blob: 22e7b9944e35d257b144fe06dce2073c91d4819f [file] [log] [blame]
/*
* GIT - The information manager from hell
*
* Copyright (C) Linus Torvalds, 2005
*/
#include "cache.h"
#include "config.h"
#include "diff.h"
#include "diffcore.h"
#include "tempfile.h"
#include "lockfile.h"
#include "cache-tree.h"
#include "refs.h"
#include "dir.h"
#include "object-store.h"
#include "tree.h"
#include "commit.h"
#include "blob.h"
#include "resolve-undo.h"
#include "run-command.h"
#include "strbuf.h"
#include "varint.h"
#include "split-index.h"
#include "utf8.h"
#include "fsmonitor.h"
#include "thread-utils.h"
#include "progress.h"
/* Mask for the name length in ce_flags in the on-disk index */
#define CE_NAMEMASK (0x0fff)
/* Index extensions.
*
* The first letter should be 'A'..'Z' for extensions that are not
* necessary for a correct operation (i.e. optimization data).
* When new extensions are added that _needs_ to be understood in
* order to correctly interpret the index file, pick character that
* is outside the range, to cause the reader to abort.
*/
#define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) )
#define CACHE_EXT_TREE 0x54524545 /* "TREE" */
#define CACHE_EXT_RESOLVE_UNDO 0x52455543 /* "REUC" */
#define CACHE_EXT_LINK 0x6c696e6b /* "link" */
#define CACHE_EXT_UNTRACKED 0x554E5452 /* "UNTR" */
#define CACHE_EXT_FSMONITOR 0x46534D4E /* "FSMN" */
#define CACHE_EXT_ENDOFINDEXENTRIES 0x454F4945 /* "EOIE" */
#define CACHE_EXT_INDEXENTRYOFFSETTABLE 0x49454F54 /* "IEOT" */
/* changes that can be kept in $GIT_DIR/index (basically all extensions) */
#define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \
CE_ENTRY_ADDED | CE_ENTRY_REMOVED | CE_ENTRY_CHANGED | \
SPLIT_INDEX_ORDERED | UNTRACKED_CHANGED | FSMONITOR_CHANGED)
/*
* This is an estimate of the pathname length in the index. We use
* this for V4 index files to guess the un-deltafied size of the index
* in memory because of pathname deltafication. This is not required
* for V2/V3 index formats because their pathnames are not compressed.
* If the initial amount of memory set aside is not sufficient, the
* mem pool will allocate extra memory.
*/
#define CACHE_ENTRY_PATH_LENGTH 80
static inline struct cache_entry *mem_pool__ce_alloc(struct mem_pool *mem_pool, size_t len)
{
struct cache_entry *ce;
ce = mem_pool_alloc(mem_pool, cache_entry_size(len));
ce->mem_pool_allocated = 1;
return ce;
}
static inline struct cache_entry *mem_pool__ce_calloc(struct mem_pool *mem_pool, size_t len)
{
struct cache_entry * ce;
ce = mem_pool_calloc(mem_pool, 1, cache_entry_size(len));
ce->mem_pool_allocated = 1;
return ce;
}
static struct mem_pool *find_mem_pool(struct index_state *istate)
{
struct mem_pool **pool_ptr;
if (istate->split_index && istate->split_index->base)
pool_ptr = &istate->split_index->base->ce_mem_pool;
else
pool_ptr = &istate->ce_mem_pool;
if (!*pool_ptr)
mem_pool_init(pool_ptr, 0);
return *pool_ptr;
}
static const char *alternate_index_output;
static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
istate->cache[nr] = ce;
add_name_hash(istate, ce);
}
static void replace_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
struct cache_entry *old = istate->cache[nr];
replace_index_entry_in_base(istate, old, ce);
remove_name_hash(istate, old);
discard_cache_entry(old);
ce->ce_flags &= ~CE_HASHED;
set_index_entry(istate, nr, ce);
ce->ce_flags |= CE_UPDATE_IN_BASE;
mark_fsmonitor_invalid(istate, ce);
istate->cache_changed |= CE_ENTRY_CHANGED;
}
void rename_index_entry_at(struct index_state *istate, int nr, const char *new_name)
{
struct cache_entry *old_entry = istate->cache[nr], *new_entry;
int namelen = strlen(new_name);
new_entry = make_empty_cache_entry(istate, namelen);
copy_cache_entry(new_entry, old_entry);
new_entry->ce_flags &= ~CE_HASHED;
new_entry->ce_namelen = namelen;
new_entry->index = 0;
memcpy(new_entry->name, new_name, namelen + 1);
cache_tree_invalidate_path(istate, old_entry->name);
untracked_cache_remove_from_index(istate, old_entry->name);
remove_index_entry_at(istate, nr);
add_index_entry(istate, new_entry, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
}
void fill_stat_data(struct stat_data *sd, struct stat *st)
{
sd->sd_ctime.sec = (unsigned int)st->st_ctime;
sd->sd_mtime.sec = (unsigned int)st->st_mtime;
sd->sd_ctime.nsec = ST_CTIME_NSEC(*st);
sd->sd_mtime.nsec = ST_MTIME_NSEC(*st);
sd->sd_dev = st->st_dev;
sd->sd_ino = st->st_ino;
sd->sd_uid = st->st_uid;
sd->sd_gid = st->st_gid;
sd->sd_size = st->st_size;
}
int match_stat_data(const struct stat_data *sd, struct stat *st)
{
int changed = 0;
if (sd->sd_mtime.sec != (unsigned int)st->st_mtime)
changed |= MTIME_CHANGED;
if (trust_ctime && check_stat &&
sd->sd_ctime.sec != (unsigned int)st->st_ctime)
changed |= CTIME_CHANGED;
#ifdef USE_NSEC
if (check_stat && sd->sd_mtime.nsec != ST_MTIME_NSEC(*st))
changed |= MTIME_CHANGED;
if (trust_ctime && check_stat &&
sd->sd_ctime.nsec != ST_CTIME_NSEC(*st))
changed |= CTIME_CHANGED;
#endif
if (check_stat) {
if (sd->sd_uid != (unsigned int) st->st_uid ||
sd->sd_gid != (unsigned int) st->st_gid)
changed |= OWNER_CHANGED;
if (sd->sd_ino != (unsigned int) st->st_ino)
changed |= INODE_CHANGED;
}
#ifdef USE_STDEV
/*
* st_dev breaks on network filesystems where different
* clients will have different views of what "device"
* the filesystem is on
*/
if (check_stat && sd->sd_dev != (unsigned int) st->st_dev)
changed |= INODE_CHANGED;
#endif
if (sd->sd_size != (unsigned int) st->st_size)
changed |= DATA_CHANGED;
return changed;
}
/*
* This only updates the "non-critical" parts of the directory
* cache, ie the parts that aren't tracked by GIT, and only used
* to validate the cache.
*/
void fill_stat_cache_info(struct cache_entry *ce, struct stat *st)
{
fill_stat_data(&ce->ce_stat_data, st);
if (assume_unchanged)
ce->ce_flags |= CE_VALID;
if (S_ISREG(st->st_mode)) {
ce_mark_uptodate(ce);
mark_fsmonitor_valid(ce);
}
}
static int ce_compare_data(struct index_state *istate,
const struct cache_entry *ce,
struct stat *st)
{
int match = -1;
int fd = git_open_cloexec(ce->name, O_RDONLY);
if (fd >= 0) {
struct object_id oid;
if (!index_fd(istate, &oid, fd, st, OBJ_BLOB, ce->name, 0))
match = !oideq(&oid, &ce->oid);
/* index_fd() closed the file descriptor already */
}
return match;
}
static int ce_compare_link(const struct cache_entry *ce, size_t expected_size)
{
int match = -1;
void *buffer;
unsigned long size;
enum object_type type;
struct strbuf sb = STRBUF_INIT;
if (strbuf_readlink(&sb, ce->name, expected_size))
return -1;
buffer = read_object_file(&ce->oid, &type, &size);
if (buffer) {
if (size == sb.len)
match = memcmp(buffer, sb.buf, size);
free(buffer);
}
strbuf_release(&sb);
return match;
}
static int ce_compare_gitlink(const struct cache_entry *ce)
{
struct object_id oid;
/*
* We don't actually require that the .git directory
* under GITLINK directory be a valid git directory. It
* might even be missing (in case nobody populated that
* sub-project).
*
* If so, we consider it always to match.
*/
if (resolve_gitlink_ref(ce->name, "HEAD", &oid) < 0)
return 0;
return !oideq(&oid, &ce->oid);
}
static int ce_modified_check_fs(struct index_state *istate,
const struct cache_entry *ce,
struct stat *st)
{
switch (st->st_mode & S_IFMT) {
case S_IFREG:
if (ce_compare_data(istate, ce, st))
return DATA_CHANGED;
break;
case S_IFLNK:
if (ce_compare_link(ce, xsize_t(st->st_size)))
return DATA_CHANGED;
break;
case S_IFDIR:
if (S_ISGITLINK(ce->ce_mode))
return ce_compare_gitlink(ce) ? DATA_CHANGED : 0;
/* else fallthrough */
default:
return TYPE_CHANGED;
}
return 0;
}
static int ce_match_stat_basic(const struct cache_entry *ce, struct stat *st)
{
unsigned int changed = 0;
if (ce->ce_flags & CE_REMOVE)
return MODE_CHANGED | DATA_CHANGED | TYPE_CHANGED;
switch (ce->ce_mode & S_IFMT) {
case S_IFREG:
changed |= !S_ISREG(st->st_mode) ? TYPE_CHANGED : 0;
/* We consider only the owner x bit to be relevant for
* "mode changes"
*/
if (trust_executable_bit &&
(0100 & (ce->ce_mode ^ st->st_mode)))
changed |= MODE_CHANGED;
break;
case S_IFLNK:
if (!S_ISLNK(st->st_mode) &&
(has_symlinks || !S_ISREG(st->st_mode)))
changed |= TYPE_CHANGED;
break;
case S_IFGITLINK:
/* We ignore most of the st_xxx fields for gitlinks */
if (!S_ISDIR(st->st_mode))
changed |= TYPE_CHANGED;
else if (ce_compare_gitlink(ce))
changed |= DATA_CHANGED;
return changed;
default:
BUG("unsupported ce_mode: %o", ce->ce_mode);
}
changed |= match_stat_data(&ce->ce_stat_data, st);
/* Racily smudged entry? */
if (!ce->ce_stat_data.sd_size) {
if (!is_empty_blob_sha1(ce->oid.hash))
changed |= DATA_CHANGED;
}
return changed;
}
static int is_racy_stat(const struct index_state *istate,
const struct stat_data *sd)
{
return (istate->timestamp.sec &&
#ifdef USE_NSEC
/* nanosecond timestamped files can also be racy! */
(istate->timestamp.sec < sd->sd_mtime.sec ||
(istate->timestamp.sec == sd->sd_mtime.sec &&
istate->timestamp.nsec <= sd->sd_mtime.nsec))
#else
istate->timestamp.sec <= sd->sd_mtime.sec
#endif
);
}
int is_racy_timestamp(const struct index_state *istate,
const struct cache_entry *ce)
{
return (!S_ISGITLINK(ce->ce_mode) &&
is_racy_stat(istate, &ce->ce_stat_data));
}
int match_stat_data_racy(const struct index_state *istate,
const struct stat_data *sd, struct stat *st)
{
if (is_racy_stat(istate, sd))
return MTIME_CHANGED;
return match_stat_data(sd, st);
}
int ie_match_stat(struct index_state *istate,
const struct cache_entry *ce, struct stat *st,
unsigned int options)
{
unsigned int changed;
int ignore_valid = options & CE_MATCH_IGNORE_VALID;
int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE;
int assume_racy_is_modified = options & CE_MATCH_RACY_IS_DIRTY;
int ignore_fsmonitor = options & CE_MATCH_IGNORE_FSMONITOR;
if (!ignore_fsmonitor)
refresh_fsmonitor(istate);
/*
* If it's marked as always valid in the index, it's
* valid whatever the checked-out copy says.
*
* skip-worktree has the same effect with higher precedence
*/
if (!ignore_skip_worktree && ce_skip_worktree(ce))
return 0;
if (!ignore_valid && (ce->ce_flags & CE_VALID))
return 0;
if (!ignore_fsmonitor && (ce->ce_flags & CE_FSMONITOR_VALID))
return 0;
/*
* Intent-to-add entries have not been added, so the index entry
* by definition never matches what is in the work tree until it
* actually gets added.
*/
if (ce_intent_to_add(ce))
return DATA_CHANGED | TYPE_CHANGED | MODE_CHANGED;
changed = ce_match_stat_basic(ce, st);
/*
* Within 1 second of this sequence:
* echo xyzzy >file && git-update-index --add file
* running this command:
* echo frotz >file
* would give a falsely clean cache entry. The mtime and
* length match the cache, and other stat fields do not change.
*
* We could detect this at update-index time (the cache entry
* being registered/updated records the same time as "now")
* and delay the return from git-update-index, but that would
* effectively mean we can make at most one commit per second,
* which is not acceptable. Instead, we check cache entries
* whose mtime are the same as the index file timestamp more
* carefully than others.
*/
if (!changed && is_racy_timestamp(istate, ce)) {
if (assume_racy_is_modified)
changed |= DATA_CHANGED;
else
changed |= ce_modified_check_fs(istate, ce, st);
}
return changed;
}
int ie_modified(struct index_state *istate,
const struct cache_entry *ce,
struct stat *st, unsigned int options)
{
int changed, changed_fs;
changed = ie_match_stat(istate, ce, st, options);
if (!changed)
return 0;
/*
* If the mode or type has changed, there's no point in trying
* to refresh the entry - it's not going to match
*/
if (changed & (MODE_CHANGED | TYPE_CHANGED))
return changed;
/*
* Immediately after read-tree or update-index --cacheinfo,
* the length field is zero, as we have never even read the
* lstat(2) information once, and we cannot trust DATA_CHANGED
* returned by ie_match_stat() which in turn was returned by
* ce_match_stat_basic() to signal that the filesize of the
* blob changed. We have to actually go to the filesystem to
* see if the contents match, and if so, should answer "unchanged".
*
* The logic does not apply to gitlinks, as ce_match_stat_basic()
* already has checked the actual HEAD from the filesystem in the
* subproject. If ie_match_stat() already said it is different,
* then we know it is.
*/
if ((changed & DATA_CHANGED) &&
(S_ISGITLINK(ce->ce_mode) || ce->ce_stat_data.sd_size != 0))
return changed;
changed_fs = ce_modified_check_fs(istate, ce, st);
if (changed_fs)
return changed | changed_fs;
return 0;
}
int base_name_compare(const char *name1, int len1, int mode1,
const char *name2, int len2, int mode2)
{
unsigned char c1, c2;
int len = len1 < len2 ? len1 : len2;
int cmp;
cmp = memcmp(name1, name2, len);
if (cmp)
return cmp;
c1 = name1[len];
c2 = name2[len];
if (!c1 && S_ISDIR(mode1))
c1 = '/';
if (!c2 && S_ISDIR(mode2))
c2 = '/';
return (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0;
}
/*
* df_name_compare() is identical to base_name_compare(), except it
* compares conflicting directory/file entries as equal. Note that
* while a directory name compares as equal to a regular file, they
* then individually compare _differently_ to a filename that has
* a dot after the basename (because '\0' < '.' < '/').
*
* This is used by routines that want to traverse the git namespace
* but then handle conflicting entries together when possible.
*/
int df_name_compare(const char *name1, int len1, int mode1,
const char *name2, int len2, int mode2)
{
int len = len1 < len2 ? len1 : len2, cmp;
unsigned char c1, c2;
cmp = memcmp(name1, name2, len);
if (cmp)
return cmp;
/* Directories and files compare equal (same length, same name) */
if (len1 == len2)
return 0;
c1 = name1[len];
if (!c1 && S_ISDIR(mode1))
c1 = '/';
c2 = name2[len];
if (!c2 && S_ISDIR(mode2))
c2 = '/';
if (c1 == '/' && !c2)
return 0;
if (c2 == '/' && !c1)
return 0;
return c1 - c2;
}
int name_compare(const char *name1, size_t len1, const char *name2, size_t len2)
{
size_t min_len = (len1 < len2) ? len1 : len2;
int cmp = memcmp(name1, name2, min_len);
if (cmp)
return cmp;
if (len1 < len2)
return -1;
if (len1 > len2)
return 1;
return 0;
}
int cache_name_stage_compare(const char *name1, int len1, int stage1, const char *name2, int len2, int stage2)
{
int cmp;
cmp = name_compare(name1, len1, name2, len2);
if (cmp)
return cmp;
if (stage1 < stage2)
return -1;
if (stage1 > stage2)
return 1;
return 0;
}
static int index_name_stage_pos(const struct index_state *istate, const char *name, int namelen, int stage)
{
int first, last;
first = 0;
last = istate->cache_nr;
while (last > first) {
int next = (last + first) >> 1;
struct cache_entry *ce = istate->cache[next];
int cmp = cache_name_stage_compare(name, namelen, stage, ce->name, ce_namelen(ce), ce_stage(ce));
if (!cmp)
return next;
if (cmp < 0) {
last = next;
continue;
}
first = next+1;
}
return -first-1;
}
int index_name_pos(const struct index_state *istate, const char *name, int namelen)
{
return index_name_stage_pos(istate, name, namelen, 0);
}
int remove_index_entry_at(struct index_state *istate, int pos)
{
struct cache_entry *ce = istate->cache[pos];
record_resolve_undo(istate, ce);
remove_name_hash(istate, ce);
save_or_free_index_entry(istate, ce);
istate->cache_changed |= CE_ENTRY_REMOVED;
istate->cache_nr--;
if (pos >= istate->cache_nr)
return 0;
MOVE_ARRAY(istate->cache + pos, istate->cache + pos + 1,
istate->cache_nr - pos);
return 1;
}
/*
* Remove all cache entries marked for removal, that is where
* CE_REMOVE is set in ce_flags. This is much more effective than
* calling remove_index_entry_at() for each entry to be removed.
*/
void remove_marked_cache_entries(struct index_state *istate, int invalidate)
{
struct cache_entry **ce_array = istate->cache;
unsigned int i, j;
for (i = j = 0; i < istate->cache_nr; i++) {
if (ce_array[i]->ce_flags & CE_REMOVE) {
if (invalidate) {
cache_tree_invalidate_path(istate,
ce_array[i]->name);
untracked_cache_remove_from_index(istate,
ce_array[i]->name);
}
remove_name_hash(istate, ce_array[i]);
save_or_free_index_entry(istate, ce_array[i]);
}
else
ce_array[j++] = ce_array[i];
}
if (j == istate->cache_nr)
return;
istate->cache_changed |= CE_ENTRY_REMOVED;
istate->cache_nr = j;
}
int remove_file_from_index(struct index_state *istate, const char *path)
{
int pos = index_name_pos(istate, path, strlen(path));
if (pos < 0)
pos = -pos-1;
cache_tree_invalidate_path(istate, path);
untracked_cache_remove_from_index(istate, path);
while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path))
remove_index_entry_at(istate, pos);
return 0;
}
static int compare_name(struct cache_entry *ce, const char *path, int namelen)
{
return namelen != ce_namelen(ce) || memcmp(path, ce->name, namelen);
}
static int index_name_pos_also_unmerged(struct index_state *istate,
const char *path, int namelen)
{
int pos = index_name_pos(istate, path, namelen);
struct cache_entry *ce;
if (pos >= 0)
return pos;
/* maybe unmerged? */
pos = -1 - pos;
if (pos >= istate->cache_nr ||
compare_name((ce = istate->cache[pos]), path, namelen))
return -1;
/* order of preference: stage 2, 1, 3 */
if (ce_stage(ce) == 1 && pos + 1 < istate->cache_nr &&
ce_stage((ce = istate->cache[pos + 1])) == 2 &&
!compare_name(ce, path, namelen))
pos++;
return pos;
}
static int different_name(struct cache_entry *ce, struct cache_entry *alias)
{
int len = ce_namelen(ce);
return ce_namelen(alias) != len || memcmp(ce->name, alias->name, len);
}
/*
* If we add a filename that aliases in the cache, we will use the
* name that we already have - but we don't want to update the same
* alias twice, because that implies that there were actually two
* different files with aliasing names!
*
* So we use the CE_ADDED flag to verify that the alias was an old
* one before we accept it as
*/
static struct cache_entry *create_alias_ce(struct index_state *istate,
struct cache_entry *ce,
struct cache_entry *alias)
{
int len;
struct cache_entry *new_entry;
if (alias->ce_flags & CE_ADDED)
die(_("will not add file alias '%s' ('%s' already exists in index)"),
ce->name, alias->name);
/* Ok, create the new entry using the name of the existing alias */
len = ce_namelen(alias);
new_entry = make_empty_cache_entry(istate, len);
memcpy(new_entry->name, alias->name, len);
copy_cache_entry(new_entry, ce);
save_or_free_index_entry(istate, ce);
return new_entry;
}
void set_object_name_for_intent_to_add_entry(struct cache_entry *ce)
{
struct object_id oid;
if (write_object_file("", 0, blob_type, &oid))
die(_("cannot create an empty blob in the object database"));
oidcpy(&ce->oid, &oid);
}
int add_to_index(struct index_state *istate, const char *path, struct stat *st, int flags)
{
int namelen, was_same;
mode_t st_mode = st->st_mode;
struct cache_entry *ce, *alias = NULL;
unsigned ce_option = CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE|CE_MATCH_RACY_IS_DIRTY;
int verbose = flags & (ADD_CACHE_VERBOSE | ADD_CACHE_PRETEND);
int pretend = flags & ADD_CACHE_PRETEND;
int intent_only = flags & ADD_CACHE_INTENT;
int add_option = (ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE|
(intent_only ? ADD_CACHE_NEW_ONLY : 0));
int hash_flags = HASH_WRITE_OBJECT;
struct object_id oid;
if (flags & ADD_CACHE_RENORMALIZE)
hash_flags |= HASH_RENORMALIZE;
if (!S_ISREG(st_mode) && !S_ISLNK(st_mode) && !S_ISDIR(st_mode))
return error(_("%s: can only add regular files, symbolic links or git-directories"), path);
namelen = strlen(path);
if (S_ISDIR(st_mode)) {
if (resolve_gitlink_ref(path, "HEAD", &oid) < 0)
return error(_("'%s' does not have a commit checked out"), path);
while (namelen && path[namelen-1] == '/')
namelen--;
}
ce = make_empty_cache_entry(istate, namelen);
memcpy(ce->name, path, namelen);
ce->ce_namelen = namelen;
if (!intent_only)
fill_stat_cache_info(ce, st);
else
ce->ce_flags |= CE_INTENT_TO_ADD;
if (trust_executable_bit && has_symlinks) {
ce->ce_mode = create_ce_mode(st_mode);
} else {
/* If there is an existing entry, pick the mode bits and type
* from it, otherwise assume unexecutable regular file.
*/
struct cache_entry *ent;
int pos = index_name_pos_also_unmerged(istate, path, namelen);
ent = (0 <= pos) ? istate->cache[pos] : NULL;
ce->ce_mode = ce_mode_from_stat(ent, st_mode);
}
/* When core.ignorecase=true, determine if a directory of the same name but differing
* case already exists within the Git repository. If it does, ensure the directory
* case of the file being added to the repository matches (is folded into) the existing
* entry's directory case.
*/
if (ignore_case) {
adjust_dirname_case(istate, ce->name);
}
if (!(flags & ADD_CACHE_RENORMALIZE)) {
alias = index_file_exists(istate, ce->name,
ce_namelen(ce), ignore_case);
if (alias &&
!ce_stage(alias) &&
!ie_match_stat(istate, alias, st, ce_option)) {
/* Nothing changed, really */
if (!S_ISGITLINK(alias->ce_mode))
ce_mark_uptodate(alias);
alias->ce_flags |= CE_ADDED;
discard_cache_entry(ce);
return 0;
}
}
if (!intent_only) {
if (index_path(istate, &ce->oid, path, st, hash_flags)) {
discard_cache_entry(ce);
return error(_("unable to index file '%s'"), path);
}
} else
set_object_name_for_intent_to_add_entry(ce);
if (ignore_case && alias && different_name(ce, alias))
ce = create_alias_ce(istate, ce, alias);
ce->ce_flags |= CE_ADDED;
/* It was suspected to be racily clean, but it turns out to be Ok */
was_same = (alias &&
!ce_stage(alias) &&
oideq(&alias->oid, &ce->oid) &&
ce->ce_mode == alias->ce_mode);
if (pretend)
discard_cache_entry(ce);
else if (add_index_entry(istate, ce, add_option)) {
discard_cache_entry(ce);
return error(_("unable to add '%s' to index"), path);
}
if (verbose && !was_same)
printf("add '%s'\n", path);
return 0;
}
int add_file_to_index(struct index_state *istate, const char *path, int flags)
{
struct stat st;
if (lstat(path, &st))
die_errno(_("unable to stat '%s'"), path);
return add_to_index(istate, path, &st, flags);
}
struct cache_entry *make_empty_cache_entry(struct index_state *istate, size_t len)
{
return mem_pool__ce_calloc(find_mem_pool(istate), len);
}
struct cache_entry *make_empty_transient_cache_entry(size_t len)
{
return xcalloc(1, cache_entry_size(len));
}
struct cache_entry *make_cache_entry(struct index_state *istate,
unsigned int mode,
const struct object_id *oid,
const char *path,
int stage,
unsigned int refresh_options)
{
struct cache_entry *ce, *ret;
int len;
if (!verify_path(path, mode)) {
error(_("invalid path '%s'"), path);
return NULL;
}
len = strlen(path);
ce = make_empty_cache_entry(istate, len);
oidcpy(&ce->oid, oid);
memcpy(ce->name, path, len);
ce->ce_flags = create_ce_flags(stage);
ce->ce_namelen = len;
ce->ce_mode = create_ce_mode(mode);
ret = refresh_cache_entry(istate, ce, refresh_options);
if (ret != ce)
discard_cache_entry(ce);
return ret;
}
struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct object_id *oid,
const char *path, int stage)
{
struct cache_entry *ce;
int len;
if (!verify_path(path, mode)) {
error(_("invalid path '%s'"), path);
return NULL;
}
len = strlen(path);
ce = make_empty_transient_cache_entry(len);
oidcpy(&ce->oid, oid);
memcpy(ce->name, path, len);
ce->ce_flags = create_ce_flags(stage);
ce->ce_namelen = len;
ce->ce_mode = create_ce_mode(mode);
return ce;
}
/*
* Chmod an index entry with either +x or -x.
*
* Returns -1 if the chmod for the particular cache entry failed (if it's
* not a regular file), -2 if an invalid flip argument is passed in, 0
* otherwise.
*/
int chmod_index_entry(struct index_state *istate, struct cache_entry *ce,
char flip)
{
if (!S_ISREG(ce->ce_mode))
return -1;
switch (flip) {
case '+':
ce->ce_mode |= 0111;
break;
case '-':
ce->ce_mode &= ~0111;
break;
default:
return -2;
}
cache_tree_invalidate_path(istate, ce->name);
ce->ce_flags |= CE_UPDATE_IN_BASE;
mark_fsmonitor_invalid(istate, ce);
istate->cache_changed |= CE_ENTRY_CHANGED;
return 0;
}
int ce_same_name(const struct cache_entry *a, const struct cache_entry *b)
{
int len = ce_namelen(a);
return ce_namelen(b) == len && !memcmp(a->name, b->name, len);
}
/*
* We fundamentally don't like some paths: we don't want
* dot or dot-dot anywhere, and for obvious reasons don't
* want to recurse into ".git" either.
*
* Also, we don't want double slashes or slashes at the
* end that can make pathnames ambiguous.
*/
static int verify_dotfile(const char *rest, unsigned mode)
{
/*
* The first character was '.', but that
* has already been discarded, we now test
* the rest.
*/
/* "." is not allowed */
if (*rest == '\0' || is_dir_sep(*rest))
return 0;
switch (*rest) {
/*
* ".git" followed by NUL or slash is bad. Note that we match
* case-insensitively here, even if ignore_case is not set.
* This outlaws ".GIT" everywhere out of an abundance of caution,
* since there's really no good reason to allow it.
*
* Once we've seen ".git", we can also find ".gitmodules", etc (also
* case-insensitively).
*/
case 'g':
case 'G':
if (rest[1] != 'i' && rest[1] != 'I')
break;
if (rest[2] != 't' && rest[2] != 'T')
break;
if (rest[3] == '\0' || is_dir_sep(rest[3]))
return 0;
if (S_ISLNK(mode)) {
rest += 3;
if (skip_iprefix(rest, "modules", &rest) &&
(*rest == '\0' || is_dir_sep(*rest)))
return 0;
}
break;
case '.':
if (rest[1] == '\0' || is_dir_sep(rest[1]))
return 0;
}
return 1;
}
int verify_path(const char *path, unsigned mode)
{
char c;
if (has_dos_drive_prefix(path))
return 0;
goto inside;
for (;;) {
if (!c)
return 1;
if (is_dir_sep(c)) {
inside:
if (protect_hfs) {
if (is_hfs_dotgit(path))
return 0;
if (S_ISLNK(mode)) {
if (is_hfs_dotgitmodules(path))
return 0;
}
}
if (protect_ntfs) {
if (is_ntfs_dotgit(path))
return 0;
if (S_ISLNK(mode)) {
if (is_ntfs_dotgitmodules(path))
return 0;
}
}
c = *path++;
if ((c == '.' && !verify_dotfile(path, mode)) ||
is_dir_sep(c) || c == '\0')
return 0;
}
c = *path++;
}
}
/*
* Do we have another file that has the beginning components being a
* proper superset of the name we're trying to add?
*/
static int has_file_name(struct index_state *istate,
const struct cache_entry *ce, int pos, int ok_to_replace)
{
int retval = 0;
int len = ce_namelen(ce);
int stage = ce_stage(ce);
const char *name = ce->name;
while (pos < istate->cache_nr) {
struct cache_entry *p = istate->cache[pos++];
if (len >= ce_namelen(p))
break;
if (memcmp(name, p->name, len))
break;
if (ce_stage(p) != stage)
continue;
if (p->name[len] != '/')
continue;
if (p->ce_flags & CE_REMOVE)
continue;
retval = -1;
if (!ok_to_replace)
break;
remove_index_entry_at(istate, --pos);
}
return retval;
}
/*
* Like strcmp(), but also return the offset of the first change.
* If strings are equal, return the length.
*/
int strcmp_offset(const char *s1, const char *s2, size_t *first_change)
{
size_t k;
if (!first_change)
return strcmp(s1, s2);
for (k = 0; s1[k] == s2[k]; k++)
if (s1[k] == '\0')
break;
*first_change = k;
return (unsigned char)s1[k] - (unsigned char)s2[k];
}
/*
* Do we have another file with a pathname that is a proper
* subset of the name we're trying to add?
*
* That is, is there another file in the index with a path
* that matches a sub-directory in the given entry?
*/
static int has_dir_name(struct index_state *istate,
const struct cache_entry *ce, int pos, int ok_to_replace)
{
int retval = 0;
int stage = ce_stage(ce);
const char *name = ce->name;
const char *slash = name + ce_namelen(ce);
size_t len_eq_last;
int cmp_last = 0;
/*
* We are frequently called during an iteration on a sorted
* list of pathnames and while building a new index. Therefore,
* there is a high probability that this entry will eventually
* be appended to the index, rather than inserted in the middle.
* If we can confirm that, we can avoid binary searches on the
* components of the pathname.
*
* Compare the entry's full path with the last path in the index.
*/
if (istate->cache_nr > 0) {
cmp_last = strcmp_offset(name,
istate->cache[istate->cache_nr - 1]->name,
&len_eq_last);
if (cmp_last > 0) {
if (len_eq_last == 0) {
/*
* The entry sorts AFTER the last one in the
* index and their paths have no common prefix,
* so there cannot be a F/D conflict.
*/
return retval;
} else {
/*
* The entry sorts AFTER the last one in the
* index, but has a common prefix. Fall through
* to the loop below to disect the entry's path
* and see where the difference is.
*/
}
} else if (cmp_last == 0) {
/*
* The entry exactly matches the last one in the
* index, but because of multiple stage and CE_REMOVE
* items, we fall through and let the regular search
* code handle it.
*/
}
}
for (;;) {
size_t len;
for (;;) {
if (*--slash == '/')
break;
if (slash <= ce->name)
return retval;
}
len = slash - name;
if (cmp_last > 0) {
/*
* (len + 1) is a directory boundary (including
* the trailing slash). And since the loop is
* decrementing "slash", the first iteration is
* the longest directory prefix; subsequent
* iterations consider parent directories.
*/
if (len + 1 <= len_eq_last) {
/*
* The directory prefix (including the trailing
* slash) also appears as a prefix in the last
* entry, so the remainder cannot collide (because
* strcmp said the whole path was greater).
*
* EQ: last: xxx/A
* this: xxx/B
*
* LT: last: xxx/file_A
* this: xxx/file_B
*/
return retval;
}
if (len > len_eq_last) {
/*
* This part of the directory prefix (excluding
* the trailing slash) is longer than the known
* equal portions, so this sub-directory cannot
* collide with a file.
*
* GT: last: xxxA
* this: xxxB/file
*/
return retval;
}
if (istate->cache_nr > 0 &&
ce_namelen(istate->cache[istate->cache_nr - 1]) > len) {
/*
* The directory prefix lines up with part of
* a longer file or directory name, but sorts
* after it, so this sub-directory cannot
* collide with a file.
*
* last: xxx/yy-file (because '-' sorts before '/')
* this: xxx/yy/abc
*/
return retval;
}
/*
* This is a possible collision. Fall through and
* let the regular search code handle it.
*
* last: xxx
* this: xxx/file
*/
}
pos = index_name_stage_pos(istate, name, len, stage);
if (pos >= 0) {
/*
* Found one, but not so fast. This could
* be a marker that says "I was here, but
* I am being removed". Such an entry is
* not a part of the resulting tree, and
* it is Ok to have a directory at the same
* path.
*/
if (!(istate->cache[pos]->ce_flags & CE_REMOVE)) {
retval = -1;
if (!ok_to_replace)
break;
remove_index_entry_at(istate, pos);
continue;
}
}
else
pos = -pos-1;
/*
* Trivial optimization: if we find an entry that
* already matches the sub-directory, then we know
* we're ok, and we can exit.
*/
while (pos < istate->cache_nr) {
struct cache_entry *p = istate->cache[pos];
if ((ce_namelen(p) <= len) ||
(p->name[len] != '/') ||
memcmp(p->name, name, len))
break; /* not our subdirectory */
if (ce_stage(p) == stage && !(p->ce_flags & CE_REMOVE))
/*
* p is at the same stage as our entry, and
* is a subdirectory of what we are looking
* at, so we cannot have conflicts at our
* level or anything shorter.
*/
return retval;
pos++;
}
}
return retval;
}
/* We may be in a situation where we already have path/file and path
* is being added, or we already have path and path/file is being
* added. Either one would result in a nonsense tree that has path
* twice when git-write-tree tries to write it out. Prevent it.
*
* If ok-to-replace is specified, we remove the conflicting entries
* from the cache so the caller should recompute the insert position.
* When this happens, we return non-zero.
*/
static int check_file_directory_conflict(struct index_state *istate,
const struct cache_entry *ce,
int pos, int ok_to_replace)
{
int retval;
/*
* When ce is an "I am going away" entry, we allow it to be added
*/
if (ce->ce_flags & CE_REMOVE)
return 0;
/*
* We check if the path is a sub-path of a subsequent pathname
* first, since removing those will not change the position
* in the array.
*/
retval = has_file_name(istate, ce, pos, ok_to_replace);
/*
* Then check if the path might have a clashing sub-directory
* before it.
*/
return retval + has_dir_name(istate, ce, pos, ok_to_replace);
}
static int add_index_entry_with_check(struct index_state *istate, struct cache_entry *ce, int option)
{
int pos;
int ok_to_add = option & ADD_CACHE_OK_TO_ADD;
int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE;
int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK;
int new_only = option & ADD_CACHE_NEW_ONLY;
if (!(option & ADD_CACHE_KEEP_CACHE_TREE))
cache_tree_invalidate_path(istate, ce->name);
/*
* If this entry's path sorts after the last entry in the index,
* we can avoid searching for it.
*/
if (istate->cache_nr > 0 &&
strcmp(ce->name, istate->cache[istate->cache_nr - 1]->name) > 0)
pos = -istate->cache_nr - 1;
else
pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
/* existing match? Just replace it. */
if (pos >= 0) {
if (!new_only)
replace_index_entry(istate, pos, ce);
return 0;
}
pos = -pos-1;
if (!(option & ADD_CACHE_KEEP_CACHE_TREE))
untracked_cache_add_to_index(istate, ce->name);
/*
* Inserting a merged entry ("stage 0") into the index
* will always replace all non-merged entries..
*/
if (pos < istate->cache_nr && ce_stage(ce) == 0) {
while (ce_same_name(istate->cache[pos], ce)) {
ok_to_add = 1;
if (!remove_index_entry_at(istate, pos))
break;
}
}
if (!ok_to_add)
return -1;
if (!verify_path(ce->name, ce->ce_mode))
return error(_("invalid path '%s'"), ce->name);
if (!skip_df_check &&
check_file_directory_conflict(istate, ce, pos, ok_to_replace)) {
if (!ok_to_replace)
return error(_("'%s' appears as both a file and as a directory"),
ce->name);
pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
pos = -pos-1;
}
return pos + 1;
}
int add_index_entry(struct index_state *istate, struct cache_entry *ce, int option)
{
int pos;
if (option & ADD_CACHE_JUST_APPEND)
pos = istate->cache_nr;
else {
int ret;
ret = add_index_entry_with_check(istate, ce, option);
if (ret <= 0)
return ret;
pos = ret - 1;
}
/* Make sure the array is big enough .. */
ALLOC_GROW(istate->cache, istate->cache_nr + 1, istate->cache_alloc);
/* Add it in.. */
istate->cache_nr++;
if (istate->cache_nr > pos + 1)
MOVE_ARRAY(istate->cache + pos + 1, istate->cache + pos,
istate->cache_nr - pos - 1);
set_index_entry(istate, pos, ce);
istate->cache_changed |= CE_ENTRY_ADDED;
return 0;
}
/*
* "refresh" does not calculate a new sha1 file or bring the
* cache up-to-date for mode/content changes. But what it
* _does_ do is to "re-match" the stat information of a file
* with the cache, so that you can refresh the cache for a
* file that hasn't been changed but where the stat entry is
* out of date.
*
* For example, you'd want to do this after doing a "git-read-tree",
* to link up the stat cache details with the proper files.
*/
static struct cache_entry *refresh_cache_ent(struct index_state *istate,
struct cache_entry *ce,
unsigned int options, int *err,
int *changed_ret)
{
struct stat st;
struct cache_entry *updated;
int changed;
int refresh = options & CE_MATCH_REFRESH;
int ignore_valid = options & CE_MATCH_IGNORE_VALID;
int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE;
int ignore_missing = options & CE_MATCH_IGNORE_MISSING;
int ignore_fsmonitor = options & CE_MATCH_IGNORE_FSMONITOR;
if (!refresh || ce_uptodate(ce))
return ce;
if (!ignore_fsmonitor)
refresh_fsmonitor(istate);
/*
* CE_VALID or CE_SKIP_WORKTREE means the user promised us
* that the change to the work tree does not matter and told
* us not to worry.
*/
if (!ignore_skip_worktree && ce_skip_worktree(ce)) {
ce_mark_uptodate(ce);
return ce;
}
if (!ignore_valid && (ce->ce_flags & CE_VALID)) {
ce_mark_uptodate(ce);
return ce;
}
if (!ignore_fsmonitor && (ce->ce_flags & CE_FSMONITOR_VALID)) {
ce_mark_uptodate(ce);
return ce;
}
if (has_symlink_leading_path(ce->name, ce_namelen(ce))) {
if (ignore_missing)
return ce;
if (err)
*err = ENOENT;
return NULL;
}
if (lstat(ce->name, &st) < 0) {
if (ignore_missing && errno == ENOENT)
return ce;
if (err)
*err = errno;
return NULL;
}
changed = ie_match_stat(istate, ce, &st, options);
if (changed_ret)
*changed_ret = changed;
if (!changed) {
/*
* The path is unchanged. If we were told to ignore
* valid bit, then we did the actual stat check and
* found that the entry is unmodified. If the entry
* is not marked VALID, this is the place to mark it
* valid again, under "assume unchanged" mode.
*/
if (ignore_valid && assume_unchanged &&
!(ce->ce_flags & CE_VALID))
; /* mark this one VALID again */
else {
/*
* We do not mark the index itself "modified"
* because CE_UPTODATE flag is in-core only;
* we are not going to write this change out.
*/
if (!S_ISGITLINK(ce->ce_mode)) {
ce_mark_uptodate(ce);
mark_fsmonitor_valid(ce);
}
return ce;
}
}
if (ie_modified(istate, ce, &st, options)) {
if (err)
*err = EINVAL;
return NULL;
}
updated = make_empty_cache_entry(istate, ce_namelen(ce));
copy_cache_entry(updated, ce);
memcpy(updated->name, ce->name, ce->ce_namelen + 1);
fill_stat_cache_info(updated, &st);
/*
* If ignore_valid is not set, we should leave CE_VALID bit
* alone. Otherwise, paths marked with --no-assume-unchanged
* (i.e. things to be edited) will reacquire CE_VALID bit
* automatically, which is not really what we want.
*/
if (!ignore_valid && assume_unchanged &&
!(ce->ce_flags & CE_VALID))
updated->ce_flags &= ~CE_VALID;
/* istate->cache_changed is updated in the caller */
return updated;
}
static void show_file(const char * fmt, const char * name, int in_porcelain,
int * first, const char *header_msg)
{
if (in_porcelain && *first && header_msg) {
printf("%s\n", header_msg);
*first = 0;
}
printf(fmt, name);
}
int refresh_index(struct index_state *istate, unsigned int flags,
const struct pathspec *pathspec,
char *seen, const char *header_msg)
{
int i;
int has_errors = 0;
int really = (flags & REFRESH_REALLY) != 0;
int allow_unmerged = (flags & REFRESH_UNMERGED) != 0;
int quiet = (flags & REFRESH_QUIET) != 0;
int not_new = (flags & REFRESH_IGNORE_MISSING) != 0;
int ignore_submodules = (flags & REFRESH_IGNORE_SUBMODULES) != 0;
int first = 1;
int in_porcelain = (flags & REFRESH_IN_PORCELAIN);
unsigned int options = (CE_MATCH_REFRESH |
(really ? CE_MATCH_IGNORE_VALID : 0) |
(not_new ? CE_MATCH_IGNORE_MISSING : 0));
const char *modified_fmt;
const char *deleted_fmt;
const char *typechange_fmt;
const char *added_fmt;
const char *unmerged_fmt;
struct progress *progress = NULL;
if (flags & REFRESH_PROGRESS && isatty(2))
progress = start_delayed_progress(_("Refresh index"),
istate->cache_nr);
trace_performance_enter();
modified_fmt = in_porcelain ? "M\t%s\n" : "%s: needs update\n";
deleted_fmt = in_porcelain ? "D\t%s\n" : "%s: needs update\n";
typechange_fmt = in_porcelain ? "T\t%s\n" : "%s: needs update\n";
added_fmt = in_porcelain ? "A\t%s\n" : "%s: needs update\n";
unmerged_fmt = in_porcelain ? "U\t%s\n" : "%s: needs merge\n";
/*
* Use the multi-threaded preload_index() to refresh most of the
* cache entries quickly then in the single threaded loop below,
* we only have to do the special cases that are left.
*/
preload_index(istate, pathspec, 0);
for (i = 0; i < istate->cache_nr; i++) {
struct cache_entry *ce, *new_entry;
int cache_errno = 0;
int changed = 0;
int filtered = 0;
ce = istate->cache[i];
if (ignore_submodules && S_ISGITLINK(ce->ce_mode))
continue;
if (pathspec && !ce_path_match(istate, ce, pathspec, seen))
filtered = 1;
if (ce_stage(ce)) {
while ((i < istate->cache_nr) &&
! strcmp(istate->cache[i]->name, ce->name))
i++;
i--;
if (allow_unmerged)
continue;
if (!filtered)
show_file(unmerged_fmt, ce->name, in_porcelain,
&first, header_msg);
has_errors = 1;
continue;
}
if (filtered)
continue;
new_entry = refresh_cache_ent(istate, ce, options, &cache_errno, &changed);
if (new_entry == ce)
continue;
if (progress)
display_progress(progress, i);
if (!new_entry) {
const char *fmt;
if (really && cache_errno == EINVAL) {
/* If we are doing --really-refresh that
* means the index is not valid anymore.
*/
ce->ce_flags &= ~CE_VALID;
ce->ce_flags |= CE_UPDATE_IN_BASE;
mark_fsmonitor_invalid(istate, ce);
istate->cache_changed |= CE_ENTRY_CHANGED;
}
if (quiet)
continue;
if (cache_errno == ENOENT)
fmt = deleted_fmt;
else if (ce_intent_to_add(ce))
fmt = added_fmt; /* must be before other checks */
else if (changed & TYPE_CHANGED)
fmt = typechange_fmt;
else
fmt = modified_fmt;
show_file(fmt,
ce->name, in_porcelain, &first, header_msg);
has_errors = 1;
continue;
}
replace_index_entry(istate, i, new_entry);
}
if (progress) {
display_progress(progress, istate->cache_nr);
stop_progress(&progress);
}
trace_performance_leave("refresh index");
return has_errors;
}
struct cache_entry *refresh_cache_entry(struct index_state *istate,
struct cache_entry *ce,
unsigned int options)
{
return refresh_cache_ent(istate, ce, options, NULL, NULL);
}
/*****************************************************************
* Index File I/O
*****************************************************************/
#define INDEX_FORMAT_DEFAULT 3
static unsigned int get_index_format_default(void)
{
char *envversion = getenv("GIT_INDEX_VERSION");
char *endp;
int value;
unsigned int version = INDEX_FORMAT_DEFAULT;
if (!envversion) {
if (!git_config_get_int("index.version", &value))
version = value;
if (version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < version) {
warning(_("index.version set, but the value is invalid.\n"
"Using version %i"), INDEX_FORMAT_DEFAULT);
return INDEX_FORMAT_DEFAULT;
}
return version;
}
version = strtoul(envversion, &endp, 10);
if (*endp ||
version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < version) {
warning(_("GIT_INDEX_VERSION set, but the value is invalid.\n"
"Using version %i"), INDEX_FORMAT_DEFAULT);
version = INDEX_FORMAT_DEFAULT;
}
return version;
}
/*
* dev/ino/uid/gid/size are also just tracked to the low 32 bits
* Again - this is just a (very strong in practice) heuristic that
* the inode hasn't changed.
*
* We save the fields in big-endian order to allow using the
* index file over NFS transparently.
*/
struct ondisk_cache_entry {
struct cache_time ctime;
struct cache_time mtime;
uint32_t dev;
uint32_t ino;
uint32_t mode;
uint32_t uid;
uint32_t gid;
uint32_t size;
/*
* unsigned char hash[hashsz];
* uint16_t flags;
* if (flags & CE_EXTENDED)
* uint16_t flags2;
*/
unsigned char data[GIT_MAX_RAWSZ + 2 * sizeof(uint16_t)];
char name[FLEX_ARRAY];
};
/* These are only used for v3 or lower */
#define align_padding_size(size, len) ((size + (len) + 8) & ~7) - (size + len)
#define align_flex_name(STRUCT,len) ((offsetof(struct STRUCT,data) + (len) + 8) & ~7)
#define ondisk_cache_entry_size(len) align_flex_name(ondisk_cache_entry,len)
#define ondisk_data_size(flags, len) (the_hash_algo->rawsz + \
((flags & CE_EXTENDED) ? 2 : 1) * sizeof(uint16_t) + len)
#define ondisk_data_size_max(len) (ondisk_data_size(CE_EXTENDED, len))
#define ondisk_ce_size(ce) (ondisk_cache_entry_size(ondisk_data_size((ce)->ce_flags, ce_namelen(ce))))
/* Allow fsck to force verification of the index checksum. */
int verify_index_checksum;
/* Allow fsck to force verification of the cache entry order. */
int verify_ce_order;
static int verify_hdr(const struct cache_header *hdr, unsigned long size)
{
git_hash_ctx c;
unsigned char hash[GIT_MAX_RAWSZ];
int hdr_version;
if (hdr->hdr_signature != htonl(CACHE_SIGNATURE))
return error(_("bad signature 0x%08x"), hdr->hdr_signature);
hdr_version = ntohl(hdr->hdr_version);
if (hdr_version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < hdr_version)
return error(_("bad index version %d"), hdr_version);
if (!verify_index_checksum)
return 0;
the_hash_algo->init_fn(&c);
the_hash_algo->update_fn(&c, hdr, size - the_hash_algo->rawsz);
the_hash_algo->final_fn(hash, &c);
if (!hasheq(hash, (unsigned char *)hdr + size - the_hash_algo->rawsz))
return error(_("bad index file sha1 signature"));
return 0;
}
static int read_index_extension(struct index_state *istate,
const char *ext, const char *data, unsigned long sz)
{
switch (CACHE_EXT(ext)) {
case CACHE_EXT_TREE:
istate->cache_tree = cache_tree_read(data, sz);
break;
case CACHE_EXT_RESOLVE_UNDO:
istate->resolve_undo = resolve_undo_read(data, sz);
break;
case CACHE_EXT_LINK:
if (read_link_extension(istate, data, sz))
return -1;
break;
case CACHE_EXT_UNTRACKED:
istate->untracked = read_untracked_extension(data, sz);
break;
case CACHE_EXT_FSMONITOR:
read_fsmonitor_extension(istate, data, sz);
break;
case CACHE_EXT_ENDOFINDEXENTRIES:
case CACHE_EXT_INDEXENTRYOFFSETTABLE:
/* already handled in do_read_index() */
break;
default:
if (*ext < 'A' || 'Z' < *ext)
return error(_("index uses %.4s extension, which we do not understand"),
ext);
fprintf_ln(stderr, _("ignoring %.4s extension"), ext);
break;
}
return 0;
}
static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
unsigned int version,
struct ondisk_cache_entry *ondisk,
unsigned long *ent_size,
const struct cache_entry *previous_ce)
{
struct cache_entry *ce;
size_t len;
const char *name;
const unsigned hashsz = the_hash_algo->rawsz;
const uint16_t *flagsp = (const uint16_t *)(ondisk->data + hashsz);
unsigned int flags;
size_t copy_len = 0;
/*
* Adjacent cache entries tend to share the leading paths, so it makes
* sense to only store the differences in later entries. In the v4
* on-disk format of the index, each on-disk cache entry stores the
* number of bytes to be stripped from the end of the previous name,
* and the bytes to append to the result, to come up with its name.
*/
int expand_name_field = version == 4;
/* On-disk flags are just 16 bits */
flags = get_be16(flagsp);
len = flags & CE_NAMEMASK;
if (flags & CE_EXTENDED) {
int extended_flags;
extended_flags = get_be16(flagsp + 1) << 16;
/* We do not yet understand any bit out of CE_EXTENDED_FLAGS */
if (extended_flags & ~CE_EXTENDED_FLAGS)
die(_("unknown index entry format 0x%08x"), extended_flags);
flags |= extended_flags;
name = (const char *)(flagsp + 2);
}
else
name = (const char *)(flagsp + 1);
if (expand_name_field) {
const unsigned char *cp = (const unsigned char *)name;
size_t strip_len, previous_len;
/* If we're at the begining of a block, ignore the previous name */
strip_len = decode_varint(&cp);
if (previous_ce) {
previous_len = previous_ce->ce_namelen;
if (previous_len < strip_len)
die(_("malformed name field in the index, near path '%s'"),
previous_ce->name);
copy_len = previous_len - strip_len;
}
name = (const char *)cp;
}
if (len == CE_NAMEMASK) {
len = strlen(name);
if (expand_name_field)
len += copy_len;
}
ce = mem_pool__ce_alloc(ce_mem_pool, len);
ce->ce_stat_data.sd_ctime.sec = get_be32(&ondisk->ctime.sec);
ce->ce_stat_data.sd_mtime.sec = get_be32(&ondisk->mtime.sec);
ce->ce_stat_data.sd_ctime.nsec = get_be32(&ondisk->ctime.nsec);
ce->ce_stat_data.sd_mtime.nsec = get_be32(&ondisk->mtime.nsec);
ce->ce_stat_data.sd_dev = get_be32(&ondisk->dev);
ce->ce_stat_data.sd_ino = get_be32(&ondisk->ino);
ce->ce_mode = get_be32(&ondisk->mode);
ce->ce_stat_data.sd_uid = get_be32(&ondisk->uid);
ce->ce_stat_data.sd_gid = get_be32(&ondisk->gid);
ce->ce_stat_data.sd_size = get_be32(&ondisk->size);
ce->ce_flags = flags & ~CE_NAMEMASK;
ce->ce_namelen = len;
ce->index = 0;
hashcpy(ce->oid.hash, ondisk->data);
memcpy(ce->name, name, len);
ce->name[len] = '\0';
if (expand_name_field) {
if (copy_len)
memcpy(ce->name, previous_ce->name, copy_len);
memcpy(ce->name + copy_len, name, len + 1 - copy_len);
*ent_size = (name - ((char *)ondisk)) + len + 1 - copy_len;
} else {
memcpy(ce->name, name, len + 1);
*ent_size = ondisk_ce_size(ce);
}
return ce;
}
static void check_ce_order(struct index_state *istate)
{
unsigned int i;
if (!verify_ce_order)
return;
for (i = 1; i < istate->cache_nr; i++) {
struct cache_entry *ce = istate->cache[i - 1];
struct cache_entry *next_ce = istate->cache[i];
int name_compare = strcmp(ce->name, next_ce->name);
if (0 < name_compare)
die(_("unordered stage entries in index"));
if (!name_compare) {
if (!ce_stage(ce))
die(_("multiple stage entries for merged file '%s'"),
ce->name);
if (ce_stage(ce) > ce_stage(next_ce))
die(_("unordered stage entries for '%s'"),
ce->name);
}
}
}
static void tweak_untracked_cache(struct index_state *istate)
{
switch (git_config_get_untracked_cache()) {
case -1: /* keep: do nothing */
break;
case 0: /* false */
remove_untracked_cache(istate);
break;
case 1: /* true */
add_untracked_cache(istate);
break;
default: /* unknown value: do nothing */
break;
}
}
static void tweak_split_index(struct index_state *istate)
{
switch (git_config_get_split_index()) {
case -1: /* unset: do nothing */
break;
case 0: /* false */
remove_split_index(istate);
break;
case 1: /* true */
add_split_index(istate);
break;
default: /* unknown value: do nothing */
break;
}
}
static void post_read_index_from(struct index_state *istate)
{
check_ce_order(istate);
tweak_untracked_cache(istate);
tweak_split_index(istate);
tweak_fsmonitor(istate);
}
static size_t estimate_cache_size_from_compressed(unsigned int entries)
{
return entries * (sizeof(struct cache_entry) + CACHE_ENTRY_PATH_LENGTH);
}
static size_t estimate_cache_size(size_t ondisk_size, unsigned int entries)
{
long per_entry = sizeof(struct cache_entry) - sizeof(struct ondisk_cache_entry);
/*
* Account for potential alignment differences.
*/
per_entry += align_padding_size(sizeof(struct cache_entry), -sizeof(struct ondisk_cache_entry));
return ondisk_size + entries * per_entry;
}
struct index_entry_offset
{
/* starting byte offset into index file, count of index entries in this block */
int offset, nr;
};
struct index_entry_offset_table
{
int nr;
struct index_entry_offset entries[FLEX_ARRAY];
};
static struct index_entry_offset_table *read_ieot_extension(const char *mmap, size_t mmap_size, size_t offset);
static void write_ieot_extension(struct strbuf *sb, struct index_entry_offset_table *ieot);
static size_t read_eoie_extension(const char *mmap, size_t mmap_size);
static void write_eoie_extension(struct strbuf *sb, git_hash_ctx *eoie_context, size_t offset);
struct load_index_extensions
{
pthread_t pthread;
struct index_state *istate;
const char *mmap;
size_t mmap_size;
unsigned long src_offset;
};
static void *load_index_extensions(void *_data)
{
struct load_index_extensions *p = _data;
unsigned long src_offset = p->src_offset;
while (src_offset <= p->mmap_size - the_hash_algo->rawsz - 8) {
/* After an array of active_nr index entries,
* there can be arbitrary number of extended
* sections, each of which is prefixed with
* extension name (4-byte) and section length
* in 4-byte network byte order.
*/
uint32_t extsize = get_be32(p->mmap + src_offset + 4);
if (read_index_extension(p->istate,
p->mmap + src_offset,
p->mmap + src_offset + 8,
extsize) < 0) {
munmap((void *)p->mmap, p->mmap_size);
die(_("index file corrupt"));
}
src_offset += 8;
src_offset += extsize;
}
return NULL;
}
/*
* A helper function that will load the specified range of cache entries
* from the memory mapped file and add them to the given index.
*/
static unsigned long load_cache_entry_block(struct index_state *istate,
struct mem_pool *ce_mem_pool, int offset, int nr, const char *mmap,
unsigned long start_offset, const struct cache_entry *previous_ce)
{
int i;
unsigned long src_offset = start_offset;
for (i = offset; i < offset + nr; i++) {
struct ondisk_cache_entry *disk_ce;
struct cache_entry *ce;
unsigned long consumed;
disk_ce = (struct ondisk_cache_entry *)(mmap + src_offset);
ce = create_from_disk(ce_mem_pool, istate->version, disk_ce, &consumed, previous_ce);
set_index_entry(istate, i, ce);
src_offset += consumed;
previous_ce = ce;
}
return src_offset - start_offset;
}
static unsigned long load_all_cache_entries(struct index_state *istate,
const char *mmap, size_t mmap_size, unsigned long src_offset)
{
unsigned long consumed;
if (istate->version == 4) {
mem_pool_init(&istate->ce_mem_pool,
estimate_cache_size_from_compressed(istate->cache_nr));
} else {
mem_pool_init(&istate->ce_mem_pool,
estimate_cache_size(mmap_size, istate->cache_nr));
}
consumed = load_cache_entry_block(istate, istate->ce_mem_pool,
0, istate->cache_nr, mmap, src_offset, NULL);
return consumed;
}
/*
* Mostly randomly chosen maximum thread counts: we
* cap the parallelism to online_cpus() threads, and we want
* to have at least 10000 cache entries per thread for it to
* be worth starting a thread.
*/
#define THREAD_COST (10000)
struct load_cache_entries_thread_data
{
pthread_t pthread;
struct index_state *istate;
struct mem_pool *ce_mem_pool;
int offset;
const char *mmap;
struct index_entry_offset_table *ieot;
int ieot_start; /* starting index into the ieot array */
int ieot_blocks; /* count of ieot entries to process */
unsigned long consumed; /* return # of bytes in index file processed */
};
/*
* A thread proc to run the load_cache_entries() computation
* across multiple background threads.
*/
static void *load_cache_entries_thread(void *_data)
{
struct load_cache_entries_thread_data *p = _data;
int i;
/* iterate across all ieot blocks assigned to this thread */
for (i = p->ieot_start; i < p->ieot_start + p->ieot_blocks; i++) {
p->consumed += load_cache_entry_block(p->istate, p->ce_mem_pool,
p->offset, p->ieot->entries[i].nr, p->mmap, p->ieot->entries[i].offset, NULL);
p->offset += p->ieot->entries[i].nr;
}
return NULL;
}
static unsigned long load_cache_entries_threaded(struct index_state *istate, const char *mmap, size_t mmap_size,
unsigned long src_offset, int nr_threads, struct index_entry_offset_table *ieot)
{
int i, offset, ieot_blocks, ieot_start, err;
struct load_cache_entries_thread_data *data;
unsigned long consumed = 0;
/* a little sanity checking */
if (istate->name_hash_initialized)
BUG("the name hash isn't thread safe");
mem_pool_init(&istate->ce_mem_pool, 0);
/* ensure we have no more threads than we have blocks to process */
if (nr_threads > ieot->nr)
nr_threads = ieot->nr;
data = xcalloc(nr_threads, sizeof(*data));
offset = ieot_start = 0;
ieot_blocks = DIV_ROUND_UP(ieot->nr, nr_threads);
for (i = 0; i < nr_threads; i++) {
struct load_cache_entries_thread_data *p = &data[i];
int nr, j;
if (ieot_start + ieot_blocks > ieot->nr)
ieot_blocks = ieot->nr - ieot_start;
p->istate = istate;
p->offset = offset;
p->mmap = mmap;
p->ieot = ieot;
p->ieot_start = ieot_start;
p->ieot_blocks = ieot_blocks;
/* create a mem_pool for each thread */
nr = 0;
for (j = p->ieot_start; j < p->ieot_start + p->ieot_blocks; j++)
nr += p->ieot->entries[j].nr;
if (istate->version == 4) {
mem_pool_init(&p->ce_mem_pool,
estimate_cache_size_from_compressed(nr));
} else {
mem_pool_init(&p->ce_mem_pool,
estimate_cache_size(mmap_size, nr));
}
err = pthread_create(&p->pthread, NULL, load_cache_entries_thread, p);
if (err)
die(_("unable to create load_cache_entries thread: %s"), strerror(err));
/* increment by the number of cache entries in the ieot block being processed */
for (j = 0; j < ieot_blocks; j++)
offset += ieot->entries[ieot_start + j].nr;
ieot_start += ieot_blocks;
}
for (i = 0; i < nr_threads; i++) {
struct load_cache_entries_thread_data *p = &data[i];
err = pthread_join(p->pthread, NULL);
if (err)
die(_("unable to join load_cache_entries thread: %s"), strerror(err));
mem_pool_combine(istate->ce_mem_pool, p->ce_mem_pool);
consumed += p->consumed;
}
free(data);
return consumed;
}
/* remember to discard_cache() before reading a different cache! */
int do_read_index(struct index_state *istate, const char *path, int must_exist)
{
int fd;
struct stat st;
unsigned long src_offset;
const struct cache_header *hdr;
const char *mmap;
size_t mmap_size;
struct load_index_extensions p;
size_t extension_offset = 0;
int nr_threads, cpus;
struct index_entry_offset_table *ieot = NULL;
if (istate->initialized)
return istate->cache_nr;
istate->timestamp.sec = 0;
istate->timestamp.nsec = 0;
fd = open(path, O_RDONLY);
if (fd < 0) {
if (!must_exist && errno == ENOENT)
return 0;
die_errno(_("%s: index file open failed"), path);
}
if (fstat(fd, &st))
die_errno(_("%s: cannot stat the open index"), path);
mmap_size = xsize_t(st.st_size);
if (mmap_size < sizeof(struct cache_header) + the_hash_algo->rawsz)
die(_("%s: index file smaller than expected"), path);
mmap = xmmap(NULL, mmap_size, PROT_READ, MAP_PRIVATE, fd, 0);
if (mmap == MAP_FAILED)
die_errno(_("%s: unable to map index file"), path);
close(fd);
hdr = (const struct cache_header *)mmap;
if (verify_hdr(hdr, mmap_size) < 0)
goto unmap;
hashcpy(istate->oid.hash, (const unsigned char *)hdr + mmap_size - the_hash_algo->rawsz);
istate->version = ntohl(hdr->hdr_version);
istate->cache_nr = ntohl(hdr->hdr_entries);
istate->cache_alloc = alloc_nr(istate->cache_nr);
istate->cache = xcalloc(istate->cache_alloc, sizeof(*istate->cache));
istate->initialized = 1;
p.istate = istate;
p.mmap = mmap;
p.mmap_size = mmap_size;
src_offset = sizeof(*hdr);
if (git_config_get_index_threads(&nr_threads))
nr_threads = 1;
/* TODO: does creating more threads than cores help? */
if (!nr_threads) {
nr_threads = istate->cache_nr / THREAD_COST;
cpus = online_cpus();
if (nr_threads > cpus)
nr_threads = cpus;
}
if (!HAVE_THREADS)
nr_threads = 1;
if (nr_threads > 1) {
extension_offset = read_eoie_extension(mmap, mmap_size);
if (extension_offset) {
int err;
p.src_offset = extension_offset;
err = pthread_create(&p.pthread, NULL, load_index_extensions, &p);
if (err)
die(_("unable to create load_index_extensions thread: %s"), strerror(err));
nr_threads--;
}
}
/*
* Locate and read the index entry offset table so that we can use it
* to multi-thread the reading of the cache entries.
*/
if (extension_offset && nr_threads > 1)
ieot = read_ieot_extension(mmap, mmap_size, extension_offset);
if (ieot) {
src_offset += load_cache_entries_threaded(istate, mmap, mmap_size, src_offset, nr_threads, ieot);
free(ieot);
} else {
src_offset += load_all_cache_entries(istate, mmap, mmap_size, src_offset);
}
istate->timestamp.sec = st.st_mtime;
istate->timestamp.nsec = ST_MTIME_NSEC(st);
/* if we created a thread, join it otherwise load the extensions on the primary thread */
if (extension_offset) {
int ret = pthread_join(p.pthread, NULL);
if (ret)
die(_("unable to join load_index_extensions thread: %s"), strerror(ret));
} else {
p.src_offset = src_offset;
load_index_extensions(&p);
}
munmap((void *)mmap, mmap_size);
/*
* TODO trace2: replace "the_repository" with the actual repo instance
* that is associated with the given "istate".
*/
trace2_data_intmax("index", the_repository, "read/version",
istate->version);
trace2_data_intmax("index", the_repository, "read/cache_nr",
istate->cache_nr);
return istate->cache_nr;
unmap:
munmap((void *)mmap, mmap_size);
die(_("index file corrupt"));
}
/*
* Signal that the shared index is used by updating its mtime.
*
* This way, shared index can be removed if they have not been used
* for some time.
*/
static void freshen_shared_index(const char *shared_index, int warn)
{
if (!check_and_freshen_file(shared_index, 1) && warn)
warning(_("could not freshen shared index '%s'"), shared_index);
}
int read_index_from(struct index_state *istate, const char *path,
const char *gitdir)
{
struct split_index *split_index;
int ret;
char *base_oid_hex;
char *base_path;
/* istate->initialized covers both .git/index and .git/sharedindex.xxx */
if (istate->initialized)
return istate->cache_nr;
/*
* TODO trace2: replace "the_repository" with the actual repo instance
* that is associated with the given "istate".
*/
trace2_region_enter_printf("index", "do_read_index", the_repository,
"%s", path);
trace_performance_enter();
ret = do_read_index(istate, path, 0);
trace_performance_leave("read cache %s", path);
trace2_region_leave_printf("index", "do_read_index", the_repository,
"%s", path);
split_index = istate->split_index;
if (!split_index || is_null_oid(&split_index->base_oid)) {
post_read_index_from(istate);
return ret;
}
trace_performance_enter();
if (split_index->base)
discard_index(split_index->base);
else
split_index->base = xcalloc(1, sizeof(*split_index->base));
base_oid_hex = oid_to_hex(&split_index->base_oid);
base_path = xstrfmt("%s/sharedindex.%s", gitdir, base_oid_hex);
trace2_region_enter_printf("index", "shared/do_read_index",
the_repository, "%s", base_path);
ret = do_read_index(split_index->base, base_path, 1);
trace2_region_leave_printf("index", "shared/do_read_index",
the_repository, "%s", base_path);
if (!oideq(&split_index->base_oid, &split_index->base->oid))
die(_("broken index, expect %s in %s, got %s"),
base_oid_hex, base_path,
oid_to_hex(&split_index->base->oid));
freshen_shared_index(base_path, 0);
merge_base_index(istate);
post_read_index_from(istate);
trace_performance_leave("read cache %s", base_path);
free(base_path);
return ret;
}
int is_index_unborn(struct index_state *istate)
{
return (!istate->cache_nr && !istate->timestamp.sec);
}
int discard_index(struct index_state *istate)
{
/*
* Cache entries in istate->cache[] should have been allocated
* from the memory pool associated with this index, or from an
* associated split_index. There is no need to free individual
* cache entries. validate_cache_entries can detect when this
* assertion does not hold.
*/
validate_cache_entries(istate);
resolve_undo_clear_index(istate);
istate->cache_nr = 0;
istate->cache_changed = 0;
istate->timestamp.sec = 0;
istate->timestamp.nsec = 0;
free_name_hash(istate);
cache_tree_free(&(istate->cache_tree));
istate->initialized = 0;
istate->fsmonitor_has_run_once = 0;
FREE_AND_NULL(istate->cache);
istate->cache_alloc = 0;
discard_split_index(istate);
free_untracked_cache(istate->untracked);
istate->untracked = NULL;
if (istate->ce_mem_pool) {
mem_pool_discard(istate->ce_mem_pool, should_validate_cache_entries());
istate->ce_mem_pool = NULL;
}
return 0;
}
/*
* Validate the cache entries of this index.
* All cache entries associated with this index
* should have been allocated by the memory pool
* associated with this index, or by a referenced
* split index.
*/
void validate_cache_entries(const struct index_state *istate)
{
int i;
if (!should_validate_cache_entries() ||!istate || !istate->initialized)
return;
for (i = 0; i < istate->cache_nr; i++) {
if (!istate) {
BUG("cache entry is not allocated from expected memory pool");
} else if (!istate->ce_mem_pool ||
!mem_pool_contains(istate->ce_mem_pool, istate->cache[i])) {
if (!istate->split_index ||
!istate->split_index->base ||
!istate->split_index->base->ce_mem_pool ||
!mem_pool_contains(istate->split_index->base->ce_mem_pool, istate->cache[i])) {
BUG("cache entry is not allocated from expected memory pool");
}
}
}
if (istate->split_index)
validate_cache_entries(istate->split_index->base);
}
int unmerged_index(const struct index_state *istate)
{
int i;
for (i = 0; i < istate->cache_nr; i++) {
if (ce_stage(istate->cache[i]))
return 1;
}
return 0;
}
int repo_index_has_changes(struct repository *repo,
struct tree *tree,
struct strbuf *sb)
{
struct index_state *istate = repo->index;
struct object_id cmp;
int i;
if (tree)
cmp = tree->object.oid;
if (tree || !get_oid_tree("HEAD", &cmp)) {
struct diff_options opt;
repo_diff_setup(repo, &opt);
opt.flags.exit_with_status = 1;
if (!sb)
opt.flags.quick = 1;
do_diff_cache(&cmp, &opt);
diffcore_std(&opt);
for (i = 0; sb && i < diff_queued_diff.nr; i++) {
if (i)
strbuf_addch(sb, ' ');
strbuf_addstr(sb, diff_queued_diff.queue[i]->two->path);
}
diff_flush(&opt);
return opt.flags.has_changes != 0;
} else {
for (i = 0; sb && i < istate->cache_nr; i++) {
if (i)
strbuf_addch(sb, ' ');
strbuf_addstr(sb, istate->cache[i]->name);
}
return !!istate->cache_nr;
}
}
#define WRITE_BUFFER_SIZE 8192
static unsigned char write_buffer[WRITE_BUFFER_SIZE];
static unsigned long write_buffer_len;
static int ce_write_flush(git_hash_ctx *context, int fd)
{
unsigned int buffered = write_buffer_len;
if (buffered) {
the_hash_algo->update_fn(context, write_buffer, buffered);
if (write_in_full(fd, write_buffer, buffered) < 0)
return -1;
write_buffer_len = 0;
}
return 0;
}
static int ce_write(git_hash_ctx *context, int fd, void *data, unsigned int len)
{
while (len) {
unsigned int buffered = write_buffer_len;
unsigned int partial = WRITE_BUFFER_SIZE - buffered;
if (partial > len)
partial = len;
memcpy(write_buffer + buffered, data, partial);
buffered += partial;
if (buffered == WRITE_BUFFER_SIZE) {
write_buffer_len = buffered;
if (ce_write_flush(context, fd))
return -1;
buffered = 0;
}
write_buffer_len = buffered;
len -= partial;
data = (char *) data + partial;
}
return 0;
}
static int write_index_ext_header(git_hash_ctx *context, git_hash_ctx *eoie_context,
int fd, unsigned int ext, unsigned int sz)
{
ext = htonl(ext);
sz = htonl(sz);
if (eoie_context) {
the_hash_algo->update_fn(eoie_context, &ext, 4);
the_hash_algo->update_fn(eoie_context, &sz, 4);
}
return ((ce_write(context, fd, &ext, 4) < 0) ||
(ce_write(context, fd, &sz, 4) < 0)) ? -1 : 0;
}
static int ce_flush(git_hash_ctx *context, int fd, unsigned char *hash)
{
unsigned int left = write_buffer_len;
if (left) {
write_buffer_len = 0;
the_hash_algo->update_fn(context, write_buffer, left);
}
/* Flush first if not enough space for hash signature */
if (left + the_hash_algo->rawsz > WRITE_BUFFER_SIZE) {
if (write_in_full(fd, write_buffer, left) < 0)
return -1;
left = 0;
}
/* Append the hash signature at the end */
the_hash_algo->final_fn(write_buffer + left, context);
hashcpy(hash, write_buffer + left);
left += the_hash_algo->rawsz;
return (write_in_full(fd, write_buffer, left) < 0) ? -1 : 0;
}
static void ce_smudge_racily_clean_entry(struct index_state *istate,
struct cache_entry *ce)
{
/*
* The only thing we care about in this function is to smudge the
* falsely clean entry due to touch-update-touch race, so we leave
* everything else as they are. We are called for entries whose
* ce_stat_data.sd_mtime match the index file mtime.
*
* Note that this actually does not do much for gitlinks, for
* which ce_match_stat_basic() always goes to the actual
* contents. The caller checks with is_racy_timestamp() which
* always says "no" for gitlinks, so we are not called for them ;-)
*/
struct stat st;
if (lstat(ce->name, &st) < 0)
return;
if (ce_match_stat_basic(ce, &st))
return;
if (ce_modified_check_fs(istate, ce, &st)) {
/* This is "racily clean"; smudge it. Note that this
* is a tricky code. At first glance, it may appear
* that it can break with this sequence:
*
* $ echo xyzzy >frotz
* $ git-update-index --add frotz
* $ : >frotz
* $ sleep 3
* $ echo filfre >nitfol
* $ git-update-index --add nitfol
*
* but it does not. When the second update-index runs,
* it notices that the entry "frotz" has the same timestamp
* as index, and if we were to smudge it by resetting its
* size to zero here, then the object name recorded
* in index is the 6-byte file but the cached stat information
* becomes zero --- which would then match what we would
* obtain from the filesystem next time we stat("frotz").
*
* However, the second update-index, before calling
* this function, notices that the cached size is 6
* bytes and what is on the filesystem is an empty
* file, and never calls us, so the cached size information
* for "frotz" stays 6 which does not match the filesystem.
*/
ce->ce_stat_data.sd_size = 0;
}
}
/* Copy miscellaneous fields but not the name */
static void copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk,
struct cache_entry *ce)
{
short flags;
const unsigned hashsz = the_hash_algo->rawsz;
uint16_t *flagsp = (uint16_t *)(ondisk->data + hashsz);
ondisk->ctime.sec = htonl(ce->ce_stat_data.sd_ctime.sec);
ondisk->mtime.sec = htonl(ce->ce_stat_data.sd_mtime.sec);
ondisk->ctime.nsec = htonl(ce->ce_stat_data.sd_ctime.nsec);
ondisk->mtime.nsec = htonl(ce->ce_stat_data.sd_mtime.nsec);
ondisk->dev = htonl(ce->ce_stat_data.sd_dev);
ondisk->ino = htonl(ce->ce_stat_data.sd_ino);
ondisk->mode = htonl(ce->ce_mode);
ondisk->uid = htonl(ce->ce_stat_data.sd_uid);
ondisk->gid = htonl(ce->ce_stat_data.sd_gid);
ondisk->size = htonl(ce->ce_stat_data.sd_size);
hashcpy(ondisk->data, ce->oid.hash);
flags = ce->ce_flags & ~CE_NAMEMASK;
flags |= (ce_namelen(ce) >= CE_NAMEMASK ? CE_NAMEMASK : ce_namelen(ce));
flagsp[0] = htons(flags);
if (ce->ce_flags & CE_EXTENDED) {
flagsp[1] = htons((ce->ce_flags & CE_EXTENDED_FLAGS) >> 16);
}
}
static int ce_write_entry(git_hash_ctx *c, int fd, struct cache_entry *ce,
struct strbuf *previous_name, struct ondisk_cache_entry *ondisk)
{
int size;
int result;
unsigned int saved_namelen;
int stripped_name = 0;
static unsigned char padding[8] = { 0x00 };
if (ce->ce_flags & CE_STRIP_NAME) {
saved_namelen = ce_namelen(ce);
ce->ce_namelen = 0;
stripped_name = 1;
}
size = offsetof(struct ondisk_cache_entry,data) + ondisk_data_size(ce->ce_flags, 0);
if (!previous_name) {
int len = ce_namelen(ce);
copy_cache_entry_to_ondisk(ondisk, ce);
result = ce_write(c, fd, ondisk, size);
if (!result)
result = ce_write(c, fd, ce->name, len);
if (!result)
result = ce_write(c, fd, padding, align_padding_size(size, len));
} else {
int common, to_remove, prefix_size;
unsigned char to_remove_vi[16];
for (common = 0;
(ce->name[common] &&
common < previous_name->len &&
ce->name[common] == previous_name->buf[common]);
common++)
; /* still matching */
to_remove = previous_name->len - common;
prefix_size = encode_varint(to_remove, to_remove_vi);
copy_cache_entry_to_ondisk(ondisk, ce);
result = ce_write(c, fd, ondisk, size);
if (!result)
result = ce_write(c, fd, to_remove_vi, prefix_size);
if (!result)
result = ce_write(c, fd, ce->name + common, ce_namelen(ce) - common);
if (!result)
result = ce_write(c, fd, padding, 1);
strbuf_splice(previous_name, common, to_remove,
ce->name + common, ce_namelen(ce) - common);
}
if (stripped_name) {
ce->ce_namelen = saved_namelen;
ce->ce_flags &= ~CE_STRIP_NAME;
}
return result;
}
/*
* This function verifies if index_state has the correct sha1 of the
* index file. Don't die if we have any other failure, just return 0.
*/
static int verify_index_from(const struct index_state *istate, const char *path)
{
int fd;
ssize_t n;
struct stat st;
unsigned char hash[GIT_MAX_RAWSZ];
if (!istate->initialized)
return 0;
fd = open(path, O_RDONLY);
if (fd < 0)
return 0;
if (fstat(fd, &st))
goto out;
if (st.st_size < sizeof(struct cache_header) + the_hash_algo->rawsz)
goto out;
n = pread_in_full(fd, hash, the_hash_algo->rawsz, st.st_size - the_hash_algo->rawsz);
if (n != the_hash_algo->rawsz)
goto out;
if (!hasheq(istate->oid.hash, hash))
goto out;
close(fd);
return 1;
out:
close(fd);
return 0;
}