git/refs.c

3363 lines
89 KiB
C
Raw Normal View History

#include "cache.h"
#include "refs.h"
#include "object.h"
#include "tag.h"
#include "dir.h"
upload/receive-pack: allow hiding ref hierarchies A repository may have refs that are only used for its internal bookkeeping purposes that should not be exposed to the others that come over the network. Teach upload-pack to omit some refs from its initial advertisement by paying attention to the uploadpack.hiderefs multi-valued configuration variable. Do the same to receive-pack via the receive.hiderefs variable. As a convenient short-hand, allow using transfer.hiderefs to set the value to both of these variables. Any ref that is under the hierarchies listed on the value of these variable is excluded from responses to requests made by "ls-remote", "fetch", etc. (for upload-pack) and "push" (for receive-pack). Because these hidden refs do not count as OUR_REF, an attempt to fetch objects at the tip of them will be rejected, and because these refs do not get advertised, "git push :" will not see local branches that have the same name as them as "matching" ones to be sent. An attempt to update/delete these hidden refs with an explicit refspec, e.g. "git push origin :refs/hidden/22", is rejected. This is not a new restriction. To the pusher, it would appear that there is no such ref, so its push request will conclude with "Now that I sent you all the data, it is time for you to update the refs. I saw that the ref did not exist when I started pushing, and I want the result to point at this commit". The receiving end will apply the compare-and-swap rule to this request and rejects the push with "Well, your update request conflicts with somebody else; I see there is such a ref.", which is the right thing to do. Otherwise a push to a hidden ref will always be "the last one wins", which is not a good default. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-01-19 08:08:30 +08:00
#include "string-list.h"
/*
* Make sure "ref" is something reasonable to have under ".git/refs/";
* We do not like it if:
*
* - any path component of it begins with ".", or
* - it has double dots "..", or
* - it has ASCII control character, "~", "^", ":" or SP, anywhere, or
* - it ends with a "/".
* - it ends with ".lock"
* - it contains a "\" (backslash)
*/
/* Return true iff ch is not allowed in reference names. */
static inline int bad_ref_char(int ch)
{
if (((unsigned) ch) <= ' ' || ch == 0x7f ||
ch == '~' || ch == '^' || ch == ':' || ch == '\\')
return 1;
/* 2.13 Pattern Matching Notation */
if (ch == '*' || ch == '?' || ch == '[') /* Unsupported */
return 1;
return 0;
}
/*
* Try to read one refname component from the front of refname. Return
* the length of the component found, or -1 if the component is not
* legal.
*/
static int check_refname_component(const char *refname, int flags)
{
const char *cp;
char last = '\0';
for (cp = refname; ; cp++) {
char ch = *cp;
if (ch == '\0' || ch == '/')
break;
if (bad_ref_char(ch))
return -1; /* Illegal character in refname. */
if (last == '.' && ch == '.')
return -1; /* Refname contains "..". */
if (last == '@' && ch == '{')
return -1; /* Refname contains "@{". */
last = ch;
}
if (cp == refname)
return 0; /* Component has zero length. */
if (refname[0] == '.') {
if (!(flags & REFNAME_DOT_COMPONENT))
return -1; /* Component starts with '.'. */
/*
* Even if leading dots are allowed, don't allow "."
* as a component (".." is prevented by a rule above).
*/
if (refname[1] == '\0')
return -1; /* Component equals ".". */
}
if (cp - refname >= 5 && !memcmp(cp - 5, ".lock", 5))
return -1; /* Refname ends with ".lock". */
return cp - refname;
}
int check_refname_format(const char *refname, int flags)
{
int component_len, component_count = 0;
if (!strcmp(refname, "@"))
/* Refname is a single character '@'. */
return -1;
while (1) {
/* We are at the start of a path component. */
component_len = check_refname_component(refname, flags);
if (component_len <= 0) {
if ((flags & REFNAME_REFSPEC_PATTERN) &&
refname[0] == '*' &&
(refname[1] == '\0' || refname[1] == '/')) {
/* Accept one wildcard as a full refname component. */
flags &= ~REFNAME_REFSPEC_PATTERN;
component_len = 1;
} else {
return -1;
}
}
component_count++;
if (refname[component_len] == '\0')
break;
/* Skip to next component. */
refname += component_len + 1;
}
if (refname[component_len - 1] == '.')
return -1; /* Refname ends with '.'. */
if (!(flags & REFNAME_ALLOW_ONELEVEL) && component_count < 2)
return -1; /* Refname has only one component. */
return 0;
}
struct ref_entry;
/*
* Information used (along with the information in ref_entry) to
* describe a single cached reference. This data structure only
* occurs embedded in a union in struct ref_entry, and only when
* (ref_entry->flag & REF_DIR) is zero.
*/
struct ref_value {
/*
* The name of the object to which this reference resolves
* (which may be a tag object). If REF_ISBROKEN, this is
* null. If REF_ISSYMREF, then this is the name of the object
* referred to by the last reference in the symlink chain.
*/
unsigned char sha1[20];
/*
* If REF_KNOWS_PEELED, then this field holds the peeled value
* of this reference, or null if the reference is known not to
* be peelable. See the documentation for peel_ref() for an
* exact definition of "peelable".
*/
unsigned char peeled[20];
};
struct ref_cache;
/*
* Information used (along with the information in ref_entry) to
* describe a level in the hierarchy of references. This data
* structure only occurs embedded in a union in struct ref_entry, and
* only when (ref_entry.flag & REF_DIR) is set. In that case,
* (ref_entry.flag & REF_INCOMPLETE) determines whether the references
* in the directory have already been read:
*
* (ref_entry.flag & REF_INCOMPLETE) unset -- a directory of loose
* or packed references, already read.
*
* (ref_entry.flag & REF_INCOMPLETE) set -- a directory of loose
* references that hasn't been read yet (nor has any of its
* subdirectories).
*
* Entries within a directory are stored within a growable array of
* pointers to ref_entries (entries, nr, alloc). Entries 0 <= i <
* sorted are sorted by their component name in strcmp() order and the
* remaining entries are unsorted.
*
* Loose references are read lazily, one directory at a time. When a
* directory of loose references is read, then all of the references
* in that directory are stored, and REF_INCOMPLETE stubs are created
* for any subdirectories, but the subdirectories themselves are not
* read. The reading is triggered by get_ref_dir().
*/
struct ref_dir {
int nr, alloc;
ref_array: keep track of whether references are sorted Keep track of how many entries at the beginning of a ref_array are already sorted. In sort_ref_array(), return early if the the array is already sorted (i.e., if no new references has been appended to the end of the list since the last call to sort_ref_array()). Sort ref_arrays only when needed, namely in search_ref_array() and in do_for_each_ref(). However, never call sort_ref_array() on the extra_refs, because extra_refs can contain multiple entries with the same name and because sort_ref_array() not only sorts, but de-dups its contents. This change is currently not useful, because entries are not added to ref_arrays after they are created. But in a moment they will be... Implementation note: we could store a binary "sorted" value instead of an integer, but storing the number of sorted entries leaves the way open for a couple of possible future optimizations: * In sort_ref_array(), sort *only* the unsorted entries, then merge them with the sorted entries. This should be faster if most of the entries are already sorted. * Teach search_ref_array() to do a binary search of any sorted entries, and if unsuccessful do a linear search of any unsorted entries. This would avoid the need to sort the list every time that search_ref_array() is called, and (given some intelligence about how often to sort) could significantly improve the speed in certain hypothetical usage patterns. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-01-17 13:50:32 +08:00
/*
* Entries with index 0 <= i < sorted are sorted by name. New
* entries are appended to the list unsorted, and are sorted
* only when required; thus we avoid the need to sort the list
* after the addition of every reference.
*/
int sorted;
/* A pointer to the ref_cache that contains this ref_dir. */
struct ref_cache *ref_cache;
struct ref_entry **entries;
};
/*
* Bit values for ref_entry::flag. REF_ISSYMREF=0x01,
* REF_ISPACKED=0x02, and REF_ISBROKEN=0x04 are public values; see
* refs.h.
*/
/*
* The field ref_entry->u.value.peeled of this value entry contains
* the correct peeled value for the reference, which might be
* null_sha1 if the reference is not a tag or if it is broken.
*/
#define REF_KNOWS_PEELED 0x08
/* ref_entry represents a directory of references */
#define REF_DIR 0x10
/*
* Entry has not yet been read from disk (used only for REF_DIR
* entries representing loose references)
*/
#define REF_INCOMPLETE 0x20
/*
* A ref_entry represents either a reference or a "subdirectory" of
* references.
*
* Each directory in the reference namespace is represented by a
* ref_entry with (flags & REF_DIR) set and containing a subdir member
* that holds the entries in that directory that have been read so
* far. If (flags & REF_INCOMPLETE) is set, then the directory and
* its subdirectories haven't been read yet. REF_INCOMPLETE is only
* used for loose reference directories.
*
* References are represented by a ref_entry with (flags & REF_DIR)
* unset and a value member that describes the reference's value. The
* flag member is at the ref_entry level, but it is also needed to
* interpret the contents of the value field (in other words, a
* ref_value object is not very much use without the enclosing
* ref_entry).
*
* Reference names cannot end with slash and directories' names are
* always stored with a trailing slash (except for the top-level
* directory, which is always denoted by ""). This has two nice
* consequences: (1) when the entries in each subdir are sorted
* lexicographically by name (as they usually are), the references in
* a whole tree can be generated in lexicographic order by traversing
* the tree in left-to-right, depth-first order; (2) the names of
* references and subdirectories cannot conflict, and therefore the
* presence of an empty subdirectory does not block the creation of a
* similarly-named reference. (The fact that reference names with the
* same leading components can conflict *with each other* is a
* separate issue that is regulated by is_refname_available().)
*
* Please note that the name field contains the fully-qualified
* reference (or subdirectory) name. Space could be saved by only
* storing the relative names. But that would require the full names
* to be generated on the fly when iterating in do_for_each_ref(), and
* would break callback functions, who have always been able to assume
* that the name strings that they are passed will not be freed during
* the iteration.
*/
struct ref_entry {
unsigned char flag; /* ISSYMREF? ISPACKED? */
union {
struct ref_value value; /* if not (flags&REF_DIR) */
struct ref_dir subdir; /* if (flags&REF_DIR) */
} u;
/*
* The full name of the reference (e.g., "refs/heads/master")
* or the full name of the directory with a trailing slash
* (e.g., "refs/heads/"):
*/
char name[FLEX_ARRAY];
};
static void read_loose_refs(const char *dirname, struct ref_dir *dir);
static struct ref_dir *get_ref_dir(struct ref_entry *entry)
{
struct ref_dir *dir;
assert(entry->flag & REF_DIR);
dir = &entry->u.subdir;
if (entry->flag & REF_INCOMPLETE) {
read_loose_refs(entry->name, dir);
entry->flag &= ~REF_INCOMPLETE;
}
return dir;
}
static struct ref_entry *create_ref_entry(const char *refname,
const unsigned char *sha1, int flag,
int check_name)
{
int len;
struct ref_entry *ref;
if (check_name &&
check_refname_format(refname, REFNAME_ALLOW_ONELEVEL|REFNAME_DOT_COMPONENT))
die("Reference has invalid format: '%s'", refname);
len = strlen(refname) + 1;
ref = xmalloc(sizeof(struct ref_entry) + len);
hashcpy(ref->u.value.sha1, sha1);
hashclr(ref->u.value.peeled);
memcpy(ref->name, refname, len);
ref->flag = flag;
return ref;
}
static void clear_ref_dir(struct ref_dir *dir);
static void free_ref_entry(struct ref_entry *entry)
{
if (entry->flag & REF_DIR) {
/*
* Do not use get_ref_dir() here, as that might
* trigger the reading of loose refs.
*/
clear_ref_dir(&entry->u.subdir);
}
free(entry);
}
/*
* Add a ref_entry to the end of dir (unsorted). Entry is always
* stored directly in dir; no recursion into subdirectories is
* done.
*/
static void add_entry_to_dir(struct ref_dir *dir, struct ref_entry *entry)
{
ALLOC_GROW(dir->entries, dir->nr + 1, dir->alloc);
dir->entries[dir->nr++] = entry;
/* optimize for the case that entries are added in order */
if (dir->nr == 1 ||
(dir->nr == dir->sorted + 1 &&
strcmp(dir->entries[dir->nr - 2]->name,
dir->entries[dir->nr - 1]->name) < 0))
dir->sorted = dir->nr;
}
/*
* Clear and free all entries in dir, recursively.
*/
static void clear_ref_dir(struct ref_dir *dir)
{
int i;
for (i = 0; i < dir->nr; i++)
free_ref_entry(dir->entries[i]);
free(dir->entries);
dir->sorted = dir->nr = dir->alloc = 0;
dir->entries = NULL;
}
/*
* Create a struct ref_entry object for the specified dirname.
* dirname is the name of the directory with a trailing slash (e.g.,
* "refs/heads/") or "" for the top-level directory.
*/
static struct ref_entry *create_dir_entry(struct ref_cache *ref_cache,
const char *dirname, size_t len,
int incomplete)
{
struct ref_entry *direntry;
direntry = xcalloc(1, sizeof(struct ref_entry) + len + 1);
memcpy(direntry->name, dirname, len);
direntry->name[len] = '\0';
direntry->u.subdir.ref_cache = ref_cache;
direntry->flag = REF_DIR | (incomplete ? REF_INCOMPLETE : 0);
return direntry;
}
static int ref_entry_cmp(const void *a, const void *b)
{
struct ref_entry *one = *(struct ref_entry **)a;
struct ref_entry *two = *(struct ref_entry **)b;
return strcmp(one->name, two->name);
}
static void sort_ref_dir(struct ref_dir *dir);
struct string_slice {
size_t len;
const char *str;
};
static int ref_entry_cmp_sslice(const void *key_, const void *ent_)
{
const struct string_slice *key = key_;
const struct ref_entry *ent = *(const struct ref_entry * const *)ent_;
int cmp = strncmp(key->str, ent->name, key->len);
if (cmp)
return cmp;
return '\0' - (unsigned char)ent->name[key->len];
}
/*
* Return the index of the entry with the given refname from the
* ref_dir (non-recursively), sorting dir if necessary. Return -1 if
* no such entry is found. dir must already be complete.
*/
static int search_ref_dir(struct ref_dir *dir, const char *refname, size_t len)
{
struct ref_entry **r;
struct string_slice key;
if (refname == NULL || !dir->nr)
return -1;
sort_ref_dir(dir);
key.len = len;
key.str = refname;
r = bsearch(&key, dir->entries, dir->nr, sizeof(*dir->entries),
ref_entry_cmp_sslice);
if (r == NULL)
return -1;
return r - dir->entries;
}
/*
* Search for a directory entry directly within dir (without
* recursing). Sort dir if necessary. subdirname must be a directory
* name (i.e., end in '/'). If mkdir is set, then create the
* directory if it is missing; otherwise, return NULL if the desired
* directory cannot be found. dir must already be complete.
*/
static struct ref_dir *search_for_subdir(struct ref_dir *dir,
const char *subdirname, size_t len,
int mkdir)
{
int entry_index = search_ref_dir(dir, subdirname, len);
struct ref_entry *entry;
if (entry_index == -1) {
if (!mkdir)
return NULL;
/*
* Since dir is complete, the absence of a subdir
* means that the subdir really doesn't exist;
* therefore, create an empty record for it but mark
* the record complete.
*/
entry = create_dir_entry(dir->ref_cache, subdirname, len, 0);
add_entry_to_dir(dir, entry);
} else {
entry = dir->entries[entry_index];
}
return get_ref_dir(entry);
}
/*
* If refname is a reference name, find the ref_dir within the dir
* tree that should hold refname. If refname is a directory name
* (i.e., ends in '/'), then return that ref_dir itself. dir must
* represent the top-level directory and must already be complete.
* Sort ref_dirs and recurse into subdirectories as necessary. If
* mkdir is set, then create any missing directories; otherwise,
* return NULL if the desired directory cannot be found.
*/
static struct ref_dir *find_containing_dir(struct ref_dir *dir,
const char *refname, int mkdir)
{
const char *slash;
for (slash = strchr(refname, '/'); slash; slash = strchr(slash + 1, '/')) {
size_t dirnamelen = slash - refname + 1;
struct ref_dir *subdir;
subdir = search_for_subdir(dir, refname, dirnamelen, mkdir);
if (!subdir) {
dir = NULL;
break;
}
dir = subdir;
}
return dir;
}
/*
* Find the value entry with the given name in dir, sorting ref_dirs
* and recursing into subdirectories as necessary. If the name is not
* found or it corresponds to a directory entry, return NULL.
*/
static struct ref_entry *find_ref(struct ref_dir *dir, const char *refname)
{
int entry_index;
struct ref_entry *entry;
dir = find_containing_dir(dir, refname, 0);
if (!dir)
return NULL;
entry_index = search_ref_dir(dir, refname, strlen(refname));
if (entry_index == -1)
return NULL;
entry = dir->entries[entry_index];
return (entry->flag & REF_DIR) ? NULL : entry;
}
/*
* Remove the entry with the given name from dir, recursing into
* subdirectories as necessary. If refname is the name of a directory
* (i.e., ends with '/'), then remove the directory and its contents.
* If the removal was successful, return the number of entries
* remaining in the directory entry that contained the deleted entry.
* If the name was not found, return -1. Please note that this
* function only deletes the entry from the cache; it does not delete
* it from the filesystem or ensure that other cache entries (which
* might be symbolic references to the removed entry) are updated.
* Nor does it remove any containing dir entries that might be made
* empty by the removal. dir must represent the top-level directory
* and must already be complete.
*/
static int remove_entry(struct ref_dir *dir, const char *refname)
{
int refname_len = strlen(refname);
int entry_index;
struct ref_entry *entry;
int is_dir = refname[refname_len - 1] == '/';
if (is_dir) {
/*
* refname represents a reference directory. Remove
* the trailing slash; otherwise we will get the
* directory *representing* refname rather than the
* one *containing* it.
*/
char *dirname = xmemdupz(refname, refname_len - 1);
dir = find_containing_dir(dir, dirname, 0);
free(dirname);
} else {
dir = find_containing_dir(dir, refname, 0);
}
if (!dir)
return -1;
entry_index = search_ref_dir(dir, refname, refname_len);
if (entry_index == -1)
return -1;
entry = dir->entries[entry_index];
memmove(&dir->entries[entry_index],
&dir->entries[entry_index + 1],
(dir->nr - entry_index - 1) * sizeof(*dir->entries)
);
dir->nr--;
if (dir->sorted > entry_index)
dir->sorted--;
free_ref_entry(entry);
return dir->nr;
}
/*
* Add a ref_entry to the ref_dir (unsorted), recursing into
* subdirectories as necessary. dir must represent the top-level
* directory. Return 0 on success.
*/
static int add_ref(struct ref_dir *dir, struct ref_entry *ref)
{
dir = find_containing_dir(dir, ref->name, 1);
if (!dir)
return -1;
add_entry_to_dir(dir, ref);
return 0;
}
/*
* Emit a warning and return true iff ref1 and ref2 have the same name
* and the same sha1. Die if they have the same name but different
* sha1s.
*/
static int is_dup_ref(const struct ref_entry *ref1, const struct ref_entry *ref2)
{
if (strcmp(ref1->name, ref2->name))
return 0;
/* Duplicate name; make sure that they don't conflict: */
if ((ref1->flag & REF_DIR) || (ref2->flag & REF_DIR))
/* This is impossible by construction */
die("Reference directory conflict: %s", ref1->name);
if (hashcmp(ref1->u.value.sha1, ref2->u.value.sha1))
die("Duplicated ref, and SHA1s don't match: %s", ref1->name);
warning("Duplicated ref: %s", ref1->name);
return 1;
}
ref_array: keep track of whether references are sorted Keep track of how many entries at the beginning of a ref_array are already sorted. In sort_ref_array(), return early if the the array is already sorted (i.e., if no new references has been appended to the end of the list since the last call to sort_ref_array()). Sort ref_arrays only when needed, namely in search_ref_array() and in do_for_each_ref(). However, never call sort_ref_array() on the extra_refs, because extra_refs can contain multiple entries with the same name and because sort_ref_array() not only sorts, but de-dups its contents. This change is currently not useful, because entries are not added to ref_arrays after they are created. But in a moment they will be... Implementation note: we could store a binary "sorted" value instead of an integer, but storing the number of sorted entries leaves the way open for a couple of possible future optimizations: * In sort_ref_array(), sort *only* the unsorted entries, then merge them with the sorted entries. This should be faster if most of the entries are already sorted. * Teach search_ref_array() to do a binary search of any sorted entries, and if unsuccessful do a linear search of any unsorted entries. This would avoid the need to sort the list every time that search_ref_array() is called, and (given some intelligence about how often to sort) could significantly improve the speed in certain hypothetical usage patterns. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-01-17 13:50:32 +08:00
/*
* Sort the entries in dir non-recursively (if they are not already
* sorted) and remove any duplicate entries.
ref_array: keep track of whether references are sorted Keep track of how many entries at the beginning of a ref_array are already sorted. In sort_ref_array(), return early if the the array is already sorted (i.e., if no new references has been appended to the end of the list since the last call to sort_ref_array()). Sort ref_arrays only when needed, namely in search_ref_array() and in do_for_each_ref(). However, never call sort_ref_array() on the extra_refs, because extra_refs can contain multiple entries with the same name and because sort_ref_array() not only sorts, but de-dups its contents. This change is currently not useful, because entries are not added to ref_arrays after they are created. But in a moment they will be... Implementation note: we could store a binary "sorted" value instead of an integer, but storing the number of sorted entries leaves the way open for a couple of possible future optimizations: * In sort_ref_array(), sort *only* the unsorted entries, then merge them with the sorted entries. This should be faster if most of the entries are already sorted. * Teach search_ref_array() to do a binary search of any sorted entries, and if unsuccessful do a linear search of any unsorted entries. This would avoid the need to sort the list every time that search_ref_array() is called, and (given some intelligence about how often to sort) could significantly improve the speed in certain hypothetical usage patterns. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-01-17 13:50:32 +08:00
*/
static void sort_ref_dir(struct ref_dir *dir)
{
int i, j;
struct ref_entry *last = NULL;
ref_array: keep track of whether references are sorted Keep track of how many entries at the beginning of a ref_array are already sorted. In sort_ref_array(), return early if the the array is already sorted (i.e., if no new references has been appended to the end of the list since the last call to sort_ref_array()). Sort ref_arrays only when needed, namely in search_ref_array() and in do_for_each_ref(). However, never call sort_ref_array() on the extra_refs, because extra_refs can contain multiple entries with the same name and because sort_ref_array() not only sorts, but de-dups its contents. This change is currently not useful, because entries are not added to ref_arrays after they are created. But in a moment they will be... Implementation note: we could store a binary "sorted" value instead of an integer, but storing the number of sorted entries leaves the way open for a couple of possible future optimizations: * In sort_ref_array(), sort *only* the unsorted entries, then merge them with the sorted entries. This should be faster if most of the entries are already sorted. * Teach search_ref_array() to do a binary search of any sorted entries, and if unsuccessful do a linear search of any unsorted entries. This would avoid the need to sort the list every time that search_ref_array() is called, and (given some intelligence about how often to sort) could significantly improve the speed in certain hypothetical usage patterns. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-01-17 13:50:32 +08:00
/*
* This check also prevents passing a zero-length array to qsort(),
* which is a problem on some platforms.
*/
if (dir->sorted == dir->nr)
return;
qsort(dir->entries, dir->nr, sizeof(*dir->entries), ref_entry_cmp);
/* Remove any duplicates: */
for (i = 0, j = 0; j < dir->nr; j++) {
struct ref_entry *entry = dir->entries[j];
if (last && is_dup_ref(last, entry))
free_ref_entry(entry);
else
last = dir->entries[i++] = entry;
}
dir->sorted = dir->nr = i;
}
/* Include broken references in a do_for_each_ref*() iteration: */
#define DO_FOR_EACH_INCLUDE_BROKEN 0x01
/*
* Return true iff the reference described by entry can be resolved to
* an object in the database. Emit a warning if the referred-to
* object does not exist.
*/
static int ref_resolves_to_object(struct ref_entry *entry)
{
if (entry->flag & REF_ISBROKEN)
return 0;
if (!has_sha1_file(entry->u.value.sha1)) {
error("%s does not point to a valid object!", entry->name);
return 0;
}
return 1;
}
/*
* current_ref is a performance hack: when iterating over references
* using the for_each_ref*() functions, current_ref is set to the
* current reference's entry before calling the callback function. If
* the callback function calls peel_ref(), then peel_ref() first
* checks whether the reference to be peeled is the current reference
* (it usually is) and if so, returns that reference's peeled version
* if it is available. This avoids a refname lookup in a common case.
*/
static struct ref_entry *current_ref;
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
typedef int each_ref_entry_fn(struct ref_entry *entry, void *cb_data);
struct ref_entry_cb {
const char *base;
int trim;
int flags;
each_ref_fn *fn;
void *cb_data;
};
/*
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
* Handle one reference in a do_for_each_ref*()-style iteration,
* calling an each_ref_fn for each entry.
*/
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
static int do_one_ref(struct ref_entry *entry, void *cb_data)
{
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
struct ref_entry_cb *data = cb_data;
struct ref_entry *old_current_ref;
int retval;
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
if (prefixcmp(entry->name, data->base))
return 0;
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
if (!(data->flags & DO_FOR_EACH_INCLUDE_BROKEN) &&
!ref_resolves_to_object(entry))
return 0;
/* Store the old value, in case this is a recursive call: */
old_current_ref = current_ref;
current_ref = entry;
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
retval = data->fn(entry->name + data->trim, entry->u.value.sha1,
entry->flag, data->cb_data);
current_ref = old_current_ref;
return retval;
}
/*
* Call fn for each reference in dir that has index in the range
* offset <= index < dir->nr. Recurse into subdirectories that are in
* that index range, sorting them before iterating. This function
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
* does not sort dir itself; it should be sorted beforehand. fn is
* called for all references, including broken ones.
*/
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
static int do_for_each_entry_in_dir(struct ref_dir *dir, int offset,
each_ref_entry_fn fn, void *cb_data)
{
int i;
assert(dir->sorted == dir->nr);
for (i = offset; i < dir->nr; i++) {
struct ref_entry *entry = dir->entries[i];
int retval;
if (entry->flag & REF_DIR) {
struct ref_dir *subdir = get_ref_dir(entry);
sort_ref_dir(subdir);
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
retval = do_for_each_entry_in_dir(subdir, 0, fn, cb_data);
} else {
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
retval = fn(entry, cb_data);
}
if (retval)
return retval;
}
return 0;
}
/*
* Call fn for each reference in the union of dir1 and dir2, in order
* by refname. Recurse into subdirectories. If a value entry appears
* in both dir1 and dir2, then only process the version that is in
* dir2. The input dirs must already be sorted, but subdirs will be
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
* sorted as needed. fn is called for all references, including
* broken ones.
*/
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
static int do_for_each_entry_in_dirs(struct ref_dir *dir1,
struct ref_dir *dir2,
each_ref_entry_fn fn, void *cb_data)
{
int retval;
int i1 = 0, i2 = 0;
assert(dir1->sorted == dir1->nr);
assert(dir2->sorted == dir2->nr);
while (1) {
struct ref_entry *e1, *e2;
int cmp;
if (i1 == dir1->nr) {
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
return do_for_each_entry_in_dir(dir2, i2, fn, cb_data);
}
if (i2 == dir2->nr) {
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
return do_for_each_entry_in_dir(dir1, i1, fn, cb_data);
}
e1 = dir1->entries[i1];
e2 = dir2->entries[i2];
cmp = strcmp(e1->name, e2->name);
if (cmp == 0) {
if ((e1->flag & REF_DIR) && (e2->flag & REF_DIR)) {
/* Both are directories; descend them in parallel. */
struct ref_dir *subdir1 = get_ref_dir(e1);
struct ref_dir *subdir2 = get_ref_dir(e2);
sort_ref_dir(subdir1);
sort_ref_dir(subdir2);
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
retval = do_for_each_entry_in_dirs(
subdir1, subdir2, fn, cb_data);
i1++;
i2++;
} else if (!(e1->flag & REF_DIR) && !(e2->flag & REF_DIR)) {
/* Both are references; ignore the one from dir1. */
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
retval = fn(e2, cb_data);
i1++;
i2++;
} else {
die("conflict between reference and directory: %s",
e1->name);
}
} else {
struct ref_entry *e;
if (cmp < 0) {
e = e1;
i1++;
} else {
e = e2;
i2++;
}
if (e->flag & REF_DIR) {
struct ref_dir *subdir = get_ref_dir(e);
sort_ref_dir(subdir);
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
retval = do_for_each_entry_in_dir(
subdir, 0, fn, cb_data);
} else {
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
retval = fn(e, cb_data);
}
}
if (retval)
return retval;
}
}
for_each_ref: load all loose refs before packed refs If we are iterating through the refs using for_each_ref (or any of its sister functions), we can get into a race condition with a simultaneous "pack-refs --prune" that looks like this: 0. We have a large number of loose refs, and a few packed refs. refs/heads/z/foo is loose, with no matching entry in the packed-refs file. 1. Process A starts iterating through the refs. It loads the packed-refs file from disk, then starts lazily traversing through the loose ref directories. 2. Process B, running "pack-refs --prune", writes out the new packed-refs file. It then deletes the newly packed refs, including refs/heads/z/foo. 3. Meanwhile, process A has finally gotten to refs/heads/z (it traverses alphabetically). It descends, but finds nothing there. It checks its cached view of the packed-refs file, but it does not mention anything in "refs/heads/z/" at all (it predates the new file written by B in step 2). The traversal completes successfully without mentioning refs/heads/z/foo at all (the name, of course, isn't important; but the more refs you have and the farther down the alphabetical list a ref is, the more likely it is to hit the race). If refs/heads/z/foo did exist in the packed refs file at state 0, we would see an entry for it, but it would show whatever sha1 the ref had the last time it was packed (which could be an arbitrarily long time ago). This can be especially dangerous when process A is "git prune", as it means our set of reachable tips will be incomplete, and we may erroneously prune objects reachable from that tip (the same thing can happen if "repack -ad" is used, as it simply drops unreachable objects that are packed). This patch solves it by loading all of the loose refs for our traversal into our in-memory cache, and then refreshing the packed-refs cache. Because a pack-refs writer will always put the new packed-refs file into place before starting the prune, we know that any loose refs we fail to see will either truly be missing, or will have already been put in the packed-refs file by the time we refresh. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-20 16:37:53 +08:00
/*
* Load all of the refs from the dir into our in-memory cache. The hard work
* of loading loose refs is done by get_ref_dir(), so we just need to recurse
* through all of the sub-directories. We do not even need to care about
* sorting, as traversal order does not matter to us.
*/
static void prime_ref_dir(struct ref_dir *dir)
{
int i;
for (i = 0; i < dir->nr; i++) {
struct ref_entry *entry = dir->entries[i];
if (entry->flag & REF_DIR)
prime_ref_dir(get_ref_dir(entry));
}
}
/*
* Return true iff refname1 and refname2 conflict with each other.
* Two reference names conflict if one of them exactly matches the
* leading components of the other; e.g., "foo/bar" conflicts with
* both "foo" and with "foo/bar/baz" but not with "foo/bar" or
* "foo/barbados".
*/
static int names_conflict(const char *refname1, const char *refname2)
{
for (; *refname1 && *refname1 == *refname2; refname1++, refname2++)
;
return (*refname1 == '\0' && *refname2 == '/')
|| (*refname1 == '/' && *refname2 == '\0');
}
struct name_conflict_cb {
const char *refname;
const char *oldrefname;
const char *conflicting_refname;
};
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
static int name_conflict_fn(struct ref_entry *entry, void *cb_data)
{
struct name_conflict_cb *data = (struct name_conflict_cb *)cb_data;
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
if (data->oldrefname && !strcmp(data->oldrefname, entry->name))
return 0;
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
if (names_conflict(data->refname, entry->name)) {
data->conflicting_refname = entry->name;
return 1;
}
return 0;
}
/*
* Return true iff a reference named refname could be created without
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
* conflicting with the name of an existing reference in dir. If
* oldrefname is non-NULL, ignore potential conflicts with oldrefname
* (e.g., because oldrefname is scheduled for deletion in the same
* operation).
*/
static int is_refname_available(const char *refname, const char *oldrefname,
struct ref_dir *dir)
{
struct name_conflict_cb data;
data.refname = refname;
data.oldrefname = oldrefname;
data.conflicting_refname = NULL;
sort_ref_dir(dir);
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
if (do_for_each_entry_in_dir(dir, 0, name_conflict_fn, &data)) {
error("'%s' exists; cannot create '%s'",
data.conflicting_refname, refname);
return 0;
}
return 1;
}
struct packed_ref_cache {
struct ref_entry *root;
/*
* Count of references to the data structure in this instance,
* including the pointer from ref_cache::packed if any. The
* data will not be freed as long as the reference count is
* nonzero.
*/
unsigned int referrers;
/*
* Iff the packed-refs file associated with this instance is
* currently locked for writing, this points at the associated
* lock (which is owned by somebody else). The referrer count
* is also incremented when the file is locked and decremented
* when it is unlocked.
*/
struct lock_file *lock;
get_packed_ref_cache: reload packed-refs file when it changes Once we read the packed-refs file into memory, we cache it to save work on future ref lookups. However, our cache may be out of date with respect to what is on disk if another process is simultaneously packing the refs. Normally it is acceptable for us to be a little out of date, since there is no guarantee whether we read the file before or after the simultaneous update. However, there is an important special case: our packed-refs file must be up to date with respect to any loose refs we read. Otherwise, we risk the following race condition: 0. There exists a loose ref refs/heads/master. 1. Process A starts and looks up the ref "master". It first checks $GIT_DIR/master, which does not exist. It then loads (and caches) the packed-refs file to see if "master" exists in it, which it does not. 2. Meanwhile, process B runs "pack-refs --all --prune". It creates a new packed-refs file which contains refs/heads/master, and removes the loose copy at $GIT_DIR/refs/heads/master. 3. Process A continues its lookup, and eventually tries $GIT_DIR/refs/heads/master. It sees that the loose ref is missing, and falls back to the packed-refs file. But it examines its cached version, which does not have refs/heads/master. After trying a few other prefixes, it reports master as a non-existent ref. There are many variants (e.g., step 1 may involve process A looking up another ref entirely, so even a fully qualified refname can fail). One of the most interesting ones is if "refs/heads/master" is already packed. In that case process A will not see it as missing, but rather will report whatever value happened to be in the packed-refs file before process B repacked (which might be an arbitrarily old value). We can fix this by making sure we reload the packed-refs file from disk after looking at any loose refs. That's unacceptably slow, so we can check its stat()-validity as a proxy, and read it only when it appears to have changed. Reading the packed-refs file after performing any loose-ref system calls is sufficient because we know the ordering of the pack-refs process: it always makes sure the newly written packed-refs file is installed into place before pruning any loose refs. As long as those operations by B appear in their executed order to process A, by the time A sees the missing loose ref, the new packed-refs file must be in place. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-20 16:37:52 +08:00
/* The metadata from when this packed-refs cache was read */
struct stat_validity validity;
};
/*
* Future: need to be in "struct repository"
* when doing a full libification.
*/
static struct ref_cache {
struct ref_cache *next;
struct ref_entry *loose;
struct packed_ref_cache *packed;
/*
* The submodule name, or "" for the main repo. We allocate
* length 1 rather than FLEX_ARRAY so that the main ref_cache
* is initialized correctly.
*/
char name[1];
} ref_cache, *submodule_ref_caches;
/* Lock used for the main packed-refs file: */
static struct lock_file packlock;
/*
* Increment the reference count of *packed_refs.
*/
static void acquire_packed_ref_cache(struct packed_ref_cache *packed_refs)
{
packed_refs->referrers++;
}
/*
* Decrease the reference count of *packed_refs. If it goes to zero,
* free *packed_refs and return true; otherwise return false.
*/
static int release_packed_ref_cache(struct packed_ref_cache *packed_refs)
{
if (!--packed_refs->referrers) {
free_ref_entry(packed_refs->root);
get_packed_ref_cache: reload packed-refs file when it changes Once we read the packed-refs file into memory, we cache it to save work on future ref lookups. However, our cache may be out of date with respect to what is on disk if another process is simultaneously packing the refs. Normally it is acceptable for us to be a little out of date, since there is no guarantee whether we read the file before or after the simultaneous update. However, there is an important special case: our packed-refs file must be up to date with respect to any loose refs we read. Otherwise, we risk the following race condition: 0. There exists a loose ref refs/heads/master. 1. Process A starts and looks up the ref "master". It first checks $GIT_DIR/master, which does not exist. It then loads (and caches) the packed-refs file to see if "master" exists in it, which it does not. 2. Meanwhile, process B runs "pack-refs --all --prune". It creates a new packed-refs file which contains refs/heads/master, and removes the loose copy at $GIT_DIR/refs/heads/master. 3. Process A continues its lookup, and eventually tries $GIT_DIR/refs/heads/master. It sees that the loose ref is missing, and falls back to the packed-refs file. But it examines its cached version, which does not have refs/heads/master. After trying a few other prefixes, it reports master as a non-existent ref. There are many variants (e.g., step 1 may involve process A looking up another ref entirely, so even a fully qualified refname can fail). One of the most interesting ones is if "refs/heads/master" is already packed. In that case process A will not see it as missing, but rather will report whatever value happened to be in the packed-refs file before process B repacked (which might be an arbitrarily old value). We can fix this by making sure we reload the packed-refs file from disk after looking at any loose refs. That's unacceptably slow, so we can check its stat()-validity as a proxy, and read it only when it appears to have changed. Reading the packed-refs file after performing any loose-ref system calls is sufficient because we know the ordering of the pack-refs process: it always makes sure the newly written packed-refs file is installed into place before pruning any loose refs. As long as those operations by B appear in their executed order to process A, by the time A sees the missing loose ref, the new packed-refs file must be in place. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-20 16:37:52 +08:00
stat_validity_clear(&packed_refs->validity);
free(packed_refs);
return 1;
} else {
return 0;
}
}
static void clear_packed_ref_cache(struct ref_cache *refs)
{
if (refs->packed) {
struct packed_ref_cache *packed_refs = refs->packed;
if (packed_refs->lock)
die("internal error: packed-ref cache cleared while locked");
refs->packed = NULL;
release_packed_ref_cache(packed_refs);
}
}
static void clear_loose_ref_cache(struct ref_cache *refs)
{
if (refs->loose) {
free_ref_entry(refs->loose);
refs->loose = NULL;
}
}
static struct ref_cache *create_ref_cache(const char *submodule)
{
int len;
struct ref_cache *refs;
if (!submodule)
submodule = "";
len = strlen(submodule) + 1;
refs = xcalloc(1, sizeof(struct ref_cache) + len);
memcpy(refs->name, submodule, len);
return refs;
}
/*
* Return a pointer to a ref_cache for the specified submodule. For
* the main repository, use submodule==NULL. The returned structure
* will be allocated and initialized but not necessarily populated; it
* should not be freed.
*/
static struct ref_cache *get_ref_cache(const char *submodule)
{
struct ref_cache *refs;
if (!submodule || !*submodule)
return &ref_cache;
for (refs = submodule_ref_caches; refs; refs = refs->next)
if (!strcmp(submodule, refs->name))
return refs;
refs = create_ref_cache(submodule);
refs->next = submodule_ref_caches;
submodule_ref_caches = refs;
return refs;
}
void invalidate_ref_cache(const char *submodule)
{
struct ref_cache *refs = get_ref_cache(submodule);
clear_packed_ref_cache(refs);
clear_loose_ref_cache(refs);
}
/* The length of a peeled reference line in packed-refs, including EOL: */
#define PEELED_LINE_LENGTH 42
repack_without_ref(): write peeled refs in the rewritten file When a reference that existed in the packed-refs file is deleted, the packed-refs file must be rewritten. Previously, the file was rewritten without any peeled refs, even if the file contained peeled refs when it was read. This was not a bug, because the packed-refs file header didn't claim that the file contained peeled values. But it had a performance cost, because the repository would lose the benefit of having precomputed peeled references until pack-refs was run again. Teach repack_without_ref() to write peeled refs to the packed-refs file (regardless of whether they were present in the old version of the file). This means that if the old version of the packed-refs file was not fully peeled, then repack_without_ref() will have to peel references. To avoid the expense of reading lots of loose references, we take two shortcuts relative to pack-refs: * If the peeled value of a reference is already known (i.e., because it was read from the old version of the packed-refs file), then output that peeled value again without any checks. This is the usual code path and should avoid any noticeable overhead. (This is different than pack-refs, which always re-peels references.) * We don't verify that the packed ref is still current. It could be that a packed references is overridden by a loose reference, in which case the packed ref is no longer needed and might even refer to an object that has been garbage collected. But we don't check; instead, we just try to peel all references. If peeling is successful, the peeled value is written out (even though it might not be needed any more); if not, then the reference is silently omitted from the output. The extra overhead of peeling references in repack_without_ref() should only be incurred the first time the packed-refs file is written by a version of Git that knows about the "fully-peeled" attribute. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:29 +08:00
/*
* The packed-refs header line that we write out. Perhaps other
* traits will be added later. The trailing space is required.
*/
static const char PACKED_REFS_HEADER[] =
"# pack-refs with: peeled fully-peeled \n";
/*
* Parse one line from a packed-refs file. Write the SHA1 to sha1.
* Return a pointer to the refname within the line (null-terminated),
* or NULL if there was a problem.
*/
static const char *parse_ref_line(char *line, unsigned char *sha1)
{
/*
* 42: the answer to everything.
*
* In this case, it happens to be the answer to
* 40 (length of sha1 hex representation)
* +1 (space in between hex and name)
* +1 (newline at the end of the line)
*/
int len = strlen(line) - 42;
if (len <= 0)
return NULL;
if (get_sha1_hex(line, sha1) < 0)
return NULL;
if (!isspace(line[40]))
return NULL;
line += 41;
if (isspace(*line))
return NULL;
if (line[len] != '\n')
return NULL;
line[len] = 0;
return line;
}
/*
* Read f, which is a packed-refs file, into dir.
*
* A comment line of the form "# pack-refs with: " may contain zero or
* more traits. We interpret the traits as follows:
*
* No traits:
*
* Probably no references are peeled. But if the file contains a
* peeled value for a reference, we will use it.
*
* peeled:
*
* References under "refs/tags/", if they *can* be peeled, *are*
* peeled in this file. References outside of "refs/tags/" are
* probably not peeled even if they could have been, but if we find
* a peeled value for such a reference we will use it.
*
* fully-peeled:
*
* All references in the file that can be peeled are peeled.
* Inversely (and this is more important), any references in the
* file for which no peeled value is recorded is not peelable. This
* trait should typically be written alongside "peeled" for
* compatibility with older clients, but we do not require it
* (i.e., "peeled" is a no-op if "fully-peeled" is set).
*/
static void read_packed_refs(FILE *f, struct ref_dir *dir)
{
struct ref_entry *last = NULL;
char refline[PATH_MAX];
enum { PEELED_NONE, PEELED_TAGS, PEELED_FULLY } peeled = PEELED_NONE;
while (fgets(refline, sizeof(refline), f)) {
unsigned char sha1[20];
const char *refname;
static const char header[] = "# pack-refs with:";
if (!strncmp(refline, header, sizeof(header)-1)) {
const char *traits = refline + sizeof(header) - 1;
if (strstr(traits, " fully-peeled "))
peeled = PEELED_FULLY;
else if (strstr(traits, " peeled "))
peeled = PEELED_TAGS;
/* perhaps other traits later as well */
continue;
}
refname = parse_ref_line(refline, sha1);
if (refname) {
last = create_ref_entry(refname, sha1, REF_ISPACKED, 1);
if (peeled == PEELED_FULLY ||
(peeled == PEELED_TAGS && !prefixcmp(refname, "refs/tags/")))
last->flag |= REF_KNOWS_PEELED;
add_ref(dir, last);
continue;
}
if (last &&
refline[0] == '^' &&
strlen(refline) == PEELED_LINE_LENGTH &&
refline[PEELED_LINE_LENGTH - 1] == '\n' &&
!get_sha1_hex(refline + 1, sha1)) {
hashcpy(last->u.value.peeled, sha1);
/*
* Regardless of what the file header said,
* we definitely know the value of *this*
* reference:
*/
last->flag |= REF_KNOWS_PEELED;
}
}
}
/*
* Get the packed_ref_cache for the specified ref_cache, creating it
* if necessary.
*/
static struct packed_ref_cache *get_packed_ref_cache(struct ref_cache *refs)
{
get_packed_ref_cache: reload packed-refs file when it changes Once we read the packed-refs file into memory, we cache it to save work on future ref lookups. However, our cache may be out of date with respect to what is on disk if another process is simultaneously packing the refs. Normally it is acceptable for us to be a little out of date, since there is no guarantee whether we read the file before or after the simultaneous update. However, there is an important special case: our packed-refs file must be up to date with respect to any loose refs we read. Otherwise, we risk the following race condition: 0. There exists a loose ref refs/heads/master. 1. Process A starts and looks up the ref "master". It first checks $GIT_DIR/master, which does not exist. It then loads (and caches) the packed-refs file to see if "master" exists in it, which it does not. 2. Meanwhile, process B runs "pack-refs --all --prune". It creates a new packed-refs file which contains refs/heads/master, and removes the loose copy at $GIT_DIR/refs/heads/master. 3. Process A continues its lookup, and eventually tries $GIT_DIR/refs/heads/master. It sees that the loose ref is missing, and falls back to the packed-refs file. But it examines its cached version, which does not have refs/heads/master. After trying a few other prefixes, it reports master as a non-existent ref. There are many variants (e.g., step 1 may involve process A looking up another ref entirely, so even a fully qualified refname can fail). One of the most interesting ones is if "refs/heads/master" is already packed. In that case process A will not see it as missing, but rather will report whatever value happened to be in the packed-refs file before process B repacked (which might be an arbitrarily old value). We can fix this by making sure we reload the packed-refs file from disk after looking at any loose refs. That's unacceptably slow, so we can check its stat()-validity as a proxy, and read it only when it appears to have changed. Reading the packed-refs file after performing any loose-ref system calls is sufficient because we know the ordering of the pack-refs process: it always makes sure the newly written packed-refs file is installed into place before pruning any loose refs. As long as those operations by B appear in their executed order to process A, by the time A sees the missing loose ref, the new packed-refs file must be in place. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-20 16:37:52 +08:00
const char *packed_refs_file;
if (*refs->name)
packed_refs_file = git_path_submodule(refs->name, "packed-refs");
else
packed_refs_file = git_path("packed-refs");
if (refs->packed &&
!stat_validity_check(&refs->packed->validity, packed_refs_file))
clear_packed_ref_cache(refs);
if (!refs->packed) {
FILE *f;
refs->packed = xcalloc(1, sizeof(*refs->packed));
acquire_packed_ref_cache(refs->packed);
refs->packed->root = create_dir_entry(refs, "", 0, 0);
f = fopen(packed_refs_file, "r");
if (f) {
get_packed_ref_cache: reload packed-refs file when it changes Once we read the packed-refs file into memory, we cache it to save work on future ref lookups. However, our cache may be out of date with respect to what is on disk if another process is simultaneously packing the refs. Normally it is acceptable for us to be a little out of date, since there is no guarantee whether we read the file before or after the simultaneous update. However, there is an important special case: our packed-refs file must be up to date with respect to any loose refs we read. Otherwise, we risk the following race condition: 0. There exists a loose ref refs/heads/master. 1. Process A starts and looks up the ref "master". It first checks $GIT_DIR/master, which does not exist. It then loads (and caches) the packed-refs file to see if "master" exists in it, which it does not. 2. Meanwhile, process B runs "pack-refs --all --prune". It creates a new packed-refs file which contains refs/heads/master, and removes the loose copy at $GIT_DIR/refs/heads/master. 3. Process A continues its lookup, and eventually tries $GIT_DIR/refs/heads/master. It sees that the loose ref is missing, and falls back to the packed-refs file. But it examines its cached version, which does not have refs/heads/master. After trying a few other prefixes, it reports master as a non-existent ref. There are many variants (e.g., step 1 may involve process A looking up another ref entirely, so even a fully qualified refname can fail). One of the most interesting ones is if "refs/heads/master" is already packed. In that case process A will not see it as missing, but rather will report whatever value happened to be in the packed-refs file before process B repacked (which might be an arbitrarily old value). We can fix this by making sure we reload the packed-refs file from disk after looking at any loose refs. That's unacceptably slow, so we can check its stat()-validity as a proxy, and read it only when it appears to have changed. Reading the packed-refs file after performing any loose-ref system calls is sufficient because we know the ordering of the pack-refs process: it always makes sure the newly written packed-refs file is installed into place before pruning any loose refs. As long as those operations by B appear in their executed order to process A, by the time A sees the missing loose ref, the new packed-refs file must be in place. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-20 16:37:52 +08:00
stat_validity_update(&refs->packed->validity, fileno(f));
read_packed_refs(f, get_ref_dir(refs->packed->root));
fclose(f);
}
}
return refs->packed;
}
static struct ref_dir *get_packed_ref_dir(struct packed_ref_cache *packed_ref_cache)
{
return get_ref_dir(packed_ref_cache->root);
}
static struct ref_dir *get_packed_refs(struct ref_cache *refs)
{
return get_packed_ref_dir(get_packed_ref_cache(refs));
}
void add_packed_ref(const char *refname, const unsigned char *sha1)
{
struct packed_ref_cache *packed_ref_cache =
get_packed_ref_cache(&ref_cache);
if (!packed_ref_cache->lock)
die("internal error: packed refs not locked");
add_ref(get_packed_ref_dir(packed_ref_cache),
create_ref_entry(refname, sha1, REF_ISPACKED, 1));
}
/*
* Read the loose references from the namespace dirname into dir
* (without recursing). dirname must end with '/'. dir must be the
* directory entry corresponding to dirname.
*/
static void read_loose_refs(const char *dirname, struct ref_dir *dir)
{
struct ref_cache *refs = dir->ref_cache;
DIR *d;
const char *path;
struct dirent *de;
int dirnamelen = strlen(dirname);
struct strbuf refname;
if (*refs->name)
path = git_path_submodule(refs->name, "%s", dirname);
else
path = git_path("%s", dirname);
d = opendir(path);
if (!d)
return;
strbuf_init(&refname, dirnamelen + 257);
strbuf_add(&refname, dirname, dirnamelen);
while ((de = readdir(d)) != NULL) {
unsigned char sha1[20];
struct stat st;
int flag;
const char *refdir;
if (de->d_name[0] == '.')
continue;
if (has_extension(de->d_name, ".lock"))
continue;
strbuf_addstr(&refname, de->d_name);
refdir = *refs->name
? git_path_submodule(refs->name, "%s", refname.buf)
: git_path("%s", refname.buf);
if (stat(refdir, &st) < 0) {
; /* silently ignore */
} else if (S_ISDIR(st.st_mode)) {
strbuf_addch(&refname, '/');
add_entry_to_dir(dir,
create_dir_entry(refs, refname.buf,
refname.len, 1));
} else {
if (*refs->name) {
hashclr(sha1);
flag = 0;
if (resolve_gitlink_ref(refs->name, refname.buf, sha1) < 0) {
hashclr(sha1);
flag |= REF_ISBROKEN;
}
} else if (read_ref_full(refname.buf, sha1, 1, &flag)) {
hashclr(sha1);
flag |= REF_ISBROKEN;
}
add_entry_to_dir(dir,
create_ref_entry(refname.buf, sha1, flag, 1));
}
strbuf_setlen(&refname, dirnamelen);
}
strbuf_release(&refname);
closedir(d);
}
static struct ref_dir *get_loose_refs(struct ref_cache *refs)
{
if (!refs->loose) {
/*
* Mark the top-level directory complete because we
* are about to read the only subdirectory that can
* hold references:
*/
refs->loose = create_dir_entry(refs, "", 0, 0);
/*
* Create an incomplete entry for "refs/":
*/
add_entry_to_dir(get_ref_dir(refs->loose),
create_dir_entry(refs, "refs/", 5, 1));
}
return get_ref_dir(refs->loose);
}
/* We allow "recursive" symbolic refs. Only within reason, though */
#define MAXDEPTH 5
#define MAXREFLEN (1024)
/*
* Called by resolve_gitlink_ref_recursive() after it failed to read
* from the loose refs in ref_cache refs. Find <refname> in the
* packed-refs file for the submodule.
*/
static int resolve_gitlink_packed_ref(struct ref_cache *refs,
const char *refname, unsigned char *sha1)
{
struct ref_entry *ref;
struct ref_dir *dir = get_packed_refs(refs);
ref = find_ref(dir, refname);
if (ref == NULL)
return -1;
memcpy(sha1, ref->u.value.sha1, 20);
return 0;
}
static int resolve_gitlink_ref_recursive(struct ref_cache *refs,
const char *refname, unsigned char *sha1,
int recursion)
{
int fd, len;
char buffer[128], *p;
char *path;
if (recursion > MAXDEPTH || strlen(refname) > MAXREFLEN)
return -1;
path = *refs->name
? git_path_submodule(refs->name, "%s", refname)
: git_path("%s", refname);
fd = open(path, O_RDONLY);
if (fd < 0)
return resolve_gitlink_packed_ref(refs, refname, sha1);
len = read(fd, buffer, sizeof(buffer)-1);
close(fd);
if (len < 0)
return -1;
while (len && isspace(buffer[len-1]))
len--;
buffer[len] = 0;
/* Was it a detached head or an old-fashioned symlink? */
if (!get_sha1_hex(buffer, sha1))
return 0;
/* Symref? */
if (strncmp(buffer, "ref:", 4))
return -1;
p = buffer + 4;
while (isspace(*p))
p++;
return resolve_gitlink_ref_recursive(refs, p, sha1, recursion+1);
}
int resolve_gitlink_ref(const char *path, const char *refname, unsigned char *sha1)
{
int len = strlen(path), retval;
char *submodule;
struct ref_cache *refs;
while (len && path[len-1] == '/')
len--;
if (!len)
return -1;
submodule = xstrndup(path, len);
refs = get_ref_cache(submodule);
free(submodule);
retval = resolve_gitlink_ref_recursive(refs, refname, sha1, 0);
return retval;
}
/*
* Return the ref_entry for the given refname from the packed
* references. If it does not exist, return NULL.
*/
static struct ref_entry *get_packed_ref(const char *refname)
{
return find_ref(get_packed_refs(&ref_cache), refname);
}
/*
* A loose ref file doesn't exist; check for a packed ref. The
* options are forwarded from resolve_safe_unsafe().
*/
static const char *handle_missing_loose_ref(const char *refname,
unsigned char *sha1,
int reading,
int *flag)
{
struct ref_entry *entry;
/*
* The loose reference file does not exist; check for a packed
* reference.
*/
entry = get_packed_ref(refname);
if (entry) {
hashcpy(sha1, entry->u.value.sha1);
if (flag)
*flag |= REF_ISPACKED;
return refname;
}
/* The reference is not a packed reference, either. */
if (reading) {
return NULL;
} else {
hashclr(sha1);
return refname;
}
}
const char *resolve_ref_unsafe(const char *refname, unsigned char *sha1, int reading, int *flag)
{
int depth = MAXDEPTH;
ssize_t len;
char buffer[256];
static char refname_buffer[256];
if (flag)
*flag = 0;
if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL))
return NULL;
for (;;) {
char path[PATH_MAX];
struct stat st;
char *buf;
int fd;
if (--depth < 0)
return NULL;
git_snpath(path, sizeof(path), "%s", refname);
resolve_ref_unsafe(): close race condition reading loose refs We read loose references in two steps. The code is roughly: lstat() if error ENOENT: loose ref is missing; look for corresponding packed ref else if S_ISLNK: readlink() if error: report failure else if S_ISDIR: report failure else open() if error: report failure read() The problem is that the first filesystem call, to lstat(), is not atomic with the second filesystem call, to readlink() or open(). Therefore it is possible for another process to change the file between our two calls, for example: * If the other process deletes the file, our second call will fail with ENOENT, which we *should* interpret as "loose ref is missing; look for corresponding packed ref". This can arise if the other process is pack-refs; it might have just written a new packed-refs file containing the old contents of the reference then deleted the loose ref. * If the other process changes a symlink into a plain file, our call to readlink() will fail with EINVAL, which we *should* respond to by trying to open() and read() the file. The old code treats the reference as missing in both of these cases, which is incorrect. So instead, handle errors more selectively: if the result of readline()/open() is a failure that is inconsistent with the result of the previous lstat(), then something is fishy. In this case jump back and start over again with a fresh call to lstat(). One race is still possible and undetected: another process could change the file from a regular file into a symlink between the call to lstat and the call to open(). The open() call would silently follow the symlink and not know that something is wrong. This situation could be detected in two ways: * On systems that support O_NOFOLLOW, pass that option to the open(). * On other systems, call fstat() on the fd returned by open() and make sure that it agrees with the stat info from the original lstat(). However, we don't use symlinks anymore, so this situation is unlikely. Moreover, it doesn't appear that treating a symlink as a regular file would have grave consequences; after all, this is exactly how the code handles non-relative symlinks. So this commit leaves that race unaddressed. Note that this solves only the part of the race within resolve_ref_unsafe. In the situation described above, we may still be depending on a cached view of the packed-refs file; that race will be dealt with in a future patch. This problem was reported and diagnosed by Jeff King <peff@peff.net>, and this solution is derived from his patch. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Reviewed-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-19 14:36:28 +08:00
/*
* We might have to loop back here to avoid a race
* condition: first we lstat() the file, then we try
* to read it as a link or as a file. But if somebody
* changes the type of the file (file <-> directory
* <-> symlink) between the lstat() and reading, then
* we don't want to report that as an error but rather
* try again starting with the lstat().
*/
stat_ref:
if (lstat(path, &st) < 0) {
if (errno == ENOENT)
return handle_missing_loose_ref(refname, sha1,
reading, flag);
else
return NULL;
}
/* Follow "normalized" - ie "refs/.." symlinks by hand */
if (S_ISLNK(st.st_mode)) {
len = readlink(path, buffer, sizeof(buffer)-1);
resolve_ref_unsafe(): close race condition reading loose refs We read loose references in two steps. The code is roughly: lstat() if error ENOENT: loose ref is missing; look for corresponding packed ref else if S_ISLNK: readlink() if error: report failure else if S_ISDIR: report failure else open() if error: report failure read() The problem is that the first filesystem call, to lstat(), is not atomic with the second filesystem call, to readlink() or open(). Therefore it is possible for another process to change the file between our two calls, for example: * If the other process deletes the file, our second call will fail with ENOENT, which we *should* interpret as "loose ref is missing; look for corresponding packed ref". This can arise if the other process is pack-refs; it might have just written a new packed-refs file containing the old contents of the reference then deleted the loose ref. * If the other process changes a symlink into a plain file, our call to readlink() will fail with EINVAL, which we *should* respond to by trying to open() and read() the file. The old code treats the reference as missing in both of these cases, which is incorrect. So instead, handle errors more selectively: if the result of readline()/open() is a failure that is inconsistent with the result of the previous lstat(), then something is fishy. In this case jump back and start over again with a fresh call to lstat(). One race is still possible and undetected: another process could change the file from a regular file into a symlink between the call to lstat and the call to open(). The open() call would silently follow the symlink and not know that something is wrong. This situation could be detected in two ways: * On systems that support O_NOFOLLOW, pass that option to the open(). * On other systems, call fstat() on the fd returned by open() and make sure that it agrees with the stat info from the original lstat(). However, we don't use symlinks anymore, so this situation is unlikely. Moreover, it doesn't appear that treating a symlink as a regular file would have grave consequences; after all, this is exactly how the code handles non-relative symlinks. So this commit leaves that race unaddressed. Note that this solves only the part of the race within resolve_ref_unsafe. In the situation described above, we may still be depending on a cached view of the packed-refs file; that race will be dealt with in a future patch. This problem was reported and diagnosed by Jeff King <peff@peff.net>, and this solution is derived from his patch. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Reviewed-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-19 14:36:28 +08:00
if (len < 0) {
if (errno == ENOENT || errno == EINVAL)
/* inconsistent with lstat; retry */
goto stat_ref;
else
return NULL;
}
buffer[len] = 0;
if (!prefixcmp(buffer, "refs/") &&
!check_refname_format(buffer, 0)) {
strcpy(refname_buffer, buffer);
refname = refname_buffer;
if (flag)
*flag |= REF_ISSYMREF;
continue;
}
}
/* Is it a directory? */
if (S_ISDIR(st.st_mode)) {
errno = EISDIR;
return NULL;
}
/*
* Anything else, just open it and try to use it as
* a ref
*/
fd = open(path, O_RDONLY);
resolve_ref_unsafe(): close race condition reading loose refs We read loose references in two steps. The code is roughly: lstat() if error ENOENT: loose ref is missing; look for corresponding packed ref else if S_ISLNK: readlink() if error: report failure else if S_ISDIR: report failure else open() if error: report failure read() The problem is that the first filesystem call, to lstat(), is not atomic with the second filesystem call, to readlink() or open(). Therefore it is possible for another process to change the file between our two calls, for example: * If the other process deletes the file, our second call will fail with ENOENT, which we *should* interpret as "loose ref is missing; look for corresponding packed ref". This can arise if the other process is pack-refs; it might have just written a new packed-refs file containing the old contents of the reference then deleted the loose ref. * If the other process changes a symlink into a plain file, our call to readlink() will fail with EINVAL, which we *should* respond to by trying to open() and read() the file. The old code treats the reference as missing in both of these cases, which is incorrect. So instead, handle errors more selectively: if the result of readline()/open() is a failure that is inconsistent with the result of the previous lstat(), then something is fishy. In this case jump back and start over again with a fresh call to lstat(). One race is still possible and undetected: another process could change the file from a regular file into a symlink between the call to lstat and the call to open(). The open() call would silently follow the symlink and not know that something is wrong. This situation could be detected in two ways: * On systems that support O_NOFOLLOW, pass that option to the open(). * On other systems, call fstat() on the fd returned by open() and make sure that it agrees with the stat info from the original lstat(). However, we don't use symlinks anymore, so this situation is unlikely. Moreover, it doesn't appear that treating a symlink as a regular file would have grave consequences; after all, this is exactly how the code handles non-relative symlinks. So this commit leaves that race unaddressed. Note that this solves only the part of the race within resolve_ref_unsafe. In the situation described above, we may still be depending on a cached view of the packed-refs file; that race will be dealt with in a future patch. This problem was reported and diagnosed by Jeff King <peff@peff.net>, and this solution is derived from his patch. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Reviewed-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-19 14:36:28 +08:00
if (fd < 0) {
if (errno == ENOENT)
/* inconsistent with lstat; retry */
goto stat_ref;
else
return NULL;
}
len = read_in_full(fd, buffer, sizeof(buffer)-1);
close(fd);
if (len < 0)
return NULL;
while (len && isspace(buffer[len-1]))
len--;
buffer[len] = '\0';
/*
* Is it a symbolic ref?
*/
if (prefixcmp(buffer, "ref:")) {
/*
* Please note that FETCH_HEAD has a second
* line containing other data.
*/
if (get_sha1_hex(buffer, sha1) ||
(buffer[40] != '\0' && !isspace(buffer[40]))) {
if (flag)
*flag |= REF_ISBROKEN;
return NULL;
}
return refname;
}
if (flag)
*flag |= REF_ISSYMREF;
buf = buffer + 4;
while (isspace(*buf))
buf++;
if (check_refname_format(buf, REFNAME_ALLOW_ONELEVEL)) {
if (flag)
*flag |= REF_ISBROKEN;
return NULL;
}
refname = strcpy(refname_buffer, buf);
}
}
char *resolve_refdup(const char *ref, unsigned char *sha1, int reading, int *flag)
{
const char *ret = resolve_ref_unsafe(ref, sha1, reading, flag);
return ret ? xstrdup(ret) : NULL;
}
/* The argument to filter_refs */
struct ref_filter {
const char *pattern;
each_ref_fn *fn;
void *cb_data;
};
int read_ref_full(const char *refname, unsigned char *sha1, int reading, int *flags)
{
if (resolve_ref_unsafe(refname, sha1, reading, flags))
return 0;
return -1;
}
int read_ref(const char *refname, unsigned char *sha1)
{
return read_ref_full(refname, sha1, 1, NULL);
}
int ref_exists(const char *refname)
{
unsigned char sha1[20];
return !!resolve_ref_unsafe(refname, sha1, 1, NULL);
}
static int filter_refs(const char *refname, const unsigned char *sha1, int flags,
void *data)
{
struct ref_filter *filter = (struct ref_filter *)data;
if (fnmatch(filter->pattern, refname, 0))
return 0;
return filter->fn(refname, sha1, flags, filter->cb_data);
}
enum peel_status {
/* object was peeled successfully: */
PEEL_PEELED = 0,
/*
* object cannot be peeled because the named object (or an
* object referred to by a tag in the peel chain), does not
* exist.
*/
PEEL_INVALID = -1,
/* object cannot be peeled because it is not a tag: */
PEEL_NON_TAG = -2,
/* ref_entry contains no peeled value because it is a symref: */
PEEL_IS_SYMREF = -3,
/*
* ref_entry cannot be peeled because it is broken (i.e., the
* symbolic reference cannot even be resolved to an object
* name):
*/
PEEL_BROKEN = -4
};
/*
* Peel the named object; i.e., if the object is a tag, resolve the
* tag recursively until a non-tag is found. If successful, store the
* result to sha1 and return PEEL_PEELED. If the object is not a tag
* or is not valid, return PEEL_NON_TAG or PEEL_INVALID, respectively,
* and leave sha1 unchanged.
*/
static enum peel_status peel_object(const unsigned char *name, unsigned char *sha1)
{
struct object *o = lookup_unknown_object(name);
if (o->type == OBJ_NONE) {
int type = sha1_object_info(name, NULL);
if (type < 0)
return PEEL_INVALID;
o->type = type;
}
if (o->type != OBJ_TAG)
return PEEL_NON_TAG;
o = deref_tag_noverify(o);
if (!o)
return PEEL_INVALID;
hashcpy(sha1, o->sha1);
return PEEL_PEELED;
}
/*
* Peel the entry (if possible) and return its new peel_status. If
* repeel is true, re-peel the entry even if there is an old peeled
* value that is already stored in it.
repack_without_ref(): write peeled refs in the rewritten file When a reference that existed in the packed-refs file is deleted, the packed-refs file must be rewritten. Previously, the file was rewritten without any peeled refs, even if the file contained peeled refs when it was read. This was not a bug, because the packed-refs file header didn't claim that the file contained peeled values. But it had a performance cost, because the repository would lose the benefit of having precomputed peeled references until pack-refs was run again. Teach repack_without_ref() to write peeled refs to the packed-refs file (regardless of whether they were present in the old version of the file). This means that if the old version of the packed-refs file was not fully peeled, then repack_without_ref() will have to peel references. To avoid the expense of reading lots of loose references, we take two shortcuts relative to pack-refs: * If the peeled value of a reference is already known (i.e., because it was read from the old version of the packed-refs file), then output that peeled value again without any checks. This is the usual code path and should avoid any noticeable overhead. (This is different than pack-refs, which always re-peels references.) * We don't verify that the packed ref is still current. It could be that a packed references is overridden by a loose reference, in which case the packed ref is no longer needed and might even refer to an object that has been garbage collected. But we don't check; instead, we just try to peel all references. If peeling is successful, the peeled value is written out (even though it might not be needed any more); if not, then the reference is silently omitted from the output. The extra overhead of peeling references in repack_without_ref() should only be incurred the first time the packed-refs file is written by a version of Git that knows about the "fully-peeled" attribute. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:29 +08:00
*
* It is OK to call this function with a packed reference entry that
* might be stale and might even refer to an object that has since
* been garbage-collected. In such a case, if the entry has
* REF_KNOWS_PEELED then leave the status unchanged and return
* PEEL_PEELED or PEEL_NON_TAG; otherwise, return PEEL_INVALID.
*/
static enum peel_status peel_entry(struct ref_entry *entry, int repeel)
{
enum peel_status status;
if (entry->flag & REF_KNOWS_PEELED) {
if (repeel) {
entry->flag &= ~REF_KNOWS_PEELED;
hashclr(entry->u.value.peeled);
} else {
return is_null_sha1(entry->u.value.peeled) ?
PEEL_NON_TAG : PEEL_PEELED;
}
}
if (entry->flag & REF_ISBROKEN)
return PEEL_BROKEN;
if (entry->flag & REF_ISSYMREF)
return PEEL_IS_SYMREF;
status = peel_object(entry->u.value.sha1, entry->u.value.peeled);
if (status == PEEL_PEELED || status == PEEL_NON_TAG)
entry->flag |= REF_KNOWS_PEELED;
return status;
}
int peel_ref(const char *refname, unsigned char *sha1)
{
int flag;
unsigned char base[20];
if (current_ref && (current_ref->name == refname
|| !strcmp(current_ref->name, refname))) {
if (peel_entry(current_ref, 0))
return -1;
hashcpy(sha1, current_ref->u.value.peeled);
return 0;
}
if (read_ref_full(refname, base, 1, &flag))
return -1;
/*
* If the reference is packed, read its ref_entry from the
* cache in the hope that we already know its peeled value.
* We only try this optimization on packed references because
* (a) forcing the filling of the loose reference cache could
* be expensive and (b) loose references anyway usually do not
* have REF_KNOWS_PEELED.
*/
if (flag & REF_ISPACKED) {
struct ref_entry *r = get_packed_ref(refname);
if (r) {
if (peel_entry(r, 0))
return -1;
hashcpy(sha1, r->u.value.peeled);
return 0;
}
}
return peel_object(base, sha1);
}
struct warn_if_dangling_data {
FILE *fp;
const char *refname;
const char *msg_fmt;
};
static int warn_if_dangling_symref(const char *refname, const unsigned char *sha1,
int flags, void *cb_data)
{
struct warn_if_dangling_data *d = cb_data;
const char *resolves_to;
unsigned char junk[20];
if (!(flags & REF_ISSYMREF))
return 0;
resolves_to = resolve_ref_unsafe(refname, junk, 0, NULL);
if (!resolves_to || strcmp(resolves_to, d->refname))
return 0;
fprintf(d->fp, d->msg_fmt, refname);
fputc('\n', d->fp);
return 0;
}
void warn_dangling_symref(FILE *fp, const char *msg_fmt, const char *refname)
{
struct warn_if_dangling_data data;
data.fp = fp;
data.refname = refname;
data.msg_fmt = msg_fmt;
for_each_rawref(warn_if_dangling_symref, &data);
}
/*
* Call fn for each reference in the specified ref_cache, omitting
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
* references not in the containing_dir of base. fn is called for all
* references, including broken ones. If fn ever returns a non-zero
* value, stop the iteration and return that value; otherwise, return
* 0.
*/
static int do_for_each_entry(struct ref_cache *refs, const char *base,
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
each_ref_entry_fn fn, void *cb_data)
{
for_each_ref: load all loose refs before packed refs If we are iterating through the refs using for_each_ref (or any of its sister functions), we can get into a race condition with a simultaneous "pack-refs --prune" that looks like this: 0. We have a large number of loose refs, and a few packed refs. refs/heads/z/foo is loose, with no matching entry in the packed-refs file. 1. Process A starts iterating through the refs. It loads the packed-refs file from disk, then starts lazily traversing through the loose ref directories. 2. Process B, running "pack-refs --prune", writes out the new packed-refs file. It then deletes the newly packed refs, including refs/heads/z/foo. 3. Meanwhile, process A has finally gotten to refs/heads/z (it traverses alphabetically). It descends, but finds nothing there. It checks its cached view of the packed-refs file, but it does not mention anything in "refs/heads/z/" at all (it predates the new file written by B in step 2). The traversal completes successfully without mentioning refs/heads/z/foo at all (the name, of course, isn't important; but the more refs you have and the farther down the alphabetical list a ref is, the more likely it is to hit the race). If refs/heads/z/foo did exist in the packed refs file at state 0, we would see an entry for it, but it would show whatever sha1 the ref had the last time it was packed (which could be an arbitrarily long time ago). This can be especially dangerous when process A is "git prune", as it means our set of reachable tips will be incomplete, and we may erroneously prune objects reachable from that tip (the same thing can happen if "repack -ad" is used, as it simply drops unreachable objects that are packed). This patch solves it by loading all of the loose refs for our traversal into our in-memory cache, and then refreshing the packed-refs cache. Because a pack-refs writer will always put the new packed-refs file into place before starting the prune, we know that any loose refs we fail to see will either truly be missing, or will have already been put in the packed-refs file by the time we refresh. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-20 16:37:53 +08:00
struct packed_ref_cache *packed_ref_cache;
struct ref_dir *loose_dir;
struct ref_dir *packed_dir;
int retval = 0;
for_each_ref: load all loose refs before packed refs If we are iterating through the refs using for_each_ref (or any of its sister functions), we can get into a race condition with a simultaneous "pack-refs --prune" that looks like this: 0. We have a large number of loose refs, and a few packed refs. refs/heads/z/foo is loose, with no matching entry in the packed-refs file. 1. Process A starts iterating through the refs. It loads the packed-refs file from disk, then starts lazily traversing through the loose ref directories. 2. Process B, running "pack-refs --prune", writes out the new packed-refs file. It then deletes the newly packed refs, including refs/heads/z/foo. 3. Meanwhile, process A has finally gotten to refs/heads/z (it traverses alphabetically). It descends, but finds nothing there. It checks its cached view of the packed-refs file, but it does not mention anything in "refs/heads/z/" at all (it predates the new file written by B in step 2). The traversal completes successfully without mentioning refs/heads/z/foo at all (the name, of course, isn't important; but the more refs you have and the farther down the alphabetical list a ref is, the more likely it is to hit the race). If refs/heads/z/foo did exist in the packed refs file at state 0, we would see an entry for it, but it would show whatever sha1 the ref had the last time it was packed (which could be an arbitrarily long time ago). This can be especially dangerous when process A is "git prune", as it means our set of reachable tips will be incomplete, and we may erroneously prune objects reachable from that tip (the same thing can happen if "repack -ad" is used, as it simply drops unreachable objects that are packed). This patch solves it by loading all of the loose refs for our traversal into our in-memory cache, and then refreshing the packed-refs cache. Because a pack-refs writer will always put the new packed-refs file into place before starting the prune, we know that any loose refs we fail to see will either truly be missing, or will have already been put in the packed-refs file by the time we refresh. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-20 16:37:53 +08:00
/*
* We must make sure that all loose refs are read before accessing the
* packed-refs file; this avoids a race condition in which loose refs
* are migrated to the packed-refs file by a simultaneous process, but
* our in-memory view is from before the migration. get_packed_ref_cache()
* takes care of making sure our view is up to date with what is on
* disk.
*/
loose_dir = get_loose_refs(refs);
if (base && *base) {
loose_dir = find_containing_dir(loose_dir, base, 0);
}
for_each_ref: load all loose refs before packed refs If we are iterating through the refs using for_each_ref (or any of its sister functions), we can get into a race condition with a simultaneous "pack-refs --prune" that looks like this: 0. We have a large number of loose refs, and a few packed refs. refs/heads/z/foo is loose, with no matching entry in the packed-refs file. 1. Process A starts iterating through the refs. It loads the packed-refs file from disk, then starts lazily traversing through the loose ref directories. 2. Process B, running "pack-refs --prune", writes out the new packed-refs file. It then deletes the newly packed refs, including refs/heads/z/foo. 3. Meanwhile, process A has finally gotten to refs/heads/z (it traverses alphabetically). It descends, but finds nothing there. It checks its cached view of the packed-refs file, but it does not mention anything in "refs/heads/z/" at all (it predates the new file written by B in step 2). The traversal completes successfully without mentioning refs/heads/z/foo at all (the name, of course, isn't important; but the more refs you have and the farther down the alphabetical list a ref is, the more likely it is to hit the race). If refs/heads/z/foo did exist in the packed refs file at state 0, we would see an entry for it, but it would show whatever sha1 the ref had the last time it was packed (which could be an arbitrarily long time ago). This can be especially dangerous when process A is "git prune", as it means our set of reachable tips will be incomplete, and we may erroneously prune objects reachable from that tip (the same thing can happen if "repack -ad" is used, as it simply drops unreachable objects that are packed). This patch solves it by loading all of the loose refs for our traversal into our in-memory cache, and then refreshing the packed-refs cache. Because a pack-refs writer will always put the new packed-refs file into place before starting the prune, we know that any loose refs we fail to see will either truly be missing, or will have already been put in the packed-refs file by the time we refresh. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-20 16:37:53 +08:00
if (loose_dir)
prime_ref_dir(loose_dir);
packed_ref_cache = get_packed_ref_cache(refs);
acquire_packed_ref_cache(packed_ref_cache);
for_each_ref: load all loose refs before packed refs If we are iterating through the refs using for_each_ref (or any of its sister functions), we can get into a race condition with a simultaneous "pack-refs --prune" that looks like this: 0. We have a large number of loose refs, and a few packed refs. refs/heads/z/foo is loose, with no matching entry in the packed-refs file. 1. Process A starts iterating through the refs. It loads the packed-refs file from disk, then starts lazily traversing through the loose ref directories. 2. Process B, running "pack-refs --prune", writes out the new packed-refs file. It then deletes the newly packed refs, including refs/heads/z/foo. 3. Meanwhile, process A has finally gotten to refs/heads/z (it traverses alphabetically). It descends, but finds nothing there. It checks its cached view of the packed-refs file, but it does not mention anything in "refs/heads/z/" at all (it predates the new file written by B in step 2). The traversal completes successfully without mentioning refs/heads/z/foo at all (the name, of course, isn't important; but the more refs you have and the farther down the alphabetical list a ref is, the more likely it is to hit the race). If refs/heads/z/foo did exist in the packed refs file at state 0, we would see an entry for it, but it would show whatever sha1 the ref had the last time it was packed (which could be an arbitrarily long time ago). This can be especially dangerous when process A is "git prune", as it means our set of reachable tips will be incomplete, and we may erroneously prune objects reachable from that tip (the same thing can happen if "repack -ad" is used, as it simply drops unreachable objects that are packed). This patch solves it by loading all of the loose refs for our traversal into our in-memory cache, and then refreshing the packed-refs cache. Because a pack-refs writer will always put the new packed-refs file into place before starting the prune, we know that any loose refs we fail to see will either truly be missing, or will have already been put in the packed-refs file by the time we refresh. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-20 16:37:53 +08:00
packed_dir = get_packed_ref_dir(packed_ref_cache);
if (base && *base) {
packed_dir = find_containing_dir(packed_dir, base, 0);
}
if (packed_dir && loose_dir) {
sort_ref_dir(packed_dir);
sort_ref_dir(loose_dir);
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
retval = do_for_each_entry_in_dirs(
packed_dir, loose_dir, fn, cb_data);
} else if (packed_dir) {
sort_ref_dir(packed_dir);
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
retval = do_for_each_entry_in_dir(
packed_dir, 0, fn, cb_data);
} else if (loose_dir) {
sort_ref_dir(loose_dir);
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
retval = do_for_each_entry_in_dir(
loose_dir, 0, fn, cb_data);
}
release_packed_ref_cache(packed_ref_cache);
return retval;
}
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
/*
* Call fn for each reference in the specified ref_cache for which the
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
* refname begins with base. If trim is non-zero, then trim that many
* characters off the beginning of each refname before passing the
* refname to fn. flags can be DO_FOR_EACH_INCLUDE_BROKEN to include
* broken references in the iteration. If fn ever returns a non-zero
* value, stop the iteration and return that value; otherwise, return
* 0.
*/
static int do_for_each_ref(struct ref_cache *refs, const char *base,
each_ref_fn fn, int trim, int flags, void *cb_data)
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
{
struct ref_entry_cb data;
data.base = base;
data.trim = trim;
data.flags = flags;
data.fn = fn;
data.cb_data = cb_data;
return do_for_each_entry(refs, base, do_one_ref, &data);
refs: change the internal reference-iteration API Establish an internal API for iterating over references, which gives the callback functions direct access to the ref_entry structure describing the reference. (Do not change the iteration API that is exposed outside of the module.) Define a new internal callback signature int each_ref_entry_fn(struct ref_entry *entry, void *cb_data) Change do_for_each_ref_in_dir() and do_for_each_ref_in_dirs() to accept each_ref_entry_fn callbacks, and rename them to do_for_each_entry_in_dir() and do_for_each_entry_in_dirs(), respectively. Adapt their callers accordingly. Add a new function do_for_each_entry() analogous to do_for_each_ref() but using the new callback style. Change do_one_ref() into an each_ref_entry_fn that does some bookkeeping and then calls a wrapped each_ref_fn. Reimplement do_for_each_ref() in terms of do_for_each_entry(), using do_one_ref() as an adapter. Please note that the responsibility for setting current_ref remains in do_one_ref(), which means that current_ref is *not* set when iterating over references via the new internal API. This is not a disadvantage, because current_ref is not needed by callers of the internal API (they receive a pointer to the current ref_entry anyway). But more importantly, this change prevents peel_ref() from returning invalid results in the following scenario: When iterating via the external API, the iteration always includes both packed and loose references, and in particular never presents a packed ref if there is a loose ref with the same name. The internal API, on the other hand, gives the option to iterate over only the packed references. During such an iteration, there is no check whether the packed ref might be hidden by a loose ref of the same name. But until now the packed ref was recorded in current_ref during the iteration. So if peel_ref() were called with the reference name corresponding to current ref, it would return the peeled version of the packed ref even though there might be a loose ref that peels to a different value. This scenario doesn't currently occur in the code, but fix it to prevent things from breaking in a very confusing way in the future. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:23 +08:00
}
static int do_head_ref(const char *submodule, each_ref_fn fn, void *cb_data)
{
unsigned char sha1[20];
int flag;
if (submodule) {
if (resolve_gitlink_ref(submodule, "HEAD", sha1) == 0)
return fn("HEAD", sha1, 0, cb_data);
return 0;
}
if (!read_ref_full("HEAD", sha1, 1, &flag))
return fn("HEAD", sha1, flag, cb_data);
return 0;
}
int head_ref(each_ref_fn fn, void *cb_data)
{
return do_head_ref(NULL, fn, cb_data);
}
int head_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data)
{
return do_head_ref(submodule, fn, cb_data);
}
int for_each_ref(each_ref_fn fn, void *cb_data)
{
return do_for_each_ref(&ref_cache, "", fn, 0, 0, cb_data);
}
int for_each_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data)
{
return do_for_each_ref(get_ref_cache(submodule), "", fn, 0, 0, cb_data);
}
int for_each_ref_in(const char *prefix, each_ref_fn fn, void *cb_data)
{
return do_for_each_ref(&ref_cache, prefix, fn, strlen(prefix), 0, cb_data);
}
int for_each_ref_in_submodule(const char *submodule, const char *prefix,
each_ref_fn fn, void *cb_data)
{
return do_for_each_ref(get_ref_cache(submodule), prefix, fn, strlen(prefix), 0, cb_data);
}
int for_each_tag_ref(each_ref_fn fn, void *cb_data)
{
return for_each_ref_in("refs/tags/", fn, cb_data);
}
int for_each_tag_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data)
{
return for_each_ref_in_submodule(submodule, "refs/tags/", fn, cb_data);
}
int for_each_branch_ref(each_ref_fn fn, void *cb_data)
{
return for_each_ref_in("refs/heads/", fn, cb_data);
}
int for_each_branch_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data)
{
return for_each_ref_in_submodule(submodule, "refs/heads/", fn, cb_data);
}
int for_each_remote_ref(each_ref_fn fn, void *cb_data)
{
return for_each_ref_in("refs/remotes/", fn, cb_data);
}
int for_each_remote_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data)
{
return for_each_ref_in_submodule(submodule, "refs/remotes/", fn, cb_data);
}
int for_each_replace_ref(each_ref_fn fn, void *cb_data)
{
return do_for_each_ref(&ref_cache, "refs/replace/", fn, 13, 0, cb_data);
}
ref namespaces: infrastructure Add support for dividing the refs of a single repository into multiple namespaces, each of which can have its own branches, tags, and HEAD. Git can expose each namespace as an independent repository to pull from and push to, while sharing the object store, and exposing all the refs to operations such as git-gc. Storing multiple repositories as namespaces of a single repository avoids storing duplicate copies of the same objects, such as when storing multiple branches of the same source. The alternates mechanism provides similar support for avoiding duplicates, but alternates do not prevent duplication between new objects added to the repositories without ongoing maintenance, while namespaces do. To specify a namespace, set the GIT_NAMESPACE environment variable to the namespace. For each ref namespace, git stores the corresponding refs in a directory under refs/namespaces/. For example, GIT_NAMESPACE=foo will store refs under refs/namespaces/foo/. You can also specify namespaces via the --namespace option to git. Note that namespaces which include a / will expand to a hierarchy of namespaces; for example, GIT_NAMESPACE=foo/bar will store refs under refs/namespaces/foo/refs/namespaces/bar/. This makes paths in GIT_NAMESPACE behave hierarchically, so that cloning with GIT_NAMESPACE=foo/bar produces the same result as cloning with GIT_NAMESPACE=foo and cloning from that repo with GIT_NAMESPACE=bar. It also avoids ambiguity with strange namespace paths such as foo/refs/heads/, which could otherwise generate directory/file conflicts within the refs directory. Add the infrastructure for ref namespaces: handle the GIT_NAMESPACE environment variable and --namespace option, and support iterating over refs in a namespace. Signed-off-by: Josh Triplett <josh@joshtriplett.org> Signed-off-by: Jamey Sharp <jamey@minilop.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-07-06 01:54:44 +08:00
int head_ref_namespaced(each_ref_fn fn, void *cb_data)
{
struct strbuf buf = STRBUF_INIT;
int ret = 0;
unsigned char sha1[20];
int flag;
strbuf_addf(&buf, "%sHEAD", get_git_namespace());
if (!read_ref_full(buf.buf, sha1, 1, &flag))
ref namespaces: infrastructure Add support for dividing the refs of a single repository into multiple namespaces, each of which can have its own branches, tags, and HEAD. Git can expose each namespace as an independent repository to pull from and push to, while sharing the object store, and exposing all the refs to operations such as git-gc. Storing multiple repositories as namespaces of a single repository avoids storing duplicate copies of the same objects, such as when storing multiple branches of the same source. The alternates mechanism provides similar support for avoiding duplicates, but alternates do not prevent duplication between new objects added to the repositories without ongoing maintenance, while namespaces do. To specify a namespace, set the GIT_NAMESPACE environment variable to the namespace. For each ref namespace, git stores the corresponding refs in a directory under refs/namespaces/. For example, GIT_NAMESPACE=foo will store refs under refs/namespaces/foo/. You can also specify namespaces via the --namespace option to git. Note that namespaces which include a / will expand to a hierarchy of namespaces; for example, GIT_NAMESPACE=foo/bar will store refs under refs/namespaces/foo/refs/namespaces/bar/. This makes paths in GIT_NAMESPACE behave hierarchically, so that cloning with GIT_NAMESPACE=foo/bar produces the same result as cloning with GIT_NAMESPACE=foo and cloning from that repo with GIT_NAMESPACE=bar. It also avoids ambiguity with strange namespace paths such as foo/refs/heads/, which could otherwise generate directory/file conflicts within the refs directory. Add the infrastructure for ref namespaces: handle the GIT_NAMESPACE environment variable and --namespace option, and support iterating over refs in a namespace. Signed-off-by: Josh Triplett <josh@joshtriplett.org> Signed-off-by: Jamey Sharp <jamey@minilop.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-07-06 01:54:44 +08:00
ret = fn(buf.buf, sha1, flag, cb_data);
strbuf_release(&buf);
return ret;
}
int for_each_namespaced_ref(each_ref_fn fn, void *cb_data)
{
struct strbuf buf = STRBUF_INIT;
int ret;
strbuf_addf(&buf, "%srefs/", get_git_namespace());
ret = do_for_each_ref(&ref_cache, buf.buf, fn, 0, 0, cb_data);
ref namespaces: infrastructure Add support for dividing the refs of a single repository into multiple namespaces, each of which can have its own branches, tags, and HEAD. Git can expose each namespace as an independent repository to pull from and push to, while sharing the object store, and exposing all the refs to operations such as git-gc. Storing multiple repositories as namespaces of a single repository avoids storing duplicate copies of the same objects, such as when storing multiple branches of the same source. The alternates mechanism provides similar support for avoiding duplicates, but alternates do not prevent duplication between new objects added to the repositories without ongoing maintenance, while namespaces do. To specify a namespace, set the GIT_NAMESPACE environment variable to the namespace. For each ref namespace, git stores the corresponding refs in a directory under refs/namespaces/. For example, GIT_NAMESPACE=foo will store refs under refs/namespaces/foo/. You can also specify namespaces via the --namespace option to git. Note that namespaces which include a / will expand to a hierarchy of namespaces; for example, GIT_NAMESPACE=foo/bar will store refs under refs/namespaces/foo/refs/namespaces/bar/. This makes paths in GIT_NAMESPACE behave hierarchically, so that cloning with GIT_NAMESPACE=foo/bar produces the same result as cloning with GIT_NAMESPACE=foo and cloning from that repo with GIT_NAMESPACE=bar. It also avoids ambiguity with strange namespace paths such as foo/refs/heads/, which could otherwise generate directory/file conflicts within the refs directory. Add the infrastructure for ref namespaces: handle the GIT_NAMESPACE environment variable and --namespace option, and support iterating over refs in a namespace. Signed-off-by: Josh Triplett <josh@joshtriplett.org> Signed-off-by: Jamey Sharp <jamey@minilop.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-07-06 01:54:44 +08:00
strbuf_release(&buf);
return ret;
}
int for_each_glob_ref_in(each_ref_fn fn, const char *pattern,
const char *prefix, void *cb_data)
{
struct strbuf real_pattern = STRBUF_INIT;
struct ref_filter filter;
int ret;
if (!prefix && prefixcmp(pattern, "refs/"))
strbuf_addstr(&real_pattern, "refs/");
else if (prefix)
strbuf_addstr(&real_pattern, prefix);
strbuf_addstr(&real_pattern, pattern);
if (!has_glob_specials(pattern)) {
/* Append implied '/' '*' if not present. */
if (real_pattern.buf[real_pattern.len - 1] != '/')
strbuf_addch(&real_pattern, '/');
/* No need to check for '*', there is none. */
strbuf_addch(&real_pattern, '*');
}
filter.pattern = real_pattern.buf;
filter.fn = fn;
filter.cb_data = cb_data;
ret = for_each_ref(filter_refs, &filter);
strbuf_release(&real_pattern);
return ret;
}
int for_each_glob_ref(each_ref_fn fn, const char *pattern, void *cb_data)
{
return for_each_glob_ref_in(fn, pattern, NULL, cb_data);
}
int for_each_rawref(each_ref_fn fn, void *cb_data)
{
return do_for_each_ref(&ref_cache, "", fn, 0,
DO_FOR_EACH_INCLUDE_BROKEN, cb_data);
}
const char *prettify_refname(const char *name)
{
return name + (
!prefixcmp(name, "refs/heads/") ? 11 :
!prefixcmp(name, "refs/tags/") ? 10 :
!prefixcmp(name, "refs/remotes/") ? 13 :
0);
}
2007-11-11 22:01:46 +08:00
const char *ref_rev_parse_rules[] = {
"%.*s",
"refs/%.*s",
"refs/tags/%.*s",
"refs/heads/%.*s",
"refs/remotes/%.*s",
"refs/remotes/%.*s/HEAD",
NULL
};
int refname_match(const char *abbrev_name, const char *full_name, const char **rules)
{
const char **p;
const int abbrev_name_len = strlen(abbrev_name);
for (p = rules; *p; p++) {
if (!strcmp(full_name, mkpath(*p, abbrev_name_len, abbrev_name))) {
return 1;
}
}
return 0;
}
static struct ref_lock *verify_lock(struct ref_lock *lock,
const unsigned char *old_sha1, int mustexist)
{
if (read_ref_full(lock->ref_name, lock->old_sha1, mustexist, NULL)) {
Enable the packed refs file format This actually "turns on" the packed ref file format, now that the infrastructure to do so sanely exists (ie notably the change to make the reference reading logic take refnames rather than pathnames to the loose objects that no longer necessarily even exist). In particular, when the ref lookup hits a refname that has no loose file associated with it, it falls back on the packed-ref information. Also, the ref-locking code, while still using a loose file for the locking itself (and _creating_ a loose file for the new ref) no longer requires that the old ref be in such an unpacked state. Finally, this does a minimal hack to git-checkout.sh to rather than check the ref-file directly, do a "git-rev-parse" on the "heads/$refname". That's not really wonderful - we should rather really have a special routine to verify the names as proper branch head names, but it is a workable solution for now. With this, I can literally do something like git pack-refs find .git/refs -type f -print0 | xargs -0 rm -f -- and the end result is a largely working repository (ie I've done two commits - which creates _one_ unpacked ref file - done things like run "gitk" and "git log" etc, and it all looks ok). There are probably things missing, but I'm hoping that the missing things are now of the "small and obvious" kind, and that somebody else might want to start looking at this too. Hint hint ;) Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-09-15 01:14:47 +08:00
error("Can't verify ref %s", lock->ref_name);
unlock_ref(lock);
return NULL;
}
if (hashcmp(lock->old_sha1, old_sha1)) {
Enable the packed refs file format This actually "turns on" the packed ref file format, now that the infrastructure to do so sanely exists (ie notably the change to make the reference reading logic take refnames rather than pathnames to the loose objects that no longer necessarily even exist). In particular, when the ref lookup hits a refname that has no loose file associated with it, it falls back on the packed-ref information. Also, the ref-locking code, while still using a loose file for the locking itself (and _creating_ a loose file for the new ref) no longer requires that the old ref be in such an unpacked state. Finally, this does a minimal hack to git-checkout.sh to rather than check the ref-file directly, do a "git-rev-parse" on the "heads/$refname". That's not really wonderful - we should rather really have a special routine to verify the names as proper branch head names, but it is a workable solution for now. With this, I can literally do something like git pack-refs find .git/refs -type f -print0 | xargs -0 rm -f -- and the end result is a largely working repository (ie I've done two commits - which creates _one_ unpacked ref file - done things like run "gitk" and "git log" etc, and it all looks ok). There are probably things missing, but I'm hoping that the missing things are now of the "small and obvious" kind, and that somebody else might want to start looking at this too. Hint hint ;) Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-09-15 01:14:47 +08:00
error("Ref %s is at %s but expected %s", lock->ref_name,
sha1_to_hex(lock->old_sha1), sha1_to_hex(old_sha1));
unlock_ref(lock);
return NULL;
}
return lock;
}
static int remove_empty_directories(const char *file)
{
/* we want to create a file but there is a directory there;
* if that is an empty directory (or a directory that contains
* only empty directories), remove them.
*/
struct strbuf path;
int result;
strbuf_init(&path, 20);
strbuf_addstr(&path, file);
result = remove_dir_recursively(&path, REMOVE_DIR_EMPTY_ONLY);
strbuf_release(&path);
return result;
}
/*
* *string and *len will only be substituted, and *string returned (for
* later free()ing) if the string passed in is a magic short-hand form
* to name a branch.
*/
static char *substitute_branch_name(const char **string, int *len)
{
struct strbuf buf = STRBUF_INIT;
int ret = interpret_branch_name(*string, &buf);
if (ret == *len) {
size_t size;
*string = strbuf_detach(&buf, &size);
*len = size;
return (char *)*string;
}
return NULL;
}
int dwim_ref(const char *str, int len, unsigned char *sha1, char **ref)
{
char *last_branch = substitute_branch_name(&str, &len);
const char **p, *r;
int refs_found = 0;
*ref = NULL;
for (p = ref_rev_parse_rules; *p; p++) {
char fullref[PATH_MAX];
unsigned char sha1_from_ref[20];
unsigned char *this_result;
int flag;
this_result = refs_found ? sha1_from_ref : sha1;
mksnpath(fullref, sizeof(fullref), *p, len, str);
r = resolve_ref_unsafe(fullref, this_result, 1, &flag);
if (r) {
if (!refs_found++)
*ref = xstrdup(r);
if (!warn_ambiguous_refs)
break;
} else if ((flag & REF_ISSYMREF) && strcmp(fullref, "HEAD")) {
warning("ignoring dangling symref %s.", fullref);
} else if ((flag & REF_ISBROKEN) && strchr(fullref, '/')) {
warning("ignoring broken ref %s.", fullref);
}
}
free(last_branch);
return refs_found;
}
int dwim_log(const char *str, int len, unsigned char *sha1, char **log)
{
char *last_branch = substitute_branch_name(&str, &len);
const char **p;
int logs_found = 0;
*log = NULL;
for (p = ref_rev_parse_rules; *p; p++) {
struct stat st;
unsigned char hash[20];
char path[PATH_MAX];
const char *ref, *it;
mksnpath(path, sizeof(path), *p, len, str);
ref = resolve_ref_unsafe(path, hash, 1, NULL);
if (!ref)
continue;
if (!stat(git_path("logs/%s", path), &st) &&
S_ISREG(st.st_mode))
it = path;
else if (strcmp(ref, path) &&
!stat(git_path("logs/%s", ref), &st) &&
S_ISREG(st.st_mode))
it = ref;
else
continue;
if (!logs_found++) {
*log = xstrdup(it);
hashcpy(sha1, hash);
}
if (!warn_ambiguous_refs)
break;
}
free(last_branch);
return logs_found;
}
static struct ref_lock *lock_ref_sha1_basic(const char *refname,
const unsigned char *old_sha1,
int flags, int *type_p)
{
Enable the packed refs file format This actually "turns on" the packed ref file format, now that the infrastructure to do so sanely exists (ie notably the change to make the reference reading logic take refnames rather than pathnames to the loose objects that no longer necessarily even exist). In particular, when the ref lookup hits a refname that has no loose file associated with it, it falls back on the packed-ref information. Also, the ref-locking code, while still using a loose file for the locking itself (and _creating_ a loose file for the new ref) no longer requires that the old ref be in such an unpacked state. Finally, this does a minimal hack to git-checkout.sh to rather than check the ref-file directly, do a "git-rev-parse" on the "heads/$refname". That's not really wonderful - we should rather really have a special routine to verify the names as proper branch head names, but it is a workable solution for now. With this, I can literally do something like git pack-refs find .git/refs -type f -print0 | xargs -0 rm -f -- and the end result is a largely working repository (ie I've done two commits - which creates _one_ unpacked ref file - done things like run "gitk" and "git log" etc, and it all looks ok). There are probably things missing, but I'm hoping that the missing things are now of the "small and obvious" kind, and that somebody else might want to start looking at this too. Hint hint ;) Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-09-15 01:14:47 +08:00
char *ref_file;
const char *orig_refname = refname;
struct ref_lock *lock;
int last_errno = 0;
int type, lflags;
int mustexist = (old_sha1 && !is_null_sha1(old_sha1));
int missing = 0;
lock = xcalloc(1, sizeof(struct ref_lock));
lock->lock_fd = -1;
refname = resolve_ref_unsafe(refname, lock->old_sha1, mustexist, &type);
if (!refname && errno == EISDIR) {
/* we are trying to lock foo but we used to
* have foo/bar which now does not exist;
* it is normal for the empty directory 'foo'
* to remain.
*/
ref_file = git_path("%s", orig_refname);
if (remove_empty_directories(ref_file)) {
last_errno = errno;
error("there are still refs under '%s'", orig_refname);
goto error_return;
}
refname = resolve_ref_unsafe(orig_refname, lock->old_sha1, mustexist, &type);
}
if (type_p)
*type_p = type;
if (!refname) {
last_errno = errno;
error("unable to resolve reference %s: %s",
orig_refname, strerror(errno));
goto error_return;
}
missing = is_null_sha1(lock->old_sha1);
/* When the ref did not exist and we are creating it,
* make sure there is no existing ref that is packed
* whose name begins with our refname, nor a ref whose
* name is a proper prefix of our refname.
*/
if (missing &&
!is_refname_available(refname, NULL, get_packed_refs(&ref_cache))) {
last_errno = ENOTDIR;
goto error_return;
}
lock->lk = xcalloc(1, sizeof(struct lock_file));
lflags = LOCK_DIE_ON_ERROR;
if (flags & REF_NODEREF) {
refname = orig_refname;
lflags |= LOCK_NODEREF;
}
lock->ref_name = xstrdup(refname);
lock->orig_ref_name = xstrdup(orig_refname);
ref_file = git_path("%s", refname);
if (missing)
lock->force_write = 1;
if ((flags & REF_NODEREF) && (type & REF_ISSYMREF))
lock->force_write = 1;
if (safe_create_leading_directories(ref_file)) {
last_errno = errno;
error("unable to create directory for %s", ref_file);
goto error_return;
}
lock->lock_fd = hold_lock_file_for_update(lock->lk, ref_file, lflags);
return old_sha1 ? verify_lock(lock, old_sha1, mustexist) : lock;
error_return:
unlock_ref(lock);
errno = last_errno;
return NULL;
}
struct ref_lock *lock_ref_sha1(const char *refname, const unsigned char *old_sha1)
{
char refpath[PATH_MAX];
if (check_refname_format(refname, 0))
return NULL;
strcpy(refpath, mkpath("refs/%s", refname));
return lock_ref_sha1_basic(refpath, old_sha1, 0, NULL);
}
struct ref_lock *lock_any_ref_for_update(const char *refname,
const unsigned char *old_sha1, int flags)
{
if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL))
return NULL;
return lock_ref_sha1_basic(refname, old_sha1, flags, NULL);
}
/*
* Write an entry to the packed-refs file for the specified refname.
* If peeled is non-NULL, write it as the entry's peeled value.
*/
static void write_packed_entry(int fd, char *refname, unsigned char *sha1,
unsigned char *peeled)
{
char line[PATH_MAX + 100];
int len;
len = snprintf(line, sizeof(line), "%s %s\n",
sha1_to_hex(sha1), refname);
/* this should not happen but just being defensive */
if (len > sizeof(line))
die("too long a refname '%s'", refname);
write_or_die(fd, line, len);
if (peeled) {
if (snprintf(line, sizeof(line), "^%s\n",
sha1_to_hex(peeled)) != PEELED_LINE_LENGTH)
die("internal error");
write_or_die(fd, line, PEELED_LINE_LENGTH);
}
}
/*
* An each_ref_entry_fn that writes the entry to a packed-refs file.
*/
static int write_packed_entry_fn(struct ref_entry *entry, void *cb_data)
{
int *fd = cb_data;
enum peel_status peel_status = peel_entry(entry, 0);
if (peel_status != PEEL_PEELED && peel_status != PEEL_NON_TAG)
error("internal error: %s is not a valid packed reference!",
entry->name);
write_packed_entry(*fd, entry->name, entry->u.value.sha1,
peel_status == PEEL_PEELED ?
entry->u.value.peeled : NULL);
return 0;
}
int lock_packed_refs(int flags)
{
struct packed_ref_cache *packed_ref_cache;
if (hold_lock_file_for_update(&packlock, git_path("packed-refs"), flags) < 0)
return -1;
/*
* Get the current packed-refs while holding the lock. If the
* packed-refs file has been modified since we last read it,
* this will automatically invalidate the cache and re-read
* the packed-refs file.
*/
packed_ref_cache = get_packed_ref_cache(&ref_cache);
packed_ref_cache->lock = &packlock;
/* Increment the reference count to prevent it from being freed: */
acquire_packed_ref_cache(packed_ref_cache);
return 0;
}
int commit_packed_refs(void)
{
struct packed_ref_cache *packed_ref_cache =
get_packed_ref_cache(&ref_cache);
int error = 0;
if (!packed_ref_cache->lock)
die("internal error: packed-refs not locked");
write_or_die(packed_ref_cache->lock->fd,
PACKED_REFS_HEADER, strlen(PACKED_REFS_HEADER));
do_for_each_entry_in_dir(get_packed_ref_dir(packed_ref_cache),
0, write_packed_entry_fn,
&packed_ref_cache->lock->fd);
if (commit_lock_file(packed_ref_cache->lock))
error = -1;
packed_ref_cache->lock = NULL;
release_packed_ref_cache(packed_ref_cache);
return error;
}
void rollback_packed_refs(void)
{
struct packed_ref_cache *packed_ref_cache =
get_packed_ref_cache(&ref_cache);
if (!packed_ref_cache->lock)
die("internal error: packed-refs not locked");
rollback_lock_file(packed_ref_cache->lock);
packed_ref_cache->lock = NULL;
release_packed_ref_cache(packed_ref_cache);
clear_packed_ref_cache(&ref_cache);
}
struct ref_to_prune {
struct ref_to_prune *next;
unsigned char sha1[20];
char name[FLEX_ARRAY];
};
struct pack_refs_cb_data {
unsigned int flags;
struct ref_dir *packed_refs;
struct ref_to_prune *ref_to_prune;
};
/*
* An each_ref_entry_fn that is run over loose references only. If
* the loose reference can be packed, add an entry in the packed ref
* cache. If the reference should be pruned, also add it to
* ref_to_prune in the pack_refs_cb_data.
*/
static int pack_if_possible_fn(struct ref_entry *entry, void *cb_data)
{
struct pack_refs_cb_data *cb = cb_data;
enum peel_status peel_status;
struct ref_entry *packed_entry;
int is_tag_ref = !prefixcmp(entry->name, "refs/tags/");
/* ALWAYS pack tags */
if (!(cb->flags & PACK_REFS_ALL) && !is_tag_ref)
return 0;
/* Do not pack symbolic or broken refs: */
if ((entry->flag & REF_ISSYMREF) || !ref_resolves_to_object(entry))
return 0;
/* Add a packed ref cache entry equivalent to the loose entry. */
peel_status = peel_entry(entry, 1);
if (peel_status != PEEL_PEELED && peel_status != PEEL_NON_TAG)
die("internal error peeling reference %s (%s)",
entry->name, sha1_to_hex(entry->u.value.sha1));
packed_entry = find_ref(cb->packed_refs, entry->name);
if (packed_entry) {
/* Overwrite existing packed entry with info from loose entry */
packed_entry->flag = REF_ISPACKED | REF_KNOWS_PEELED;
hashcpy(packed_entry->u.value.sha1, entry->u.value.sha1);
} else {
packed_entry = create_ref_entry(entry->name, entry->u.value.sha1,
REF_ISPACKED | REF_KNOWS_PEELED, 0);
add_ref(cb->packed_refs, packed_entry);
}
hashcpy(packed_entry->u.value.peeled, entry->u.value.peeled);
/* Schedule the loose reference for pruning if requested. */
if ((cb->flags & PACK_REFS_PRUNE)) {
int namelen = strlen(entry->name) + 1;
struct ref_to_prune *n = xcalloc(1, sizeof(*n) + namelen);
hashcpy(n->sha1, entry->u.value.sha1);
strcpy(n->name, entry->name);
n->next = cb->ref_to_prune;
cb->ref_to_prune = n;
}
return 0;
}
/*
* Remove empty parents, but spare refs/ and immediate subdirs.
* Note: munges *name.
*/
static void try_remove_empty_parents(char *name)
{
char *p, *q;
int i;
p = name;
for (i = 0; i < 2; i++) { /* refs/{heads,tags,...}/ */
while (*p && *p != '/')
p++;
/* tolerate duplicate slashes; see check_refname_format() */
while (*p == '/')
p++;
}
for (q = p; *q; q++)
;
while (1) {
while (q > p && *q != '/')
q--;
while (q > p && *(q-1) == '/')
q--;
if (q == p)
break;
*q = '\0';
if (rmdir(git_path("%s", name)))
break;
}
}
/* make sure nobody touched the ref, and unlink */
static void prune_ref(struct ref_to_prune *r)
{
struct ref_lock *lock = lock_ref_sha1(r->name + 5, r->sha1);
if (lock) {
unlink_or_warn(git_path("%s", r->name));
unlock_ref(lock);
try_remove_empty_parents(r->name);
}
}
static void prune_refs(struct ref_to_prune *r)
{
while (r) {
prune_ref(r);
r = r->next;
}
}
int pack_refs(unsigned int flags)
{
struct pack_refs_cb_data cbdata;
memset(&cbdata, 0, sizeof(cbdata));
cbdata.flags = flags;
lock_packed_refs(LOCK_DIE_ON_ERROR);
cbdata.packed_refs = get_packed_refs(&ref_cache);
do_for_each_entry_in_dir(get_loose_refs(&ref_cache), 0,
pack_if_possible_fn, &cbdata);
if (commit_packed_refs())
die_errno("unable to overwrite old ref-pack file");
prune_refs(cbdata.ref_to_prune);
return 0;
}
/*
* If entry is no longer needed in packed-refs, add it to the string
* list pointed to by cb_data. Reasons for deleting entries:
*
* - Entry is broken.
* - Entry is overridden by a loose ref.
* - Entry does not point at a valid object.
*
* In the first and third cases, also emit an error message because these
* are indications of repository corruption.
*/
static int curate_packed_ref_fn(struct ref_entry *entry, void *cb_data)
{
struct string_list *refs_to_delete = cb_data;
repack_without_ref(): silence errors for dangling packed refs Stop emitting an error message when deleting a packed reference if we find another dangling packed reference that is overridden by a loose reference. See the previous commit for a longer explanation of the issue. We have to be careful to make sure that the invalid packed reference really *is* overridden by a loose reference; otherwise what we have found is repository corruption, which we *should* report. Please note that this approach is vulnerable to a race condition similar to the race conditions already known to affect packed references [1]: * Process 1 tries to peel packed reference X as part of deleting another packed reference. It discovers that X does not refer to a valid object (because the object that it referred to has been garbage collected). * Process 2 tries to delete reference X. It starts by deleting the loose reference X. * Process 1 checks whether there is a loose reference X. There is not (it has just been deleted by process 2), so process 1 reports a spurious error "X does not point to a valid object!" The worst case seems relatively harmless, and the fix is identical to the fix that will be needed for the other race conditions (namely holding a lock on the packed-refs file during *all* reference deletions), so we leave the cleaning up of all of them as a future project. [1] http://thread.gmane.org/gmane.comp.version-control.git/211956 Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:25 +08:00
if (entry->flag & REF_ISBROKEN) {
/* This shouldn't happen to packed refs. */
error("%s is broken!", entry->name);
string_list_append(refs_to_delete, entry->name);
return 0;
repack_without_ref(): silence errors for dangling packed refs Stop emitting an error message when deleting a packed reference if we find another dangling packed reference that is overridden by a loose reference. See the previous commit for a longer explanation of the issue. We have to be careful to make sure that the invalid packed reference really *is* overridden by a loose reference; otherwise what we have found is repository corruption, which we *should* report. Please note that this approach is vulnerable to a race condition similar to the race conditions already known to affect packed references [1]: * Process 1 tries to peel packed reference X as part of deleting another packed reference. It discovers that X does not refer to a valid object (because the object that it referred to has been garbage collected). * Process 2 tries to delete reference X. It starts by deleting the loose reference X. * Process 1 checks whether there is a loose reference X. There is not (it has just been deleted by process 2), so process 1 reports a spurious error "X does not point to a valid object!" The worst case seems relatively harmless, and the fix is identical to the fix that will be needed for the other race conditions (namely holding a lock on the packed-refs file during *all* reference deletions), so we leave the cleaning up of all of them as a future project. [1] http://thread.gmane.org/gmane.comp.version-control.git/211956 Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:25 +08:00
}
if (!has_sha1_file(entry->u.value.sha1)) {
unsigned char sha1[20];
int flags;
if (read_ref_full(entry->name, sha1, 0, &flags))
/* We should at least have found the packed ref. */
die("Internal error");
if ((flags & REF_ISSYMREF) || !(flags & REF_ISPACKED)) {
repack_without_ref(): silence errors for dangling packed refs Stop emitting an error message when deleting a packed reference if we find another dangling packed reference that is overridden by a loose reference. See the previous commit for a longer explanation of the issue. We have to be careful to make sure that the invalid packed reference really *is* overridden by a loose reference; otherwise what we have found is repository corruption, which we *should* report. Please note that this approach is vulnerable to a race condition similar to the race conditions already known to affect packed references [1]: * Process 1 tries to peel packed reference X as part of deleting another packed reference. It discovers that X does not refer to a valid object (because the object that it referred to has been garbage collected). * Process 2 tries to delete reference X. It starts by deleting the loose reference X. * Process 1 checks whether there is a loose reference X. There is not (it has just been deleted by process 2), so process 1 reports a spurious error "X does not point to a valid object!" The worst case seems relatively harmless, and the fix is identical to the fix that will be needed for the other race conditions (namely holding a lock on the packed-refs file during *all* reference deletions), so we leave the cleaning up of all of them as a future project. [1] http://thread.gmane.org/gmane.comp.version-control.git/211956 Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:25 +08:00
/*
* This packed reference is overridden by a
* loose reference, so it is OK that its value
* is no longer valid; for example, it might
* refer to an object that has been garbage
* collected. For this purpose we don't even
* care whether the loose reference itself is
* invalid, broken, symbolic, etc. Silently
* remove the packed reference.
repack_without_ref(): silence errors for dangling packed refs Stop emitting an error message when deleting a packed reference if we find another dangling packed reference that is overridden by a loose reference. See the previous commit for a longer explanation of the issue. We have to be careful to make sure that the invalid packed reference really *is* overridden by a loose reference; otherwise what we have found is repository corruption, which we *should* report. Please note that this approach is vulnerable to a race condition similar to the race conditions already known to affect packed references [1]: * Process 1 tries to peel packed reference X as part of deleting another packed reference. It discovers that X does not refer to a valid object (because the object that it referred to has been garbage collected). * Process 2 tries to delete reference X. It starts by deleting the loose reference X. * Process 1 checks whether there is a loose reference X. There is not (it has just been deleted by process 2), so process 1 reports a spurious error "X does not point to a valid object!" The worst case seems relatively harmless, and the fix is identical to the fix that will be needed for the other race conditions (namely holding a lock on the packed-refs file during *all* reference deletions), so we leave the cleaning up of all of them as a future project. [1] http://thread.gmane.org/gmane.comp.version-control.git/211956 Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:25 +08:00
*/
string_list_append(refs_to_delete, entry->name);
repack_without_ref(): silence errors for dangling packed refs Stop emitting an error message when deleting a packed reference if we find another dangling packed reference that is overridden by a loose reference. See the previous commit for a longer explanation of the issue. We have to be careful to make sure that the invalid packed reference really *is* overridden by a loose reference; otherwise what we have found is repository corruption, which we *should* report. Please note that this approach is vulnerable to a race condition similar to the race conditions already known to affect packed references [1]: * Process 1 tries to peel packed reference X as part of deleting another packed reference. It discovers that X does not refer to a valid object (because the object that it referred to has been garbage collected). * Process 2 tries to delete reference X. It starts by deleting the loose reference X. * Process 1 checks whether there is a loose reference X. There is not (it has just been deleted by process 2), so process 1 reports a spurious error "X does not point to a valid object!" The worst case seems relatively harmless, and the fix is identical to the fix that will be needed for the other race conditions (namely holding a lock on the packed-refs file during *all* reference deletions), so we leave the cleaning up of all of them as a future project. [1] http://thread.gmane.org/gmane.comp.version-control.git/211956 Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:25 +08:00
return 0;
}
repack_without_ref(): silence errors for dangling packed refs Stop emitting an error message when deleting a packed reference if we find another dangling packed reference that is overridden by a loose reference. See the previous commit for a longer explanation of the issue. We have to be careful to make sure that the invalid packed reference really *is* overridden by a loose reference; otherwise what we have found is repository corruption, which we *should* report. Please note that this approach is vulnerable to a race condition similar to the race conditions already known to affect packed references [1]: * Process 1 tries to peel packed reference X as part of deleting another packed reference. It discovers that X does not refer to a valid object (because the object that it referred to has been garbage collected). * Process 2 tries to delete reference X. It starts by deleting the loose reference X. * Process 1 checks whether there is a loose reference X. There is not (it has just been deleted by process 2), so process 1 reports a spurious error "X does not point to a valid object!" The worst case seems relatively harmless, and the fix is identical to the fix that will be needed for the other race conditions (namely holding a lock on the packed-refs file during *all* reference deletions), so we leave the cleaning up of all of them as a future project. [1] http://thread.gmane.org/gmane.comp.version-control.git/211956 Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:25 +08:00
/*
* There is no overriding loose reference, so the fact
* that this reference doesn't refer to a valid object
* indicates some kind of repository corruption.
* Report the problem, then omit the reference from
* the output.
*/
error("%s does not point to a valid object!", entry->name);
string_list_append(refs_to_delete, entry->name);
repack_without_ref(): silence errors for dangling packed refs Stop emitting an error message when deleting a packed reference if we find another dangling packed reference that is overridden by a loose reference. See the previous commit for a longer explanation of the issue. We have to be careful to make sure that the invalid packed reference really *is* overridden by a loose reference; otherwise what we have found is repository corruption, which we *should* report. Please note that this approach is vulnerable to a race condition similar to the race conditions already known to affect packed references [1]: * Process 1 tries to peel packed reference X as part of deleting another packed reference. It discovers that X does not refer to a valid object (because the object that it referred to has been garbage collected). * Process 2 tries to delete reference X. It starts by deleting the loose reference X. * Process 1 checks whether there is a loose reference X. There is not (it has just been deleted by process 2), so process 1 reports a spurious error "X does not point to a valid object!" The worst case seems relatively harmless, and the fix is identical to the fix that will be needed for the other race conditions (namely holding a lock on the packed-refs file during *all* reference deletions), so we leave the cleaning up of all of them as a future project. [1] http://thread.gmane.org/gmane.comp.version-control.git/211956 Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-23 03:52:25 +08:00
return 0;
}
return 0;
}
static int repack_without_ref(const char *refname)
{
struct ref_dir *packed;
struct string_list refs_to_delete = STRING_LIST_INIT_DUP;
struct string_list_item *ref_to_delete;
if (!get_packed_ref(refname))
return 0; /* refname does not exist in packed refs */
if (lock_packed_refs(0)) {
unable_to_lock_error(git_path("packed-refs"), errno);
return error("cannot delete '%s' from packed refs", refname);
}
packed = get_packed_refs(&ref_cache);
/* Remove refname from the cache: */
if (remove_entry(packed, refname) == -1) {
/*
* The packed entry disappeared while we were
* acquiring the lock.
*/
rollback_packed_refs();
return 0;
}
/* Remove any other accumulated cruft: */
do_for_each_entry_in_dir(packed, 0, curate_packed_ref_fn, &refs_to_delete);
for_each_string_list_item(ref_to_delete, &refs_to_delete) {
if (remove_entry(packed, ref_to_delete->string) == -1)
die("internal error");
}
/* Write what remains: */
return commit_packed_refs();
}
int delete_ref(const char *refname, const unsigned char *sha1, int delopt)
{
struct ref_lock *lock;
int err, i = 0, ret = 0, flag = 0;
lock = lock_ref_sha1_basic(refname, sha1, delopt, &flag);
if (!lock)
return 1;
if (!(flag & REF_ISPACKED) || flag & REF_ISSYMREF) {
/* loose */
i = strlen(lock->lk->filename) - 5; /* .lock */
lock->lk->filename[i] = 0;
err = unlink_or_warn(lock->lk->filename);
if (err && errno != ENOENT)
ret = 1;
lock->lk->filename[i] = '.';
}
/* removing the loose one could have resurrected an earlier
* packed one. Also, if it was not loose we need to repack
* without it.
*/
ret |= repack_without_ref(lock->ref_name);
unlink_or_warn(git_path("logs/%s", lock->ref_name));
clear_loose_ref_cache(&ref_cache);
unlock_ref(lock);
return ret;
}
/*
* People using contrib's git-new-workdir have .git/logs/refs ->
* /some/other/path/.git/logs/refs, and that may live on another device.
*
* IOW, to avoid cross device rename errors, the temporary renamed log must
* live into logs/refs.
*/
#define TMP_RENAMED_LOG "logs/refs/.tmp-renamed-log"
int rename_ref(const char *oldrefname, const char *newrefname, const char *logmsg)
{
unsigned char sha1[20], orig_sha1[20];
int flag = 0, logmoved = 0;
struct ref_lock *lock;
struct stat loginfo;
int log = !lstat(git_path("logs/%s", oldrefname), &loginfo);
const char *symref = NULL;
if (log && S_ISLNK(loginfo.st_mode))
return error("reflog for %s is a symlink", oldrefname);
symref = resolve_ref_unsafe(oldrefname, orig_sha1, 1, &flag);
if (flag & REF_ISSYMREF)
return error("refname %s is a symbolic ref, renaming it is not supported",
oldrefname);
if (!symref)
return error("refname %s not found", oldrefname);
if (!is_refname_available(newrefname, oldrefname, get_packed_refs(&ref_cache)))
return 1;
if (!is_refname_available(newrefname, oldrefname, get_loose_refs(&ref_cache)))
return 1;
if (log && rename(git_path("logs/%s", oldrefname), git_path(TMP_RENAMED_LOG)))
return error("unable to move logfile logs/%s to "TMP_RENAMED_LOG": %s",
oldrefname, strerror(errno));
if (delete_ref(oldrefname, orig_sha1, REF_NODEREF)) {
error("unable to delete old %s", oldrefname);
goto rollback;
}
if (!read_ref_full(newrefname, sha1, 1, &flag) &&
delete_ref(newrefname, sha1, REF_NODEREF)) {
if (errno==EISDIR) {
if (remove_empty_directories(git_path("%s", newrefname))) {
error("Directory not empty: %s", newrefname);
goto rollback;
}
} else {
error("unable to delete existing %s", newrefname);
goto rollback;
}
}
if (log && safe_create_leading_directories(git_path("logs/%s", newrefname))) {
error("unable to create directory for %s", newrefname);
goto rollback;
}
retry:
if (log && rename(git_path(TMP_RENAMED_LOG), git_path("logs/%s", newrefname))) {
if (errno==EISDIR || errno==ENOTDIR) {
/*
* rename(a, b) when b is an existing
* directory ought to result in ISDIR, but
* Solaris 5.8 gives ENOTDIR. Sheesh.
*/
if (remove_empty_directories(git_path("logs/%s", newrefname))) {
error("Directory not empty: logs/%s", newrefname);
goto rollback;
}
goto retry;
} else {
error("unable to move logfile "TMP_RENAMED_LOG" to logs/%s: %s",
newrefname, strerror(errno));
goto rollback;
}
}
logmoved = log;
lock = lock_ref_sha1_basic(newrefname, NULL, 0, NULL);
if (!lock) {
error("unable to lock %s for update", newrefname);
goto rollback;
}
lock->force_write = 1;
hashcpy(lock->old_sha1, orig_sha1);
if (write_ref_sha1(lock, orig_sha1, logmsg)) {
error("unable to write current sha1 into %s", newrefname);
goto rollback;
}
return 0;
rollback:
lock = lock_ref_sha1_basic(oldrefname, NULL, 0, NULL);
if (!lock) {
error("unable to lock %s for rollback", oldrefname);
goto rollbacklog;
}
lock->force_write = 1;
flag = log_all_ref_updates;
log_all_ref_updates = 0;
if (write_ref_sha1(lock, orig_sha1, NULL))
error("unable to write current sha1 into %s", oldrefname);
log_all_ref_updates = flag;
rollbacklog:
if (logmoved && rename(git_path("logs/%s", newrefname), git_path("logs/%s", oldrefname)))
error("unable to restore logfile %s from %s: %s",
oldrefname, newrefname, strerror(errno));
if (!logmoved && log &&
rename(git_path(TMP_RENAMED_LOG), git_path("logs/%s", oldrefname)))
error("unable to restore logfile %s from "TMP_RENAMED_LOG": %s",
oldrefname, strerror(errno));
return 1;
}
int close_ref(struct ref_lock *lock)
{
if (close_lock_file(lock->lk))
return -1;
lock->lock_fd = -1;
return 0;
}
int commit_ref(struct ref_lock *lock)
{
if (commit_lock_file(lock->lk))
return -1;
lock->lock_fd = -1;
return 0;
}
void unlock_ref(struct ref_lock *lock)
{
/* Do not free lock->lk -- atexit() still looks at them */
if (lock->lk)
rollback_lock_file(lock->lk);
Enable the packed refs file format This actually "turns on" the packed ref file format, now that the infrastructure to do so sanely exists (ie notably the change to make the reference reading logic take refnames rather than pathnames to the loose objects that no longer necessarily even exist). In particular, when the ref lookup hits a refname that has no loose file associated with it, it falls back on the packed-ref information. Also, the ref-locking code, while still using a loose file for the locking itself (and _creating_ a loose file for the new ref) no longer requires that the old ref be in such an unpacked state. Finally, this does a minimal hack to git-checkout.sh to rather than check the ref-file directly, do a "git-rev-parse" on the "heads/$refname". That's not really wonderful - we should rather really have a special routine to verify the names as proper branch head names, but it is a workable solution for now. With this, I can literally do something like git pack-refs find .git/refs -type f -print0 | xargs -0 rm -f -- and the end result is a largely working repository (ie I've done two commits - which creates _one_ unpacked ref file - done things like run "gitk" and "git log" etc, and it all looks ok). There are probably things missing, but I'm hoping that the missing things are now of the "small and obvious" kind, and that somebody else might want to start looking at this too. Hint hint ;) Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-09-15 01:14:47 +08:00
free(lock->ref_name);
free(lock->orig_ref_name);
free(lock);
}
/*
* copy the reflog message msg to buf, which has been allocated sufficiently
* large, while cleaning up the whitespaces. Especially, convert LF to space,
* because reflog file is one line per entry.
*/
static int copy_msg(char *buf, const char *msg)
{
char *cp = buf;
char c;
int wasspace = 1;
*cp++ = '\t';
while ((c = *msg++)) {
if (wasspace && isspace(c))
continue;
wasspace = isspace(c);
if (wasspace)
c = ' ';
*cp++ = c;
}
while (buf < cp && isspace(cp[-1]))
cp--;
*cp++ = '\n';
return cp - buf;
}
int log_ref_setup(const char *refname, char *logfile, int bufsize)
{
int logfd, oflags = O_APPEND | O_WRONLY;
git_snpath(logfile, bufsize, "logs/%s", refname);
if (log_all_ref_updates &&
(!prefixcmp(refname, "refs/heads/") ||
!prefixcmp(refname, "refs/remotes/") ||
!prefixcmp(refname, "refs/notes/") ||
!strcmp(refname, "HEAD"))) {
if (safe_create_leading_directories(logfile) < 0)
return error("unable to create directory for %s",
logfile);
oflags |= O_CREAT;
}
logfd = open(logfile, oflags, 0666);
if (logfd < 0) {
2006-10-10 12:15:59 +08:00
if (!(oflags & O_CREAT) && errno == ENOENT)
return 0;
if ((oflags & O_CREAT) && errno == EISDIR) {
if (remove_empty_directories(logfile)) {
return error("There are still logs under '%s'",
logfile);
}
logfd = open(logfile, oflags, 0666);
}
if (logfd < 0)
return error("Unable to append to %s: %s",
logfile, strerror(errno));
}
adjust_shared_perm(logfile);
close(logfd);
return 0;
}
static int log_ref_write(const char *refname, const unsigned char *old_sha1,
const unsigned char *new_sha1, const char *msg)
{
int logfd, result, written, oflags = O_APPEND | O_WRONLY;
unsigned maxlen, len;
int msglen;
char log_file[PATH_MAX];
char *logrec;
const char *committer;
if (log_all_ref_updates < 0)
log_all_ref_updates = !is_bare_repository();
result = log_ref_setup(refname, log_file, sizeof(log_file));
if (result)
return result;
logfd = open(log_file, oflags);
if (logfd < 0)
return 0;
msglen = msg ? strlen(msg) : 0;
Re-fix "builtin-commit: fix --signoff" An earlier fix to the said commit was incomplete; it mixed up the meaning of the flag parameter passed to the internal fmt_ident() function, so this corrects it. git_author_info() and git_committer_info() can be told to issue a warning when no usable user information is found, and optionally can be told to error out. Operations that actually use the information to record a new commit or a tag will still error out, but the caller to leave reflog record will just silently use bogus user information. Not warning on misconfigured user information while writing a reflog entry is somewhat debatable, but it is probably nicer to the users to silently let it pass, because the only information you are losing is who checked out the branch. * git_author_info() and git_committer_info() used to take 1 (positive int) to error out with a warning on misconfiguration; this is now signalled with a symbolic constant IDENT_ERROR_ON_NO_NAME. * These functions used to take -1 (negative int) to warn but continue; this is now signalled with a symbolic constant IDENT_WARN_ON_NO_NAME. * fmt_ident() function implements the above error reporting behaviour common to git_author_info() and git_committer_info(). A symbolic constant IDENT_NO_DATE can be or'ed in to the flag parameter to make it return only the "Name <email@address.xz>". * fmt_name() is a thin wrapper around fmt_ident() that always passes IDENT_ERROR_ON_NO_NAME and IDENT_NO_DATE. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-12-09 09:32:08 +08:00
committer = git_committer_info(0);
maxlen = strlen(committer) + msglen + 100;
logrec = xmalloc(maxlen);
len = sprintf(logrec, "%s %s %s\n",
sha1_to_hex(old_sha1),
sha1_to_hex(new_sha1),
committer);
if (msglen)
len += copy_msg(logrec + len - 1, msg) - 1;
written = len <= maxlen ? write_in_full(logfd, logrec, len) : -1;
free(logrec);
if (close(logfd) != 0 || written != len)
return error("Unable to append to %s", log_file);
return 0;
}
static int is_branch(const char *refname)
{
return !strcmp(refname, "HEAD") || !prefixcmp(refname, "refs/heads/");
}
int write_ref_sha1(struct ref_lock *lock,
const unsigned char *sha1, const char *logmsg)
{
static char term = '\n';
struct object *o;
if (!lock)
return -1;
if (!lock->force_write && !hashcmp(lock->old_sha1, sha1)) {
unlock_ref(lock);
return 0;
}
o = parse_object(sha1);
if (!o) {
error("Trying to write ref %s with nonexistent object %s",
lock->ref_name, sha1_to_hex(sha1));
unlock_ref(lock);
return -1;
}
if (o->type != OBJ_COMMIT && is_branch(lock->ref_name)) {
error("Trying to write non-commit object %s to branch %s",
sha1_to_hex(sha1), lock->ref_name);
unlock_ref(lock);
return -1;
}
if (write_in_full(lock->lock_fd, sha1_to_hex(sha1), 40) != 40 ||
write_in_full(lock->lock_fd, &term, 1) != 1
|| close_ref(lock) < 0) {
error("Couldn't write %s", lock->lk->filename);
unlock_ref(lock);
return -1;
}
clear_loose_ref_cache(&ref_cache);
if (log_ref_write(lock->ref_name, lock->old_sha1, sha1, logmsg) < 0 ||
(strcmp(lock->ref_name, lock->orig_ref_name) &&
log_ref_write(lock->orig_ref_name, lock->old_sha1, sha1, logmsg) < 0)) {
unlock_ref(lock);
return -1;
}
if (strcmp(lock->orig_ref_name, "HEAD") != 0) {
/*
* Special hack: If a branch is updated directly and HEAD
* points to it (may happen on the remote side of a push
* for example) then logically the HEAD reflog should be
* updated too.
* A generic solution implies reverse symref information,
* but finding all symrefs pointing to the given branch
* would be rather costly for this rare event (the direct
* update of a branch) to be worth it. So let's cheat and
* check with HEAD only which should cover 99% of all usage
* scenarios (even 100% of the default ones).
*/
unsigned char head_sha1[20];
int head_flag;
const char *head_ref;
head_ref = resolve_ref_unsafe("HEAD", head_sha1, 1, &head_flag);
if (head_ref && (head_flag & REF_ISSYMREF) &&
!strcmp(head_ref, lock->ref_name))
log_ref_write("HEAD", lock->old_sha1, sha1, logmsg);
}
if (commit_ref(lock)) {
Enable the packed refs file format This actually "turns on" the packed ref file format, now that the infrastructure to do so sanely exists (ie notably the change to make the reference reading logic take refnames rather than pathnames to the loose objects that no longer necessarily even exist). In particular, when the ref lookup hits a refname that has no loose file associated with it, it falls back on the packed-ref information. Also, the ref-locking code, while still using a loose file for the locking itself (and _creating_ a loose file for the new ref) no longer requires that the old ref be in such an unpacked state. Finally, this does a minimal hack to git-checkout.sh to rather than check the ref-file directly, do a "git-rev-parse" on the "heads/$refname". That's not really wonderful - we should rather really have a special routine to verify the names as proper branch head names, but it is a workable solution for now. With this, I can literally do something like git pack-refs find .git/refs -type f -print0 | xargs -0 rm -f -- and the end result is a largely working repository (ie I've done two commits - which creates _one_ unpacked ref file - done things like run "gitk" and "git log" etc, and it all looks ok). There are probably things missing, but I'm hoping that the missing things are now of the "small and obvious" kind, and that somebody else might want to start looking at this too. Hint hint ;) Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-09-15 01:14:47 +08:00
error("Couldn't set %s", lock->ref_name);
unlock_ref(lock);
return -1;
}
unlock_ref(lock);
return 0;
}
int create_symref(const char *ref_target, const char *refs_heads_master,
const char *logmsg)
{
const char *lockpath;
char ref[1000];
int fd, len, written;
char *git_HEAD = git_pathdup("%s", ref_target);
unsigned char old_sha1[20], new_sha1[20];
if (logmsg && read_ref(ref_target, old_sha1))
hashclr(old_sha1);
if (safe_create_leading_directories(git_HEAD) < 0)
return error("unable to create directory for %s", git_HEAD);
#ifndef NO_SYMLINK_HEAD
if (prefer_symlink_refs) {
unlink(git_HEAD);
if (!symlink(refs_heads_master, git_HEAD))
goto done;
fprintf(stderr, "no symlink - falling back to symbolic ref\n");
}
#endif
len = snprintf(ref, sizeof(ref), "ref: %s\n", refs_heads_master);
if (sizeof(ref) <= len) {
error("refname too long: %s", refs_heads_master);
goto error_free_return;
}
lockpath = mkpath("%s.lock", git_HEAD);
fd = open(lockpath, O_CREAT | O_EXCL | O_WRONLY, 0666);
if (fd < 0) {
error("Unable to open %s for writing", lockpath);
goto error_free_return;
}
written = write_in_full(fd, ref, len);
if (close(fd) != 0 || written != len) {
error("Unable to write to %s", lockpath);
goto error_unlink_return;
}
if (rename(lockpath, git_HEAD) < 0) {
error("Unable to create %s", git_HEAD);
goto error_unlink_return;
}
if (adjust_shared_perm(git_HEAD)) {
error("Unable to fix permissions on %s", lockpath);
error_unlink_return:
unlink_or_warn(lockpath);
error_free_return:
free(git_HEAD);
return -1;
}
#ifndef NO_SYMLINK_HEAD
done:
#endif
if (logmsg && !read_ref(refs_heads_master, new_sha1))
log_ref_write(ref_target, old_sha1, new_sha1, logmsg);
free(git_HEAD);
return 0;
}
static char *ref_msg(const char *line, const char *endp)
{
const char *ep;
line += 82;
ep = memchr(line, '\n', endp - line);
if (!ep)
ep = endp;
return xmemdupz(line, ep - line);
}
int read_ref_at(const char *refname, unsigned long at_time, int cnt,
unsigned char *sha1, char **msg,
unsigned long *cutoff_time, int *cutoff_tz, int *cutoff_cnt)
{
const char *logfile, *logdata, *logend, *rec, *lastgt, *lastrec;
char *tz_c;
int logfd, tz, reccnt = 0;
struct stat st;
unsigned long date;
unsigned char logged_sha1[20];
void *log_mapped;
size_t mapsz;
logfile = git_path("logs/%s", refname);
logfd = open(logfile, O_RDONLY, 0);
if (logfd < 0)
die_errno("Unable to read log '%s'", logfile);
fstat(logfd, &st);
if (!st.st_size)
die("Log %s is empty.", logfile);
mapsz = xsize_t(st.st_size);
log_mapped = xmmap(NULL, mapsz, PROT_READ, MAP_PRIVATE, logfd, 0);
logdata = log_mapped;
close(logfd);
lastrec = NULL;
rec = logend = logdata + st.st_size;
while (logdata < rec) {
reccnt++;
if (logdata < rec && *(rec-1) == '\n')
rec--;
lastgt = NULL;
while (logdata < rec && *(rec-1) != '\n') {
rec--;
if (*rec == '>')
lastgt = rec;
}
if (!lastgt)
die("Log %s is corrupt.", logfile);
date = strtoul(lastgt + 1, &tz_c, 10);
if (date <= at_time || cnt == 0) {
show-branch --reflog: show the reflog message at the top. This changes the output so the list at the top shows the reflog message, along with their relative timestamps. You can use --reflog=<n> to show <n> most recent log entries, or use --reflog=<n>,<b> to show <n> entries going back from the entry <b>. <b> can be either a number (so --reflog=4,20 shows 4 records starting from @{20}) or a timestamp (e.g. --reflog='4,1 day'). Here is a sample output (with --list option): $ git show-branch --reflog=10 --list jc/show-reflog [jc/show-reflog@{0}] (3 minutes ago) commit (amend): show-branch --ref [jc/show-reflog@{1}] (5 minutes ago) reset HEAD^ [jc/show-reflog@{2}] (14 minutes ago) commit: show-branch --reflog: sho [jc/show-reflog@{3}] (14 minutes ago) commit: show-branch --reflog: sho [jc/show-reflog@{4}] (18 minutes ago) commit (amend): Extend read_ref_a [jc/show-reflog@{5}] (18 minutes ago) commit (amend): Extend read_ref_a [jc/show-reflog@{6}] (18 minutes ago) commit (amend): Extend read_ref_a [jc/show-reflog@{7}] (18 minutes ago) am: read_ref_at(): allow retrievi [jc/show-reflog@{8}] (18 minutes ago) reset --hard HEAD~4 [jc/show-reflog@{9}] (61 minutes ago) commit: show-branch --reflog: use This shows what I did more cleanly: $ git show-branch --reflog=10 jc/show-reflog ! [jc/show-reflog@{0}] (3 minutes ago) commit (amend): show-branch --ref ! [jc/show-reflog@{1}] (5 minutes ago) reset HEAD^ ! [jc/show-reflog@{2}] (14 minutes ago) commit: show-branch --reflog: ! [jc/show-reflog@{3}] (14 minutes ago) commit: show-branch --reflog: ! [jc/show-reflog@{4}] (18 minutes ago) commit (amend): Extend read_ ! [jc/show-reflog@{5}] (18 minutes ago) commit (amend): Extend read ! [jc/show-reflog@{6}] (18 minutes ago) commit (amend): Extend rea ! [jc/show-reflog@{7}] (18 minutes ago) am: read_ref_at(): allow ! [jc/show-reflog@{8}] (18 minutes ago) reset --hard HEAD~4 ! [jc/show-reflog@{9}] (61 minutes ago) commit: show-branch --r ---------- + [jc/show-reflog@{0}] show-branch --reflog: show the reflog + [jc/show-reflog@{2}] show-branch --reflog: show the reflog +++ [jc/show-reflog@{1}] show-branch --reflog: show the reflog +++++ [jc/show-reflog@{4}] Extend read_ref_at() to be usable fro + [jc/show-reflog@{5}] Extend read_ref_at() to be usable fro + [jc/show-reflog@{6}] Extend read_ref_at() to be usable fro + [jc/show-reflog@{7}] read_ref_at(): allow retrieving the r + [jc/show-reflog@{9}] show-branch --reflog: use updated rea + [jc/show-reflog@{9}^] read_ref_at(): allow reporting the c + [jc/show-reflog@{9}~2] show-branch --reflog: show the refl + [jc/show-reflog@{9}~3] read_ref_at(): allow retrieving the ++++++++++ [jc/show-reflog@{8}] dwim_ref(): Separate name-to-ref DWIM At @{9}, I had a commit to complete 5 patch series, but I wanted to consolidate two commits that enhances read_ref_at() into one (they were @{9}^ and @{9}~3), and another two that touch show-branch into one (@{9} and @{9}~2). I first saved them with "format-patch -4", and then did a reset at @{8}. At @{7}, I applied one of them with "am", and then used "git-apply" on the other one, and amended the commit at @{6} (so @{6} and @{7} has the same parent). I did not like the log message, so I amended again at @{5}. Then I cherry-picked @{9}~2 to create @{3} (the log message shows that it needs to learn to set GIT_REFLOG_ACTION -- it uses "git-commit" and the log entry is attributed for it). Another cherry-pick built @{2} out of @{9}, but what I wanted to do was to squash these two into one, so I did a "reset HEAD^" at @{1} and then made the final commit by amending what was at the top. Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-01-19 17:20:23 +08:00
tz = strtoul(tz_c, NULL, 10);
if (msg)
*msg = ref_msg(rec, logend);
if (cutoff_time)
*cutoff_time = date;
if (cutoff_tz)
*cutoff_tz = tz;
if (cutoff_cnt)
show-branch --reflog: show the reflog message at the top. This changes the output so the list at the top shows the reflog message, along with their relative timestamps. You can use --reflog=<n> to show <n> most recent log entries, or use --reflog=<n>,<b> to show <n> entries going back from the entry <b>. <b> can be either a number (so --reflog=4,20 shows 4 records starting from @{20}) or a timestamp (e.g. --reflog='4,1 day'). Here is a sample output (with --list option): $ git show-branch --reflog=10 --list jc/show-reflog [jc/show-reflog@{0}] (3 minutes ago) commit (amend): show-branch --ref [jc/show-reflog@{1}] (5 minutes ago) reset HEAD^ [jc/show-reflog@{2}] (14 minutes ago) commit: show-branch --reflog: sho [jc/show-reflog@{3}] (14 minutes ago) commit: show-branch --reflog: sho [jc/show-reflog@{4}] (18 minutes ago) commit (amend): Extend read_ref_a [jc/show-reflog@{5}] (18 minutes ago) commit (amend): Extend read_ref_a [jc/show-reflog@{6}] (18 minutes ago) commit (amend): Extend read_ref_a [jc/show-reflog@{7}] (18 minutes ago) am: read_ref_at(): allow retrievi [jc/show-reflog@{8}] (18 minutes ago) reset --hard HEAD~4 [jc/show-reflog@{9}] (61 minutes ago) commit: show-branch --reflog: use This shows what I did more cleanly: $ git show-branch --reflog=10 jc/show-reflog ! [jc/show-reflog@{0}] (3 minutes ago) commit (amend): show-branch --ref ! [jc/show-reflog@{1}] (5 minutes ago) reset HEAD^ ! [jc/show-reflog@{2}] (14 minutes ago) commit: show-branch --reflog: ! [jc/show-reflog@{3}] (14 minutes ago) commit: show-branch --reflog: ! [jc/show-reflog@{4}] (18 minutes ago) commit (amend): Extend read_ ! [jc/show-reflog@{5}] (18 minutes ago) commit (amend): Extend read ! [jc/show-reflog@{6}] (18 minutes ago) commit (amend): Extend rea ! [jc/show-reflog@{7}] (18 minutes ago) am: read_ref_at(): allow ! [jc/show-reflog@{8}] (18 minutes ago) reset --hard HEAD~4 ! [jc/show-reflog@{9}] (61 minutes ago) commit: show-branch --r ---------- + [jc/show-reflog@{0}] show-branch --reflog: show the reflog + [jc/show-reflog@{2}] show-branch --reflog: show the reflog +++ [jc/show-reflog@{1}] show-branch --reflog: show the reflog +++++ [jc/show-reflog@{4}] Extend read_ref_at() to be usable fro + [jc/show-reflog@{5}] Extend read_ref_at() to be usable fro + [jc/show-reflog@{6}] Extend read_ref_at() to be usable fro + [jc/show-reflog@{7}] read_ref_at(): allow retrieving the r + [jc/show-reflog@{9}] show-branch --reflog: use updated rea + [jc/show-reflog@{9}^] read_ref_at(): allow reporting the c + [jc/show-reflog@{9}~2] show-branch --reflog: show the refl + [jc/show-reflog@{9}~3] read_ref_at(): allow retrieving the ++++++++++ [jc/show-reflog@{8}] dwim_ref(): Separate name-to-ref DWIM At @{9}, I had a commit to complete 5 patch series, but I wanted to consolidate two commits that enhances read_ref_at() into one (they were @{9}^ and @{9}~3), and another two that touch show-branch into one (@{9} and @{9}~2). I first saved them with "format-patch -4", and then did a reset at @{8}. At @{7}, I applied one of them with "am", and then used "git-apply" on the other one, and amended the commit at @{6} (so @{6} and @{7} has the same parent). I did not like the log message, so I amended again at @{5}. Then I cherry-picked @{9}~2 to create @{3} (the log message shows that it needs to learn to set GIT_REFLOG_ACTION -- it uses "git-commit" and the log entry is attributed for it). Another cherry-pick built @{2} out of @{9}, but what I wanted to do was to squash these two into one, so I did a "reset HEAD^" at @{1} and then made the final commit by amending what was at the top. Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-01-19 17:20:23 +08:00
*cutoff_cnt = reccnt - 1;
if (lastrec) {
if (get_sha1_hex(lastrec, logged_sha1))
die("Log %s is corrupt.", logfile);
if (get_sha1_hex(rec + 41, sha1))
die("Log %s is corrupt.", logfile);
if (hashcmp(logged_sha1, sha1)) {
warning("Log %s has gap after %s.",
logfile, show_date(date, tz, DATE_RFC2822));
}
}
else if (date == at_time) {
if (get_sha1_hex(rec + 41, sha1))
die("Log %s is corrupt.", logfile);
}
else {
if (get_sha1_hex(rec + 41, logged_sha1))
die("Log %s is corrupt.", logfile);
if (hashcmp(logged_sha1, sha1)) {
warning("Log %s unexpectedly ended on %s.",
logfile, show_date(date, tz, DATE_RFC2822));
}
}
munmap(log_mapped, mapsz);
return 0;
}
lastrec = rec;
if (cnt > 0)
cnt--;
}
rec = logdata;
while (rec < logend && *rec != '>' && *rec != '\n')
rec++;
if (rec == logend || *rec == '\n')
die("Log %s is corrupt.", logfile);
date = strtoul(rec + 1, &tz_c, 10);
tz = strtoul(tz_c, NULL, 10);
if (get_sha1_hex(logdata, sha1))
die("Log %s is corrupt.", logfile);
if (is_null_sha1(sha1)) {
if (get_sha1_hex(logdata + 41, sha1))
die("Log %s is corrupt.", logfile);
}
if (msg)
*msg = ref_msg(logdata, logend);
munmap(log_mapped, mapsz);
if (cutoff_time)
*cutoff_time = date;
if (cutoff_tz)
*cutoff_tz = tz;
if (cutoff_cnt)
*cutoff_cnt = reccnt;
return 1;
}
static int show_one_reflog_ent(struct strbuf *sb, each_reflog_ent_fn fn, void *cb_data)
{
unsigned char osha1[20], nsha1[20];
char *email_end, *message;
unsigned long timestamp;
int tz;
/* old SP new SP name <email> SP time TAB msg LF */
if (sb->len < 83 || sb->buf[sb->len - 1] != '\n' ||
get_sha1_hex(sb->buf, osha1) || sb->buf[40] != ' ' ||
get_sha1_hex(sb->buf + 41, nsha1) || sb->buf[81] != ' ' ||
!(email_end = strchr(sb->buf + 82, '>')) ||
email_end[1] != ' ' ||
!(timestamp = strtoul(email_end + 2, &message, 10)) ||
!message || message[0] != ' ' ||
(message[1] != '+' && message[1] != '-') ||
!isdigit(message[2]) || !isdigit(message[3]) ||
!isdigit(message[4]) || !isdigit(message[5]))
return 0; /* corrupt? */
email_end[1] = '\0';
tz = strtol(message + 1, NULL, 10);
if (message[6] != '\t')
message += 6;
else
message += 7;
return fn(osha1, nsha1, sb->buf + 82, timestamp, tz, message, cb_data);
}
static char *find_beginning_of_line(char *bob, char *scan)
{
while (bob < scan && *(--scan) != '\n')
; /* keep scanning backwards */
/*
* Return either beginning of the buffer, or LF at the end of
* the previous line.
*/
return scan;
}
int for_each_reflog_ent_reverse(const char *refname, each_reflog_ent_fn fn, void *cb_data)
{
struct strbuf sb = STRBUF_INIT;
FILE *logfp;
long pos;
int ret = 0, at_tail = 1;
logfp = fopen(git_path("logs/%s", refname), "r");
if (!logfp)
return -1;
/* Jump to the end */
if (fseek(logfp, 0, SEEK_END) < 0)
return error("cannot seek back reflog for %s: %s",
refname, strerror(errno));
pos = ftell(logfp);
while (!ret && 0 < pos) {
int cnt;
size_t nread;
char buf[BUFSIZ];
char *endp, *scanp;
/* Fill next block from the end */
cnt = (sizeof(buf) < pos) ? sizeof(buf) : pos;
if (fseek(logfp, pos - cnt, SEEK_SET))
return error("cannot seek back reflog for %s: %s",
refname, strerror(errno));
nread = fread(buf, cnt, 1, logfp);
if (nread != 1)
return error("cannot read %d bytes from reflog for %s: %s",
cnt, refname, strerror(errno));
pos -= cnt;
scanp = endp = buf + cnt;
if (at_tail && scanp[-1] == '\n')
/* Looking at the final LF at the end of the file */
scanp--;
at_tail = 0;
while (buf < scanp) {
/*
* terminating LF of the previous line, or the beginning
* of the buffer.
*/
char *bp;
bp = find_beginning_of_line(buf, scanp);
if (*bp != '\n') {
strbuf_splice(&sb, 0, 0, buf, endp - buf);
if (pos)
break; /* need to fill another block */
scanp = buf - 1; /* leave loop */
} else {
/*
* (bp + 1) thru endp is the beginning of the
* current line we have in sb
*/
strbuf_splice(&sb, 0, 0, bp + 1, endp - (bp + 1));
scanp = bp;
endp = bp + 1;
}
ret = show_one_reflog_ent(&sb, fn, cb_data);
strbuf_reset(&sb);
if (ret)
break;
}
}
if (!ret && sb.len)
ret = show_one_reflog_ent(&sb, fn, cb_data);
fclose(logfp);
strbuf_release(&sb);
return ret;
}
int for_each_reflog_ent(const char *refname, each_reflog_ent_fn fn, void *cb_data)
{
FILE *logfp;
struct strbuf sb = STRBUF_INIT;
int ret = 0;
logfp = fopen(git_path("logs/%s", refname), "r");
if (!logfp)
return -1;
while (!ret && !strbuf_getwholeline(&sb, logfp, '\n'))
ret = show_one_reflog_ent(&sb, fn, cb_data);
fclose(logfp);
strbuf_release(&sb);
return ret;
}
/*
* Call fn for each reflog in the namespace indicated by name. name
* must be empty or end with '/'. Name will be used as a scratch
* space, but its contents will be restored before return.
*/
static int do_for_each_reflog(struct strbuf *name, each_ref_fn fn, void *cb_data)
{
DIR *d = opendir(git_path("logs/%s", name->buf));
int retval = 0;
struct dirent *de;
int oldlen = name->len;
if (!d)
return name->len ? errno : 0;
while ((de = readdir(d)) != NULL) {
struct stat st;
if (de->d_name[0] == '.')
continue;
if (has_extension(de->d_name, ".lock"))
continue;
strbuf_addstr(name, de->d_name);
if (stat(git_path("logs/%s", name->buf), &st) < 0) {
; /* silently ignore */
} else {
if (S_ISDIR(st.st_mode)) {
strbuf_addch(name, '/');
retval = do_for_each_reflog(name, fn, cb_data);
} else {
unsigned char sha1[20];
if (read_ref_full(name->buf, sha1, 0, NULL))
retval = error("bad ref for %s", name->buf);
else
retval = fn(name->buf, sha1, 0, cb_data);
}
if (retval)
break;
}
strbuf_setlen(name, oldlen);
}
closedir(d);
return retval;
}
int for_each_reflog(each_ref_fn fn, void *cb_data)
{
int retval;
struct strbuf name;
strbuf_init(&name, PATH_MAX);
retval = do_for_each_reflog(&name, fn, cb_data);
strbuf_release(&name);
return retval;
}
int update_ref(const char *action, const char *refname,
const unsigned char *sha1, const unsigned char *oldval,
int flags, enum action_on_err onerr)
{
static struct ref_lock *lock;
lock = lock_any_ref_for_update(refname, oldval, flags);
if (!lock) {
const char *str = "Cannot lock the ref '%s'.";
switch (onerr) {
case MSG_ON_ERR: error(str, refname); break;
case DIE_ON_ERR: die(str, refname); break;
case QUIET_ON_ERR: break;
}
return 1;
}
if (write_ref_sha1(lock, sha1, action) < 0) {
const char *str = "Cannot update the ref '%s'.";
switch (onerr) {
case MSG_ON_ERR: error(str, refname); break;
case DIE_ON_ERR: die(str, refname); break;
case QUIET_ON_ERR: break;
}
return 1;
}
return 0;
}
struct ref *find_ref_by_name(const struct ref *list, const char *name)
{
for ( ; list; list = list->next)
if (!strcmp(list->name, name))
return (struct ref *)list;
return NULL;
}
/*
* generate a format suitable for scanf from a ref_rev_parse_rules
* rule, that is replace the "%.*s" spec with a "%s" spec
*/
static void gen_scanf_fmt(char *scanf_fmt, const char *rule)
{
char *spec;
spec = strstr(rule, "%.*s");
if (!spec || strstr(spec + 4, "%.*s"))
die("invalid rule in ref_rev_parse_rules: %s", rule);
/* copy all until spec */
strncpy(scanf_fmt, rule, spec - rule);
scanf_fmt[spec - rule] = '\0';
/* copy new spec */
strcat(scanf_fmt, "%s");
/* copy remaining rule */
strcat(scanf_fmt, spec + 4);
return;
}
char *shorten_unambiguous_ref(const char *refname, int strict)
{
int i;
static char **scanf_fmts;
static int nr_rules;
char *short_name;
/* pre generate scanf formats from ref_rev_parse_rules[] */
if (!nr_rules) {
size_t total_len = 0;
/* the rule list is NULL terminated, count them first */
for (; ref_rev_parse_rules[nr_rules]; nr_rules++)
/* no +1 because strlen("%s") < strlen("%.*s") */
total_len += strlen(ref_rev_parse_rules[nr_rules]);
scanf_fmts = xmalloc(nr_rules * sizeof(char *) + total_len);
total_len = 0;
for (i = 0; i < nr_rules; i++) {
scanf_fmts[i] = (char *)&scanf_fmts[nr_rules]
+ total_len;
gen_scanf_fmt(scanf_fmts[i], ref_rev_parse_rules[i]);
total_len += strlen(ref_rev_parse_rules[i]);
}
}
/* bail out if there are no rules */
if (!nr_rules)
return xstrdup(refname);
/* buffer for scanf result, at most refname must fit */
short_name = xstrdup(refname);
/* skip first rule, it will always match */
for (i = nr_rules - 1; i > 0 ; --i) {
int j;
int rules_to_fail = i;
int short_name_len;
if (1 != sscanf(refname, scanf_fmts[i], short_name))
continue;
short_name_len = strlen(short_name);
/*
* in strict mode, all (except the matched one) rules
* must fail to resolve to a valid non-ambiguous ref
*/
if (strict)
rules_to_fail = nr_rules;
/*
* check if the short name resolves to a valid ref,
* but use only rules prior to the matched one
*/
for (j = 0; j < rules_to_fail; j++) {
const char *rule = ref_rev_parse_rules[j];
char refname[PATH_MAX];
/* skip matched rule */
if (i == j)
continue;
/*
* the short name is ambiguous, if it resolves
* (with this previous rule) to a valid ref
* read_ref() returns 0 on success
*/
mksnpath(refname, sizeof(refname),
rule, short_name_len, short_name);
if (ref_exists(refname))
break;
}
/*
* short name is non-ambiguous if all previous rules
* haven't resolved to a valid ref
*/
if (j == rules_to_fail)
return short_name;
}
free(short_name);
return xstrdup(refname);
}
upload/receive-pack: allow hiding ref hierarchies A repository may have refs that are only used for its internal bookkeeping purposes that should not be exposed to the others that come over the network. Teach upload-pack to omit some refs from its initial advertisement by paying attention to the uploadpack.hiderefs multi-valued configuration variable. Do the same to receive-pack via the receive.hiderefs variable. As a convenient short-hand, allow using transfer.hiderefs to set the value to both of these variables. Any ref that is under the hierarchies listed on the value of these variable is excluded from responses to requests made by "ls-remote", "fetch", etc. (for upload-pack) and "push" (for receive-pack). Because these hidden refs do not count as OUR_REF, an attempt to fetch objects at the tip of them will be rejected, and because these refs do not get advertised, "git push :" will not see local branches that have the same name as them as "matching" ones to be sent. An attempt to update/delete these hidden refs with an explicit refspec, e.g. "git push origin :refs/hidden/22", is rejected. This is not a new restriction. To the pusher, it would appear that there is no such ref, so its push request will conclude with "Now that I sent you all the data, it is time for you to update the refs. I saw that the ref did not exist when I started pushing, and I want the result to point at this commit". The receiving end will apply the compare-and-swap rule to this request and rejects the push with "Well, your update request conflicts with somebody else; I see there is such a ref.", which is the right thing to do. Otherwise a push to a hidden ref will always be "the last one wins", which is not a good default. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-01-19 08:08:30 +08:00
static struct string_list *hide_refs;
int parse_hide_refs_config(const char *var, const char *value, const char *section)
{
if (!strcmp("transfer.hiderefs", var) ||
/* NEEDSWORK: use parse_config_key() once both are merged */
(!prefixcmp(var, section) && var[strlen(section)] == '.' &&
!strcmp(var + strlen(section), ".hiderefs"))) {
char *ref;
int len;
if (!value)
return config_error_nonbool(var);
ref = xstrdup(value);
len = strlen(ref);
while (len && ref[len - 1] == '/')
ref[--len] = '\0';
if (!hide_refs) {
hide_refs = xcalloc(1, sizeof(*hide_refs));
hide_refs->strdup_strings = 1;
}
string_list_append(hide_refs, ref);
}
return 0;
}
int ref_is_hidden(const char *refname)
{
struct string_list_item *item;
if (!hide_refs)
return 0;
for_each_string_list_item(item, hide_refs) {
int len;
if (prefixcmp(refname, item->string))
continue;
len = strlen(item->string);
if (!refname[len] || refname[len] == '/')
return 1;
}
return 0;
}