ig)
- goto next;
- }
+ if (last_found_pack && fill_pack_entry(sha1, e, last_found_pack))
+ return 1;
- offset = find_pack_entry_one(sha1, p);
- if (offset) {
- /*
- * We are about to tell the caller where they can
- * locate the requested object. We better make
- * sure the packfile is still here and can be
- * accessed before supplying that answer, as
- * it may have been deleted since the index
- * was loaded!
- */
- if (p->pack_fd == -1 && open_packed_git(p)) {
- error("packfile %s cannot be accessed", p->pack_name);
- goto next;
- }
- e->offset = offset;
- e->p = p;
- hashcpy(e->sha1, sha1);
- last_found = p;
- return 1;
- }
+ for (p = packed_git; p; p = p->next) {
+ if (p == last_found_pack || !fill_pack_entry(sha1, e, p))
+ continue;
- next:
- if (p == last_found)
- p = packed_git;
- else
- p = p->next;
- if (p == last_found)
- p = p->next;
- } while (p);
+ last_found_pack = p;
+ return 1;
+ }
return 0;
}
@@ -1838,7 +2091,7 @@ static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *size
int status;
unsigned long mapsize, size;
void *map;
- z_stream stream;
+ git_zstream stream;
char hdr[32];
map = map_sha1_file(sha1, &mapsize);
@@ -1851,69 +2104,87 @@ static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *size
status = error("unable to parse %s header", sha1_to_hex(sha1));
else if (sizep)
*sizep = size;
- inflateEnd(&stream);
+ git_inflate_end(&stream);
munmap(map, mapsize);
return status;
}
-int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
+/* returns enum object_type or negative */
+int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi)
{
+ struct cached_object *co;
struct pack_entry e;
+ int status, rtype;
- if (!find_pack_entry(sha1, &e, NULL)) {
+ co = find_cached_object(sha1);
+ if (co) {
+ if (oi->sizep)
+ *(oi->sizep) = co->size;
+ oi->whence = OI_CACHED;
+ return co->type;
+ }
+
+ if (!find_pack_entry(sha1, &e)) {
+ /* Most likely it's a loose object. */
+ status = sha1_loose_object_info(sha1, oi->sizep);
+ if (status >= 0) {
+ oi->whence = OI_LOOSE;
+ return status;
+ }
+
+ /* Not a loose object; someone else may have just packed it. */
reprepare_packed_git();
- if (!find_pack_entry(sha1, &e, NULL))
- return sha1_loose_object_info(sha1, sizep);
+ if (!find_pack_entry(sha1, &e))
+ return status;
}
- return packed_object_info(e.p, e.offset, sizep);
-}
-static void *read_packed_sha1(const unsigned char *sha1,
- enum object_type *type, unsigned long *size)
-{
- struct pack_entry e;
+ status = packed_object_info(e.p, e.offset, oi->sizep, &rtype);
+ if (status < 0) {
+ mark_bad_packed_object(e.p, sha1);
+ status = sha1_object_info_extended(sha1, oi);
+ } else if (in_delta_base_cache(e.p, e.offset)) {
+ oi->whence = OI_DBCACHED;
+ } else {
+ oi->whence = OI_PACKED;
+ oi->u.packed.offset = e.offset;
+ oi->u.packed.pack = e.p;
+ oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
+ rtype == OBJ_OFS_DELTA);
+ }
- if (!find_pack_entry(sha1, &e, NULL))
- return NULL;
- else
- return cache_or_unpack_entry(e.p, e.offset, size, type, 1);
+ return status;
}
-/*
- * 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
- * to write them into the object store (e.g. a browse-only
- * application).
- */
-static struct cached_object {
- unsigned char sha1[20];
- enum object_type type;
- void *buf;
- unsigned long size;
-} *cached_objects;
-static int cached_object_nr, cached_object_alloc;
+int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
+{
+ struct object_info oi;
-static struct cached_object empty_tree = {
- /* empty tree sha1: 4b825dc642cb6eb9a060e54bf8d69288fbee4904 */
- "\x4b\x82\x5d\xc6\x42\xcb\x6e\xb9\xa0\x60"
- "\xe5\x4b\xf8\xd6\x92\x88\xfb\xee\x49\x04",
- OBJ_TREE,
- "",
- 0
-};
+ oi.sizep = sizep;
+ return sha1_object_info_extended(sha1, &oi);
+}
-static struct cached_object *find_cached_object(const unsigned char *sha1)
+static void *read_packed_sha1(const unsigned char *sha1,
+ enum object_type *type, unsigned long *size)
{
- int i;
- struct cached_object *co = cached_objects;
+ struct pack_entry e;
+ void *data;
- for (i = 0; i < cached_object_nr; i++, co++) {
- if (!hashcmp(co->sha1, sha1))
- return co;
+ if (!find_pack_entry(sha1, &e))
+ return NULL;
+ data = cache_or_unpack_entry(e.p, e.offset, size, type, 1);
+ if (!data) {
+ /*
+ * We're probably in deep shit, but let's try to fetch
+ * the required object anyway from another pack or loose.
+ * This should happen only in the presence of a corrupted
+ * pack, and is better than failing outright.
+ */
+ error("failed to read object %s at offset %"PRIuMAX" from %s",
+ sha1_to_hex(sha1), (uintmax_t)e.offset, e.p->pack_name);
+ mark_bad_packed_object(e.p, sha1);
+ data = read_object(sha1, type, size);
}
- if (!hashcmp(sha1, empty_tree.sha1))
- return &empty_tree;
- return NULL;
+ return data;
}
int pretend_sha1_file(void *buf, unsigned long len, enum object_type type,
@@ -1939,8 +2210,8 @@ int pretend_sha1_file(void *buf, unsigned long len, enum object_type type,
return 0;
}
-void *read_sha1_file(const unsigned char *sha1, enum object_type *type,
- unsigned long *size)
+static void *read_object(const unsigned char *sha1, enum object_type *type,
+ unsigned long *size)
{
unsigned long mapsize;
void *map, *buf;
@@ -1966,6 +2237,48 @@ void *read_sha1_file(const unsigned char *sha1, enum object_type *type,
return read_packed_sha1(sha1, type, size);
}
+/*
+ * This function dies on corrupt objects; the callers who want to
+ * deal with them should arrange to call read_object() and give error
+ * messages themselves.
+ */
+void *read_sha1_file_extended(const unsigned char *sha1,
+ enum object_type *type,
+ unsigned long *size,
+ unsigned flag)
+{
+ void *data;
+ char *path;
+ const struct packed_git *p;
+ const unsigned char *repl = (flag & READ_SHA1_FILE_REPLACE)
+ ? lookup_replace_object(sha1) : sha1;
+
+ errno = 0;
+ data = read_object(repl, type, size);
+ if (data)
+ return data;
+
+ if (errno && errno != ENOENT)
+ die_errno("failed to read object %s", sha1_to_hex(sha1));
+
+ /* die if we replaced an object with one that does not exist */
+ if (repl != sha1)
+ die("replacement %s not found for %s",
+ sha1_to_hex(repl), sha1_to_hex(sha1));
+
+ if (has_loose_object(repl)) {
+ path = sha1_file_name(sha1);
+ die("loose object %s (stored in %s) is corrupt",
+ sha1_to_hex(repl), path);
+ }
+
+ if ((p = has_packed_and_bad(repl)) != NULL)
+ die("packed object %s (stored in %s) is corrupt",
+ sha1_to_hex(repl), p->pack_name);
+
+ return NULL;
+}
+
void *read_object_with_reference(const unsigned char *sha1,
const char *required_type_name,
unsigned long *size,
@@ -2018,24 +2331,32 @@ static void write_sha1_file_prepare(const void *buf, unsigned long len,
const char *type, unsigned char *sha1,
char *hdr, int *hdrlen)
{
- SHA_CTX c;
+ git_SHA_CTX c;
/* Generate the header */
*hdrlen = sprintf(hdr, "%s %lu", type, len)+1;
/* Sha1.. */
- SHA1_Init(&c);
- SHA1_Update(&c, hdr, *hdrlen);
- SHA1_Update(&c, buf, len);
- SHA1_Final(sha1, &c);
+ git_SHA1_Init(&c);
+ git_SHA1_Update(&c, hdr, *hdrlen);
+ git_SHA1_Update(&c, buf, len);
+ git_SHA1_Final(sha1, &c);
}
/*
- * Move the just written object into its final resting place
+ * Move the just written object into its final resting place.
+ * NEEDSWORK: this should be renamed to finalize_temp_file() as
+ * "moving" is only a part of what it does, when no patch between
+ * master to pu changes the call sites of this function.
*/
int move_temp_to_file(const char *tmpfile, const char *filename)
{
- int ret = link(tmpfile, filename);
+ int ret = 0;
+
+ if (object_creation_mode == OBJECT_CREATION_USES_RENAMES)
+ goto try_rename;
+ else if (link(tmpfile, filename))
+ ret = errno;
/*
* Coda hack - coda doesn't like cross-directory links,
@@ -2045,15 +2366,16 @@ int move_temp_to_file(const char *tmpfile, const char *filename)
*
* The same holds for FAT formatted media.
*
- * When this succeeds, we just return 0. We have nothing
+ * When this succeeds, we just return. We have nothing
* left to unlink.
*/
if (ret && ret != EEXIST) {
+ try_rename:
if (!rename(tmpfile, filename))
- return 0;
+ goto out;
ret = errno;
}
- unlink(tmpfile);
+ unlink_or_warn(tmpfile);
if (ret) {
if (ret != EEXIST) {
return error("unable to write sha1 filename %s: %s\n", filename, strerror(ret));
@@ -2061,6 +2383,9 @@ int move_temp_to_file(const char *tmpfile, const char *filename)
/* FIXME!!! Collision check here ? */
}
+out:
+ if (adjust_shared_perm(filename))
+ return error("unable to set permission to '%s'", filename);
return 0;
}
@@ -2083,10 +2408,10 @@ int hash_sha1_file(const void *buf, unsigned long len, const char *type,
/* Finalize a file on disk, and close it. */
static void close_sha1_file(int fd)
{
- /* For safe-mode, we could fsync_or_die(fd, "sha1 file") here */
- fchmod(fd, 0444);
+ if (fsync_object_files)
+ fsync_or_die(fd, "sha1 file");
if (close(fd) != 0)
- die("unable to write sha1 file");
+ die_errno("error when closing sha1 file");
}
/* Size of directory component, including the ending '/' */
@@ -2115,85 +2440,92 @@ static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename)
}
memcpy(buffer, filename, dirlen);
strcpy(buffer + dirlen, "tmp_obj_XXXXXX");
- fd = mkstemp(buffer);
- if (fd < 0 && dirlen) {
+ fd = git_mkstemp_mode(buffer, 0444);
+ if (fd < 0 && dirlen && errno == ENOENT) {
/* Make sure the directory exists */
+ memcpy(buffer, filename, dirlen);
buffer[dirlen-1] = 0;
if (mkdir(buffer, 0777) || adjust_shared_perm(buffer))
return -1;
/* Try again */
strcpy(buffer + dirlen - 1, "/tmp_obj_XXXXXX");
- fd = mkstemp(buffer);
+ fd = git_mkstemp_mode(buffer, 0444);
}
return fd;
}
static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
- void *buf, unsigned long len, time_t mtime)
+ const void *buf, unsigned long len, time_t mtime)
{
- int fd, size, ret;
- unsigned char *compressed;
- z_stream stream;
+ int fd, ret;
+ unsigned char compressed[4096];
+ git_zstream stream;
+ git_SHA_CTX c;
+ unsigned char parano_sha1[20];
char *filename;
- static char tmpfile[PATH_MAX];
+ static char tmp_file[PATH_MAX];
filename = sha1_file_name(sha1);
- fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
+ fd = create_tmpfile(tmp_file, sizeof(tmp_file), filename);
if (fd < 0) {
- if (errno == EPERM)
+ if (errno == EACCES)
return error("insufficient permission for adding an object to repository database %s\n", get_object_directory());
else
- return error("unable to create temporary sha1 filename %s: %s\n", tmpfile, strerror(errno));
+ return error("unable to create temporary sha1 filename %s: %s\n", tmp_file, strerror(errno));
}
/* Set it up */
memset(&stream, 0, sizeof(stream));
- deflateInit(&stream, zlib_compression_level);
- size = 8 + deflateBound(&stream, len+hdrlen);
- compressed = xmalloc(size);
-
- /* Compress it */
+ git_deflate_init(&stream, zlib_compression_level);
stream.next_out = compressed;
- stream.avail_out = size;
+ stream.avail_out = sizeof(compressed);
+ git_SHA1_Init(&c);
/* First header.. */
stream.next_in = (unsigned char *)hdr;
stream.avail_in = hdrlen;
- while (deflate(&stream, 0) == Z_OK)
- /* nothing */;
+ while (git_deflate(&stream, 0) == Z_OK)
+ ; /* nothing */
+ git_SHA1_Update(&c, hdr, hdrlen);
/* Then the data itself.. */
- stream.next_in = buf;
+ stream.next_in = (void *)buf;
stream.avail_in = len;
- ret = deflate(&stream, Z_FINISH);
+ do {
+ unsigned char *in0 = stream.next_in;
+ ret = git_deflate(&stream, Z_FINISH);
+ git_SHA1_Update(&c, in0, stream.next_in - in0);
+ if (write_buffer(fd, compressed, stream.next_out - compressed) < 0)
+ die("unable to write sha1 file");
+ stream.next_out = compressed;
+ stream.avail_out = sizeof(compressed);
+ } while (ret == Z_OK);
+
if (ret != Z_STREAM_END)
die("unable to deflate new object %s (%d)", sha1_to_hex(sha1), ret);
-
- ret = deflateEnd(&stream);
+ ret = git_deflate_end_gently(&stream);
if (ret != Z_OK)
die("deflateEnd on object %s failed (%d)", sha1_to_hex(sha1), ret);
+ git_SHA1_Final(parano_sha1, &c);
+ if (hashcmp(sha1, parano_sha1) != 0)
+ die("confused by unstable object source data for %s", sha1_to_hex(sha1));
- size = stream.total_out;
-
- if (write_buffer(fd, compressed, size) < 0)
- die("unable to write sha1 file");
close_sha1_file(fd);
- free(compressed);
if (mtime) {
struct utimbuf utb;
utb.actime = mtime;
utb.modtime = mtime;
- if (utime(tmpfile, &utb) < 0)
+ if (utime(tmp_file, &utb) < 0)
warning("failed utime() on %s: %s",
- tmpfile, strerror(errno));
+ tmp_file, strerror(errno));
}
- return move_temp_to_file(tmpfile, filename);
+ return move_temp_to_file(tmp_file, filename);
}
-int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
+int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
{
unsigned char sha1[20];
char hdr[32];
@@ -2217,6 +2549,7 @@ int force_object_loose(const unsigned char *sha1, time_t mtime)
enum object_type type;
char hdr[32];
int hdrlen;
+ int ret;
if (has_loose_object(sha1))
return 0;
@@ -2224,7 +2557,10 @@ int force_object_loose(const unsigned char *sha1, time_t mtime)
if (!buf)
return error("cannot read sha1_file for %s", sha1_to_hex(sha1));
hdrlen = sprintf(hdr, "%s %lu", typename(type), len) + 1;
- return write_loose_object(sha1, hdr, hdrlen, buf, len, mtime);
+ ret = write_loose_object(sha1, hdr, hdrlen, buf, len, mtime);
+ free(buf);
+
+ return ret;
}
int has_pack_index(const unsigned char *sha1)
@@ -2235,61 +2571,55 @@ int has_pack_index(const unsigned char *sha1)
return 1;
}
-int has_pack_file(const unsigned char *sha1)
-{
- struct stat st;
- if (stat(sha1_pack_name(sha1), &st))
- return 0;
- return 1;
-}
-
-int has_sha1_pack(const unsigned char *sha1, const char **ignore_packed)
+int has_sha1_pack(const unsigned char *sha1)
{
struct pack_entry e;
- return find_pack_entry(sha1, &e, ignore_packed);
+ return find_pack_entry(sha1, &e);
}
int has_sha1_file(const unsigned char *sha1)
{
struct pack_entry e;
- if (find_pack_entry(sha1, &e, NULL))
+ if (find_pack_entry(sha1, &e))
return 1;
return has_loose_object(sha1);
}
-int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object)
+static void check_tree(const void *buf, size_t size)
{
- struct strbuf buf;
- int ret;
+ struct tree_desc desc;
+ struct name_entry entry;
- strbuf_init(&buf, 0);
- if (strbuf_read(&buf, fd, 4096) < 0) {
- strbuf_release(&buf);
- return -1;
- }
+ init_tree_desc(&desc, buf, size);
+ while (tree_entry(&desc, &entry))
+ /* do nothing
+ * tree_entry() will die() on malformed entries */
+ ;
+}
- if (!type)
- type = blob_type;
- if (write_object)
- ret = write_sha1_file(buf.buf, buf.len, type, sha1);
- else
- ret = hash_sha1_file(buf.buf, buf.len, type, sha1);
- strbuf_release(&buf);
+static void check_commit(const void *buf, size_t size)
+{
+ struct commit c;
+ memset(&c, 0, sizeof(c));
+ if (parse_commit_buffer(&c, buf, size))
+ die("corrupt commit");
+}
- return ret;
+static void check_tag(const void *buf, size_t size)
+{
+ struct tag t;
+ memset(&t, 0, sizeof(t));
+ if (parse_tag_buffer(&t, buf, size))
+ die("corrupt tag");
}
-int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
- enum object_type type, const char *path)
+static int index_mem(unsigned char *sha1, void *buf, size_t size,
+ enum object_type type,
+ const char *path, unsigned flags)
{
- size_t size = xsize_t(st->st_size);
- void *buf = NULL;
int ret, re_allocated = 0;
-
- if (size)
- buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
- close(fd);
+ int write_object = flags & HASH_WRITE_OBJECT;
if (!type)
type = OBJ_BLOB;
@@ -2297,35 +2627,114 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
/*
* Convert blobs to git internal format
*/
- if ((type == OBJ_BLOB) && S_ISREG(st->st_mode)) {
- struct strbuf nbuf;
- strbuf_init(&nbuf, 0);
+ if ((type == OBJ_BLOB) && path) {
+ struct strbuf nbuf = STRBUF_INIT;
if (convert_to_git(path, buf, size, &nbuf,
- write_object ? safe_crlf : 0)) {
- munmap(buf, size);
+ write_object ? safe_crlf : SAFE_CRLF_FALSE)) {
buf = strbuf_detach(&nbuf, &size);
re_allocated = 1;
}
}
+ if (flags & HASH_FORMAT_CHECK) {
+ if (type == OBJ_TREE)
+ check_tree(buf, size);
+ if (type == OBJ_COMMIT)
+ check_commit(buf, size);
+ if (type == OBJ_TAG)
+ check_tag(buf, size);
+ }
if (write_object)
ret = write_sha1_file(buf, size, typename(type), sha1);
else
ret = hash_sha1_file(buf, size, typename(type), sha1);
- if (re_allocated) {
+ if (re_allocated)
free(buf);
- return ret;
- }
- if (size)
+ return ret;
+}
+
+static int index_pipe(unsigned char *sha1, int fd, enum object_type type,
+ const char *path, unsigned flags)
+{
+ struct strbuf sbuf = STRBUF_INIT;
+ int ret;
+
+ if (strbuf_read(&sbuf, fd, 4096) >= 0)
+ ret = index_mem(sha1, sbuf.buf, sbuf.len, type, path, flags);
+ else
+ ret = -1;
+ strbuf_release(&sbuf);
+ return ret;
+}
+
+#define SMALL_FILE_SIZE (32*1024)
+
+static int index_core(unsigned char *sha1, int fd, size_t size,
+ enum object_type type, const char *path,
+ unsigned flags)
+{
+ int ret;
+
+ if (!size) {
+ ret = index_mem(sha1, NULL, size, type, path, flags);
+ } else if (size <= SMALL_FILE_SIZE) {
+ char *buf = xmalloc(size);
+ if (size == read_in_full(fd, buf, size))
+ ret = index_mem(sha1, buf, size, type, path, flags);
+ else
+ ret = error("short read %s", strerror(errno));
+ free(buf);
+ } else {
+ void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
+ ret = index_mem(sha1, buf, size, type, path, flags);
munmap(buf, size);
+ }
+ return ret;
+}
+
+/*
+ * This creates one packfile per large blob unless bulk-checkin
+ * machinery is "plugged".
+ *
+ * This also bypasses the usual "convert-to-git" dance, and that is on
+ * purpose. We could write a streaming version of the converting
+ * functions and insert that before feeding the data to fast-import
+ * (or equivalent in-core API described above). However, that is
+ * somewhat complicated, as we do not know the size of the filter
+ * result, which we need to know beforehand when writing a git object.
+ * Since the primary motivation for trying to stream from the working
+ * tree file and to avoid mmaping it in core is to deal with large
+ * binary blobs, they generally do not want to get any conversion, and
+ * callers should avoid this code path when filters are requested.
+ */
+static int index_stream(unsigned char *sha1, int fd, size_t size,
+ enum object_type type, const char *path,
+ unsigned flags)
+{
+ return index_bulk_checkin(sha1, fd, size, type, path, flags);
+}
+
+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))
+ 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
+ ret = index_stream(sha1, fd, size, type, path, flags);
+ close(fd);
return ret;
}
-int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object)
+int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags)
{
int fd;
- char *target;
- size_t len;
+ struct strbuf sb = STRBUF_INIT;
switch (st->st_mode & S_IFMT) {
case S_IFREG:
@@ -2333,25 +2742,22 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write
if (fd < 0)
return error("open(\"%s\"): %s", path,
strerror(errno));
- if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path) < 0)
+ if (index_fd(sha1, fd, st, OBJ_BLOB, path, flags) < 0)
return error("%s: failed to insert into database",
path);
break;
case S_IFLNK:
- len = xsize_t(st->st_size);
- target = xmalloc(len + 1);
- if (readlink(path, target, len + 1) != st->st_size) {
+ if (strbuf_readlink(&sb, path, st->st_size)) {
char *errstr = strerror(errno);
- free(target);
return error("readlink(\"%s\"): %s", path,
errstr);
}
- if (!write_object)
- hash_sha1_file(target, len, blob_type, sha1);
- else if (write_sha1_file(target, len, blob_type, sha1))
+ if (!(flags & HASH_WRITE_OBJECT))
+ hash_sha1_file(sb.buf, sb.len, blob_type, sha1);
+ else if (write_sha1_file(sb.buf, sb.len, blob_type, sha1))
return error("%s: failed to insert into database",
path);
- free(target);
+ strbuf_release(&sb);
break;
case S_IFDIR:
return resolve_gitlink_ref(path, "HEAD", sha1);
@@ -2375,3 +2781,13 @@ int read_pack_header(int fd, struct pack_header *header)
return PH_ERROR_PROTOCOL;
return 0;
}
+
+void assert_sha1_type(const unsigned char *sha1, enum object_type expect)
+{
+ enum object_type type = sha1_object_info(sha1, NULL);
+ if (type < 0)
+ die("%s is not a valid object", sha1_to_hex(sha1));
+ if (type != expect)
+ die("%s is not a valid '%s' object", sha1_to_hex(sha1),
+ typename(expect));
+}
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-17 22:04:28 +0000