New hash table implementation

---
 submodule.c | 25 +------------------------
 1 file changed, 1 insertion(+), 24 deletions(-)

submodule.c +1 ~~-24~~

index 1905d75..e388487 100644
@@ -116,30 +116,7 @@ int remove_path_from_gitmodules(const char *path)
 
 void stage_updated_gitmodules(void)
 {
-	struct strbuf buf = STRBUF_INIT;
-	struct stat st;
-	int pos;
-	struct cache_entry *ce;
-	int namelen = strlen(".gitmodules");
-
-	pos = cache_name_pos(".gitmodules", namelen);
-	if (pos < 0) {
-		warning(_("could not find .gitmodules in index"));
-		return;
-	}
-	ce = active_cache[pos];
-	ce->ce_flags = namelen;
-	if (strbuf_read_file(&buf, ".gitmodules", 0) < 0)
-		die(_("reading updated .gitmodules failed"));
-	if (lstat(".gitmodules", &st) < 0)
-		die_errno(_("unable to stat updated .gitmodules"));
-	fill_stat_cache_info(ce, &st);
-	ce->ce_mode = ce_mode_from_stat(ce, st.st_mode);
-	if (remove_cache_entry_at(pos) < 0)
-		die(_("unable to remove .gitmodules from index"));
-	if (write_sha1_file(buf.buf, buf.len, blob_type, ce->sha1))
-		die(_("adding updated .gitmodules failed"));
-	if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE))
+	if (add_file_to_cache(".gitmodules", 0))
 		die(_("staging updated .gitmodules failed"));
 }

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #2 lore raw

PATCH v5 2/14 add a hashtable implementation that supports O(1) removal

The existing hashtable implementation (in hash.[ch]) uses open addressing (i.e. resolve hash collisions by distributing entries across the table). Thus, removal is difficult to implement with less than O(n) complexity. Resolving collisions of entries with identical hashes (e.g. via chaining) is left to the client code.

Add a hashtable implementation that supports O(1) removal and is slightly easier to use due to builtin entry chaining.

Supports all basic operations init, free, get, add, remove and iteration.

Also includes ready-to-use hash functions based on the public domain FNV-1 algorithm (http://www.isthe.com/chongo/tech/comp/fnv).

The per-entry data structure (hashmap_entry) is piggybacked in front of the client's data structure to save memory. See test-hashmap.c for usage examples.

The hashtable is resized by a factor of four when 80% full. With these settings, average memory consumption is about 2/3 of hash.[ch], and insertion is about twice as fast due to less frequent resizing.

Lookups are also slightly faster, because entries are strictly confined to their bucket (i.e. no data of other buckets needs to be traversed).

In reply to Jonathan Nieder

---
 Documentation/technical/api-hashmap.txt | 235 ++++++++++++++++++++++
 Makefile                                |   3 +
 hashmap.c                               | 228 +++++++++++++++++++++
 hashmap.h                               |  71 +++++++
 t/t0011-hashmap.sh                      | 240 ++++++++++++++++++++++
 test-hashmap.c                          | 340 ++++++++++++++++++++++++++++++++
 6 files changed, 1117 insertions(+)
 create mode 100644 Documentation/technical/api-hashmap.txt
 create mode 100644 hashmap.c
 create mode 100644 hashmap.h
 create mode 100755 t/t0011-hashmap.sh
 create mode 100644 test-hashmap.c

Documentation/technical/api-hashmap.txt new file +235 -0

new file mode 100644
index 0000000..b2280f1
@@ -0,0 +1,235 @@
+hashmap API
+===========
+
+The hashmap API is a generic implementation of hash-based key-value mappings.
+
+Data Structures
+---------------
+
+`struct hashmap`::
+
+	The hash table structure.
++
+The `size` member keeps track of the total number of entries. The `cmpfn`
+member is a function used to compare two entries for equality. The `table` and
+`tablesize` members store the hash table and its size, respectively.
+
+`struct hashmap_entry`::
+
+	An opaque structure representing an entry in the hash table, which must
+	be used as first member of user data structures. Ideally it should be
+	followed by an int-sized member to prevent unused memory on 64-bit
+	systems due to alignment.
++
+The `hash` member is the entry's hash code and the `next` member points to the
+next entry in case of collisions (i.e. if multiple entries map to the same
+bucket).
+
+`struct hashmap_iter`::
+
+	An iterator structure, to be used with hashmap_iter_* functions.
+
+Types
+-----
+
+`int (*hashmap_cmp_fn)(const void *entry, const void *entry_or_key, const void *keydata)`::
+
+	User-supplied function to test two hashmap entries for equality. Shall
+	return 0 if the entries are equal.
++
+This function is always called with non-NULL `entry` / `entry_or_key`
+parameters that have the same hash code. When looking up an entry, the `key`
+and `keydata` parameters to hashmap_get and hashmap_remove are always passed
+as second and third argument, respectively. Otherwise, `keydata` is NULL.
+
+Functions
+---------
+
+`unsigned int strhash(const char *buf)`::
+`unsigned int strihash(const char *buf)`::
+`unsigned int memhash(const void *buf, size_t len)`::
+`unsigned int memihash(const void *buf, size_t len)`::
+
+	Ready-to-use hash functions for strings, using the FNV-1 algorithm (see
+	http://www.isthe.com/chongo/tech/comp/fnv).
++
+`strhash` and `strihash` take 0-terminated strings, while `memhash` and
+`memihash` operate on arbitrary-length memory.
++
+`strihash` and `memihash` are case insensitive versions.
+
+`void hashmap_init(struct hashmap *map, hashmap_cmp_fn equals_function, size_t initial_size)`::
+
+	Initializes a hashmap structure.
++
+`map` is the hashmap to initialize.
++
+The `equals_function` can be specified to compare two entries for equality.
+If NULL, entries are considered equal if their hash codes are equal.
++
+If the total number of entries is known in advance, the `initial_size`
+parameter may be used to preallocate a sufficiently large table and thus
+prevent expensive resizing. If 0, the table is dynamically resized.
+
+`void hashmap_free(struct hashmap *map, int free_entries)`::
+
+	Frees a hashmap structure and allocated memory.
++
+`map` is the hashmap to free.
++
+If `free_entries` is true, each hashmap_entry in the map is freed as well
+(using stdlib's free()).
+
+`void hashmap_entry_init(void *entry, int hash)`::
+
+	Initializes a hashmap_entry structure.
++
+`entry` points to the entry to initialize.
++
+`hash` is the hash code of the entry.
+
+`void *hashmap_get(const struct hashmap *map, const void *key, const void *keydata)`::
+
+	Returns the hashmap entry for the specified key, or NULL if not found.
++
+`map` is the hashmap structure.
++
+`key` is a hashmap_entry structure (or user data structure that starts with
+hashmap_entry) that has at least been initialized with the proper hash code
+(via `hashmap_entry_init`).
++
+If an entry with matching hash code is found, `key` and `keydata` are passed
+to `hashmap_cmp_fn` to decide whether the entry matches the key.
+
+`void *hashmap_get_next(const struct hashmap *map, const void *entry)`::
+
+	Returns the next equal hashmap entry, or NULL if not found. This can be
+	used to iterate over duplicate entries (see `hashmap_add`).
++
+`map` is the hashmap structure.
++
+`entry` is the hashmap_entry to start the search from, obtained via a previous
+call to `hashmap_get` or `hashmap_get_next`.
+
+`void hashmap_add(struct hashmap *map, void *entry)`::
+
+	Adds a hashmap entry. This allows to add duplicate entries (i.e.
+	separate values with the same key according to hashmap_cmp_fn).
++
+`map` is the hashmap structure.
++
+`entry` is the entry to add.
+
+`void *hashmap_put(struct hashmap *map, void *entry)`::
+
+	Adds or replaces a hashmap entry. If the hashmap contains duplicate
+	entries equal to the specified entry, only one of them will be replaced.
++
+`map` is the hashmap structure.
++
+`entry` is the entry to add or replace.
++
+Returns the replaced entry, or NULL if not found (i.e. the entry was added).
+
+`void *hashmap_remove(struct hashmap *map, const void *key, const void *keydata)`::
+
+	Removes a hashmap entry matching the specified key. If the hashmap
+	contains duplicate entries equal to the specified key, only one of
+	them will be removed.
++
+`map` is the hashmap structure.
++
+`key` is a hashmap_entry structure (or user data structure that starts with
+hashmap_entry) that has at least been initialized with the proper hash code
+(via `hashmap_entry_init`).
++
+If an entry with matching hash code is found, `key` and `keydata` are
+passed to `hashmap_cmp_fn` to decide whether the entry matches the key.
++
+Returns the removed entry, or NULL if not found.
+
+`void hashmap_iter_init(struct hashmap *map, struct hashmap_iter *iter)`::
+`void *hashmap_iter_next(struct hashmap_iter *iter)`::
+`void *hashmap_iter_first(struct hashmap *map, struct hashmap_iter *iter)`::
+
+	Used to iterate over all entries of a hashmap.
++
+`hashmap_iter_init` initializes a `hashmap_iter` structure.
++
+`hashmap_iter_next` returns the next hashmap_entry, or NULL if there are no
+more entries.
++
+`hashmap_iter_first` is a combination of both (i.e. initializes the iterator
+and returns the first entry, if any).
+
+Usage example
+-------------
+
+Here's a simple usage example that maps long keys to double values.
+[source,c]
+------------
+struct hashmap map;
+
+struct long2double {
+	struct hashmap_entry ent; /* must be the first member! */
+	long key;
+	double value;
+};
+
+static int long2double_cmp(const struct long2double *e1, const struct long2double *e2, const void *unused)
+{
+	return !(e1->key == e2->key);
+}
+
+void long2double_init(void)
+{
+	hashmap_init(&map, (hashmap_cmp_fn) long2double_cmp, 0);
+}
+
+void long2double_free(void)
+{
+	hashmap_free(&map, 1);
+}
+
+static struct long2double *find_entry(long key)
+{
+	struct long2double k;
+	hashmap_entry_init(&k, memhash(&key, sizeof(long)));
+	k.key = key;
+	return hashmap_get(&map, &k, NULL);
+}
+
+double get_value(long key)
+{
+	struct long2double *e = find_entry(key);
+	return e ? e->value : 0;
+}
+
+void set_value(long key, double value)
+{
+	struct long2double *e = find_entry(key);
+	if (!e) {
+		e = malloc(sizeof(struct long2double));
+		hashmap_entry_init(e, memhash(&key, sizeof(long)));
+		e->key = key;
+		hashmap_add(&map, e);
+	}
+	e->value = value;
+}
+------------
+
+Using variable-sized keys
+-------------------------
+
+The `hashmap_entry_get` and `hashmap_entry_remove` functions expect an ordinary
+`hashmap_entry` structure as key to find the correct entry. If the key data is
+variable-sized (e.g. a FLEX_ARRAY string) or quite large, it is undesirable
+to create a full-fledged entry structure on the heap and copy all the key data
+into the structure.
+
+In this case, the `keydata` parameter can be used to pass
+variable-sized key data directly to the comparison function, and the `key`
+parameter can be a stripped-down, fixed size entry structure allocated on the
+stack.
+
+See test-hashmap.c for an example using arbitrary-length strings as keys.

Makefile +3 -0

index 504931f..75bb1a6 100644
@@ -555,6 +555,7 @@ TEST_PROGRAMS_NEED_X += test-date
 TEST_PROGRAMS_NEED_X += test-delta
 TEST_PROGRAMS_NEED_X += test-dump-cache-tree
 TEST_PROGRAMS_NEED_X += test-genrandom
+TEST_PROGRAMS_NEED_X += test-hashmap
 TEST_PROGRAMS_NEED_X += test-index-version
 TEST_PROGRAMS_NEED_X += test-line-buffer
 TEST_PROGRAMS_NEED_X += test-match-trees

@@ -673,6 +674,7 @@ LIB_H += gpg-interface.h
 LIB_H += graph.h
 LIB_H += grep.h
 LIB_H += hash.h
+LIB_H += hashmap.h
 LIB_H += help.h
 LIB_H += http.h
 LIB_H += kwset.h

@@ -804,6 +806,7 @@ LIB_OBJS += gpg-interface.o
 LIB_OBJS += graph.o
 LIB_OBJS += grep.o
 LIB_OBJS += hash.o
+LIB_OBJS += hashmap.o
 LIB_OBJS += help.o
 LIB_OBJS += hex.o
 LIB_OBJS += ident.o

hashmap.c new file +228 -0

228 lines not on this page · raw message

hashmap.h new file +71 -0

71 lines not on this page · raw message

t/t0011-hashmap.sh new file +240 -0

240 lines not on this page · raw message

test-hashmap.c new file +340 -0

340 lines not on this page · raw message

Signature · 1 line

1.8.5.rc0.333.g5394214

Jonathan Nieder

2016-06-15 22:59 UTC #3 lore raw

Re: [PATCH v5 02/14] add a hashtable implementation that supports O(1) removal

Hi,

Quoted 1 line · Karsten Blees

 test-hashmap.c                          | 340 ++++++++++++++++++++++++++++++++

Here come two small tweaks on top (meant for squashing in or applying to the series, whichever is more convenient).

Thanks,
Jonathan Nieder (2):
Add test-hashmap to .gitignore
Drop unnecessary #includes from test-hashmap

 .gitignore     | 1 +
 test-hashmap.c | 3 +--
 2 files changed, 2 insertions(+), 2 deletions(-)

Jonathan Nieder

2016-06-15 22:59 UTC #4 lore raw

PATCH 1/2 Add test-hashmap to .gitignore

Prevent the "test-hashmap" program from being accidentally tracked with "git add" or cluttering "git status" output.

Signed-off-by Jonathan Nieder <[email protected]>

---
 .gitignore | 1 +
 1 file changed, 1 insertion(+)

.gitignore +1 -0

index b5f9def..dc600f9 100644
@@ -182,6 +182,7 @@
 /test-dump-cache-tree
 /test-scrap-cache-tree
 /test-genrandom
+/test-hashmap
 /test-index-version
 /test-line-buffer
 /test-match-trees

Signature · 1 line

1.8.5.1

Jonathan Nieder

2016-06-15 22:59 UTC #5 lore raw

PATCH 2/2 Drop unnecessary #includes from test-hashmap

Per Documentation/CodingGuidelines most C files in git start with a #include of git-compat-util.h or another header file that includes it, such as cache.h or builtin.h. This file doesn't need anything beyond "git-compat-util.h", so use that.

Remove a #include of the system header <stdio.h> since it is already included by "git-compat-util.h".

Signed-off-by Jonathan Nieder <[email protected]>

---
 test-hashmap.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

test-hashmap.c +1 -2

index 7e86f88..f5183fb 100644
@@ -1,6 +1,5 @@
-#include "cache.h"
+#include "git-compat-util.h"
 #include "hashmap.h"
-#include <stdio.h>
 
 struct test_entry
 {

Signature · 1 line

1.8.5.1

Karsten Blees

author Acked-by

2016-06-15 22:59 UTC #6 lore raw

Re: [PATCH v5 02/14] add a hashtable implementation that supports O(1) removal

In reply to Jonathan Nieder

Am 14.12.2013 03:04, schrieb Jonathan Nieder:

Quoted 9 lines

Hi,
Quoted 1 line · Karsten Blees
 test-hashmap.c                          | 340 ++++++++++++++++++++++++++++++++
Here come two small tweaks on top (meant for squashing in or applying to the series, whichever is more convenient).

Quoted 9 lines

Thanks,
Jonathan Nieder (2):
Add test-hashmap to .gitignore
Drop unnecessary #includes from test-hashmap
 .gitignore     | 1 +
 test-hashmap.c | 3 +--
 2 files changed, 2 insertions(+), 2 deletions(-)

Thanks, these two make perfect sense.

I'm too damn slow again (merged to next two days ago), but FWIW:

Acked-by Karsten Blees <[email protected]>

Karsten Blees

author

2016-06-15 22:59 UTC #7 lore raw

PATCH v5 3/14 buitin/describe.c: use new hash map implementation

---
 builtin/describe.c | 53 ++++++++++++++++++++++++-----------------------------
 1 file changed, 24 insertions(+), 29 deletions(-)

builtin/describe.c +24 ~~-29~~

index 6f62109..0b2cef4 100644
@@ -6,7 +6,7 @@
 #include "exec_cmd.h"
 #include "parse-options.h"
 #include "diff.h"
-#include "hash.h"
+#include "hashmap.h"
 #include "argv-array.h"
 
 #define SEEN		(1u << 0)

@@ -25,7 +25,7 @@ static int longformat;
 static int first_parent;
 static int abbrev = -1; /* unspecified */
 static int max_candidates = 10;
-static struct hash_table names;
+static struct hashmap names;
 static int have_util;
 static const char *pattern;
 static int always;

@@ -37,7 +37,7 @@ static const char *diff_index_args[] = {
 };
 
 struct commit_name {
-	struct commit_name *next;
+	struct hashmap_entry entry;
 	unsigned char peeled[20];
 	struct tag *tag;
 	unsigned prio:2; /* annotated tag = 2, tag = 1, head = 0 */

@@ -50,6 +50,12 @@ static const char *prio_names[] = {
 	"head", "lightweight", "annotated",
 };
 
+static int commit_name_cmp(const struct commit_name *cn1,
+		const struct commit_name *cn2, const void *peeled)
+{
+	return hashcmp(cn1->peeled, peeled ? peeled : cn2->peeled);
+}
+
 static inline unsigned int hash_sha1(const unsigned char *sha1)
 {
 	unsigned int hash;

@@ -59,21 +65,9 @@ static inline unsigned int hash_sha1(const unsigned char *sha1)
 
 static inline struct commit_name *find_commit_name(const unsigned char *peeled)
 {
-	struct commit_name *n = lookup_hash(hash_sha1(peeled), &names);
-	while (n && !!hashcmp(peeled, n->peeled))
-		n = n->next;
-	return n;
-}
-
-static int set_util(void *chain, void *data)
-{
-	struct commit_name *n;
-	for (n = chain; n; n = n->next) {
-		struct commit *c = lookup_commit_reference_gently(n->peeled, 1);
-		if (c)
-			c->util = n;
-	}
-	return 0;
+	struct commit_name key;
+	hashmap_entry_init(&key, hash_sha1(peeled));
+	return hashmap_get(&names, &key, peeled);
 }
 
 static int replace_name(struct commit_name *e,

@@ -118,16 +112,10 @@ static void add_to_known_names(const char *path,
 	struct tag *tag = NULL;
 	if (replace_name(e, prio, sha1, &tag)) {
 		if (!e) {
-			void **pos;
 			e = xmalloc(sizeof(struct commit_name));
 			hashcpy(e->peeled, peeled);
-			pos = insert_hash(hash_sha1(peeled), e, &names);
-			if (pos) {
-				e->next = *pos;
-				*pos = e;
-			} else {
-				e->next = NULL;
-			}
+			hashmap_entry_init(e, hash_sha1(peeled));
+			hashmap_add(&names, e);
 			e->path = NULL;
 		}
 		e->tag = tag;

@@ -292,7 +280,14 @@ static void describe(const char *arg, int last_one)
 		fprintf(stderr, _("searching to describe %s\n"), arg);
 
 	if (!have_util) {
-		for_each_hash(&names, set_util, NULL);
+		struct hashmap_iter iter;
+		struct commit *c;
+		struct commit_name *n = hashmap_iter_first(&names, &iter);
+		for (; n; n = hashmap_iter_next(&iter)) {
+			c = lookup_commit_reference_gently(n->peeled, 1);
+			if (c)
+				c->util = n;
+		}
 		have_util = 1;
 	}

@@ -463,9 +458,9 @@ int cmd_describe(int argc, const char **argv, const char *prefix)
 		return cmd_name_rev(args.argc, args.argv, prefix);
 	}
 
-	init_hash(&names);
+	hashmap_init(&names, (hashmap_cmp_fn) commit_name_cmp, 0);
 	for_each_rawref(get_name, NULL);
-	if (!names.nr && !always)
+	if (!names.size && !always)
 		die(_("No names found, cannot describe anything."));
 
 	if (argc == 0) {

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #8 lore raw

PATCH v5 4/14 diffcore-rename.c: move code around to prepare for the next patch

No actual code changes, just move hash_filespec up and outdent part of find_identical_files.

---
 diffcore-rename.c | 98 +++++++++++++++++++++++++++----------------------------
 1 file changed, 49 insertions(+), 49 deletions(-)

diffcore-rename.c +49 ~~-49~~

index 6c7a72f..008a60c 100644
@@ -248,6 +248,18 @@ struct file_similarity {
 	struct file_similarity *next;
 };
 
+static unsigned int hash_filespec(struct diff_filespec *filespec)
+{
+	unsigned int hash;
+	if (!filespec->sha1_valid) {
+		if (diff_populate_filespec(filespec, 0))
+			return 0;
+		hash_sha1_file(filespec->data, filespec->size, "blob", filespec->sha1);
+	}
+	memcpy(&hash, filespec->sha1, sizeof(hash));
+	return hash;
+}
+
 static int find_identical_files(struct file_similarity *src,
 				struct file_similarity *dst,
 				struct diff_options *options)

@@ -258,46 +270,46 @@ static int find_identical_files(struct file_similarity *src,
 	 * Walk over all the destinations ...
 	 */
 	do {
-		struct diff_filespec *target = dst->filespec;
-		struct file_similarity *p, *best;
-		int i = 100, best_score = -1;
-
-		/*
-		 * .. to find the best source match
-		 */
-		best = NULL;
-		for (p = src; p; p = p->next) {
-			int score;
-			struct diff_filespec *source = p->filespec;
-
-			/* False hash collision? */
-			if (hashcmp(source->sha1, target->sha1))
-				continue;
-			/* Non-regular files? If so, the modes must match! */
-			if (!S_ISREG(source->mode) || !S_ISREG(target->mode)) {
-				if (source->mode != target->mode)
-					continue;
-			}
-			/* Give higher scores to sources that haven't been used already */
-			score = !source->rename_used;
-			if (source->rename_used && options->detect_rename != DIFF_DETECT_COPY)
-				continue;
-			score += basename_same(source, target);
-			if (score > best_score) {
-				best = p;
-				best_score = score;
-				if (score == 2)
-					break;
-			}
+	struct diff_filespec *target = dst->filespec;
+	struct file_similarity *p, *best;
+	int i = 100, best_score = -1;
 
-			/* Too many identical alternatives? Pick one */
-			if (!--i)
-				break;
+	/*
+	 * .. to find the best source match
+	 */
+	best = NULL;
+	for (p = src; p; p = p->next) {
+		int score;
+		struct diff_filespec *source = p->filespec;
+
+		/* False hash collision? */
+		if (hashcmp(source->sha1, target->sha1))
+			continue;
+		/* Non-regular files? If so, the modes must match! */
+		if (!S_ISREG(source->mode) || !S_ISREG(target->mode)) {
+			if (source->mode != target->mode)
+				continue;
 		}
-		if (best) {
-			record_rename_pair(dst->index, best->index, MAX_SCORE);
-			renames++;
+		/* Give higher scores to sources that haven't been used already */
+		score = !source->rename_used;
+		if (source->rename_used && options->detect_rename != DIFF_DETECT_COPY)
+			continue;
+		score += basename_same(source, target);
+		if (score > best_score) {
+			best = p;
+			best_score = score;
+			if (score == 2)
+				break;
 		}
+
+		/* Too many identical alternatives? Pick one */
+		if (!--i)
+			break;
+	}
+	if (best) {
+		record_rename_pair(dst->index, best->index, MAX_SCORE);
+		renames++;
+	}
 	} while ((dst = dst->next) != NULL);
 	return renames;
 }

@@ -343,18 +355,6 @@ static int find_same_files(void *ptr, void *data)
 	return ret;
 }
 
-static unsigned int hash_filespec(struct diff_filespec *filespec)
-{
-	unsigned int hash;
-	if (!filespec->sha1_valid) {
-		if (diff_populate_filespec(filespec, 0))
-			return 0;
-		hash_sha1_file(filespec->data, filespec->size, "blob", filespec->sha1);
-	}
-	memcpy(&hash, filespec->sha1, sizeof(hash));
-	return hash;
-}
-
 static void insert_file_table(struct hash_table *table, int src_dst, int index, struct diff_filespec *filespec)
 {
 	void **pos;

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #9 lore raw

PATCH v5 5/14 diffcore-rename.c: simplify finding exact renames

The find_exact_renames function currently only uses the hash table for grouping, i.e.:

1. add sources
2. add destinations
3. iterate all buckets, per bucket:
4. split sources from destinations
5. iterate destinations, per destination:
6. iterate sources to find best match

This can be simplified by utilizing the lookup functionality of the hash table, i.e.:

1. add sources
2. iterate destinations, per destination:
3. lookup sources matching the current destination
4. iterate sources to find best match

This saves several iterations and file_similarity allocations for the destinations.

---
 diffcore-rename.c | 75 +++++++++++++++----------------------------------------
 1 file changed, 20 insertions(+), 55 deletions(-)

diffcore-rename.c +20 ~~-55~~

index 008a60c..cfeb408 100644
@@ -243,7 +243,7 @@ static int score_compare(const void *a_, const void *b_)
 }
 
 struct file_similarity {
-	int src_dst, index;
+	int index;
 	struct diff_filespec *filespec;
 	struct file_similarity *next;
 };

@@ -260,25 +260,21 @@ static unsigned int hash_filespec(struct diff_filespec *filespec)
 	return hash;
 }
 
-static int find_identical_files(struct file_similarity *src,
-				struct file_similarity *dst,
+static int find_identical_files(struct hash_table *srcs,
+				int dst_index,
 				struct diff_options *options)
 {
 	int renames = 0;
 
-	/*
-	 * Walk over all the destinations ...
-	 */
-	do {
-	struct diff_filespec *target = dst->filespec;
+	struct diff_filespec *target = rename_dst[dst_index].two;
 	struct file_similarity *p, *best;
 	int i = 100, best_score = -1;
 
 	/*
-	 * .. to find the best source match
+	 * Find the best source match for specified destination.
 	 */
 	best = NULL;
-	for (p = src; p; p = p->next) {
+	for (p = lookup_hash(hash_filespec(target), srcs); p; p = p->next) {
 		int score;
 		struct diff_filespec *source = p->filespec;

@@ -307,61 +303,28 @@ static int find_identical_files(struct file_similarity *src,
 			break;
 	}
 	if (best) {
-		record_rename_pair(dst->index, best->index, MAX_SCORE);
+		record_rename_pair(dst_index, best->index, MAX_SCORE);
 		renames++;
 	}
-	} while ((dst = dst->next) != NULL);
 	return renames;
 }
 
-static void free_similarity_list(struct file_similarity *p)
+static int free_similarity_list(void *p, void *unused)
 {
 	while (p) {
 		struct file_similarity *entry = p;
-		p = p->next;
+		p = entry->next;
 		free(entry);
 	}
+	return 0;
 }
 
-static int find_same_files(void *ptr, void *data)
-{
-	int ret;
-	struct file_similarity *p = ptr;
-	struct file_similarity *src = NULL, *dst = NULL;
-	struct diff_options *options = data;
-
-	/* Split the hash list up into sources and destinations */
-	do {
-		struct file_similarity *entry = p;
-		p = p->next;
-		if (entry->src_dst < 0) {
-			entry->next = src;
-			src = entry;
-		} else {
-			entry->next = dst;
-			dst = entry;
-		}
-	} while (p);
-
-	/*
-	 * If we have both sources *and* destinations, see if
-	 * we can match them up
-	 */
-	ret = (src && dst) ? find_identical_files(src, dst, options) : 0;
-
-	/* Free the hashes and return the number of renames found */
-	free_similarity_list(src);
-	free_similarity_list(dst);
-	return ret;
-}
-
-static void insert_file_table(struct hash_table *table, int src_dst, int index, struct diff_filespec *filespec)
+static void insert_file_table(struct hash_table *table, int index, struct diff_filespec *filespec)
 {
 	void **pos;
 	unsigned int hash;
 	struct file_similarity *entry = xmalloc(sizeof(*entry));
 
-	entry->src_dst = src_dst;
 	entry->index = index;
 	entry->filespec = filespec;
 	entry->next = NULL;

@@ -385,24 +348,26 @@ static void insert_file_table(struct hash_table *table, int src_dst, int index,
  */
 static int find_exact_renames(struct diff_options *options)
 {
-	int i;
+	int i, renames = 0;
 	struct hash_table file_table;
 
+	/* Add all sources to the hash table */
 	init_hash(&file_table);
-	preallocate_hash(&file_table, rename_src_nr + rename_dst_nr);
+	preallocate_hash(&file_table, rename_src_nr);
 	for (i = 0; i < rename_src_nr; i++)
-		insert_file_table(&file_table, -1, i, rename_src[i].p->one);
+		insert_file_table(&file_table, i, rename_src[i].p->one);
 
+	/* Walk the destinations and find best source match */
 	for (i = 0; i < rename_dst_nr; i++)
-		insert_file_table(&file_table, 1, i, rename_dst[i].two);
+		renames += find_identical_files(&file_table, i, options);
 
-	/* Find the renames */
-	i = for_each_hash(&file_table, find_same_files, options);
+	/* Free source file_similarity chains */
+	for_each_hash(&file_table, free_similarity_list, options);
 
 	/* .. and free the hash data structure */
 	free_hash(&file_table);
 
-	return i;
+	return renames;
 }
 
 #define NUM_CANDIDATE_PER_DST 4

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #10 lore raw

PATCH v5 6/14 diffcore-rename.c: use new hash map implementation

---
 diffcore-rename.c | 48 +++++++++++++-----------------------------------
 1 file changed, 13 insertions(+), 35 deletions(-)

diffcore-rename.c +13 ~~-35~~

index cfeb408..9b4f068 100644
@@ -4,7 +4,7 @@
 #include "cache.h"
 #include "diff.h"
 #include "diffcore.h"
-#include "hash.h"
+#include "hashmap.h"
 #include "progress.h"
 
 /* Table of rename/copy destinations */

@@ -243,9 +243,9 @@ static int score_compare(const void *a_, const void *b_)
 }
 
 struct file_similarity {
+	struct hashmap_entry entry;
 	int index;
 	struct diff_filespec *filespec;
-	struct file_similarity *next;
 };
 
 static unsigned int hash_filespec(struct diff_filespec *filespec)

@@ -260,21 +260,22 @@ static unsigned int hash_filespec(struct diff_filespec *filespec)
 	return hash;
 }
 
-static int find_identical_files(struct hash_table *srcs,
+static int find_identical_files(struct hashmap *srcs,
 				int dst_index,
 				struct diff_options *options)
 {
 	int renames = 0;
 
 	struct diff_filespec *target = rename_dst[dst_index].two;
-	struct file_similarity *p, *best;
+	struct file_similarity *p, *best, dst;
 	int i = 100, best_score = -1;
 
 	/*
 	 * Find the best source match for specified destination.
 	 */
 	best = NULL;
-	for (p = lookup_hash(hash_filespec(target), srcs); p; p = p->next) {
+	hashmap_entry_init(&dst, hash_filespec(target));
+	for (p = hashmap_get(srcs, &dst, NULL); p; p = hashmap_get_next(srcs, p)) {
 		int score;
 		struct diff_filespec *source = p->filespec;

@@ -309,34 +310,15 @@ static int find_identical_files(struct hash_table *srcs,
 	return renames;
 }
 
-static int free_similarity_list(void *p, void *unused)
+static void insert_file_table(struct hashmap *table, int index, struct diff_filespec *filespec)
 {
-	while (p) {
-		struct file_similarity *entry = p;
-		p = entry->next;
-		free(entry);
-	}
-	return 0;
-}
-
-static void insert_file_table(struct hash_table *table, int index, struct diff_filespec *filespec)
-{
-	void **pos;
-	unsigned int hash;
 	struct file_similarity *entry = xmalloc(sizeof(*entry));
 
 	entry->index = index;
 	entry->filespec = filespec;
-	entry->next = NULL;
-
-	hash = hash_filespec(filespec);
-	pos = insert_hash(hash, entry, table);
 
-	/* We already had an entry there? */
-	if (pos) {
-		entry->next = *pos;
-		*pos = entry;
-	}
+	hashmap_entry_init(entry, hash_filespec(filespec));
+	hashmap_add(table, entry);
 }
 
 /*

@@ -349,11 +331,10 @@ static void insert_file_table(struct hash_table *table, int index, struct diff_f
 static int find_exact_renames(struct diff_options *options)
 {
 	int i, renames = 0;
-	struct hash_table file_table;
+	struct hashmap file_table;
 
 	/* Add all sources to the hash table */
-	init_hash(&file_table);
-	preallocate_hash(&file_table, rename_src_nr);
+	hashmap_init(&file_table, NULL, rename_src_nr);
 	for (i = 0; i < rename_src_nr; i++)
 		insert_file_table(&file_table, i, rename_src[i].p->one);

@@ -361,11 +342,8 @@ static int find_exact_renames(struct diff_options *options)
 	for (i = 0; i < rename_dst_nr; i++)
 		renames += find_identical_files(&file_table, i, options);
 
-	/* Free source file_similarity chains */
-	for_each_hash(&file_table, free_similarity_list, options);
-
-	/* .. and free the hash data structure */
-	free_hash(&file_table);
+	/* Free the hash data structure and entries */
+	hashmap_free(&file_table, 1);
 
 	return renames;
 }

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #11 lore raw

PATCH v5 7/14 name-hash.c: use new hash map implementation for directories

---
 cache.h     |  3 ++-
 name-hash.c | 77 +++++++++++++++----------------------------------------------
 2 files changed, 20 insertions(+), 60 deletions(-)

cache.h +2 -1

index d1f3c71..84e9ad6 100644
@@ -4,6 +4,7 @@
 #include "git-compat-util.h"
 #include "strbuf.h"
 #include "hash.h"
+#include "hashmap.h"
 #include "advice.h"
 #include "gettext.h"
 #include "convert.h"

@@ -278,7 +279,7 @@ struct index_state {
 	unsigned name_hash_initialized : 1,
 		 initialized : 1;
 	struct hash_table name_hash;
-	struct hash_table dir_hash;
+	struct hashmap dir_hash;
 };
 
 extern struct index_state the_index;

name-hash.c +18 ~~-59~~

131 lines not on this page · raw message

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #12 lore raw

PATCH v5 8/14 name-hash.c: remove unreferenced directory entries

The new hashmap implementation supports remove, so remove and free directory entries that are no longer referenced by active cache entries.

---
 name-hash.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

name-hash.c +8 -7

index c75fadf..effe96d 100644
@@ -86,15 +86,16 @@ static void add_dir_entry(struct index_state *istate, struct cache_entry *ce)
 static void remove_dir_entry(struct index_state *istate, struct cache_entry *ce)
 {
 	/*
-	 * Release reference to the directory entry (and parents if 0).
-	 *
-	 * Note: we do not remove / free the entry because there's no
-	 * hash.[ch]::remove_hash and dir->next may point to other entries
-	 * that are still valid, so we must not free the memory.
+	 * Release reference to the directory entry. If 0, remove and continue
+	 * with parent directory.
 	 */
 	struct dir_entry *dir = hash_dir_entry(istate, ce, ce_namelen(ce));
-	while (dir && dir->nr && !(--dir->nr))
-		dir = dir->parent;
+	while (dir && !(--dir->nr)) {
+		struct dir_entry *parent = dir->parent;
+		hashmap_remove(&istate->dir_hash, dir, NULL);
+		free(dir);
+		dir = parent;
+	}
 }
 
 static void hash_index_entry(struct index_state *istate, struct cache_entry *ce)

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #13 lore raw

PATCH v5 9/14 name-hash.c: use new hash map implementation for cache entries

Note: the "ce->next = NULL;" in unpack-trees.c::do_add_entry can safely be removed, as ce->next (now ce->ent.next) is always properly initialized in name-hash.c::hash_index_entry.

---
 cache.h        |  8 +++++---
 name-hash.c    | 24 ++++++++----------------
 unpack-trees.c |  1 -
 3 files changed, 13 insertions(+), 20 deletions(-)

cache.h +5 -3

index 84e9ad6..cedc7ae 100644
@@ -131,12 +131,12 @@ struct stat_data {
 };
 
 struct cache_entry {
+	struct hashmap_entry ent;
 	struct stat_data ce_stat_data;
 	unsigned int ce_mode;
 	unsigned int ce_flags;
 	unsigned int ce_namelen;
 	unsigned char sha1[20];
-	struct cache_entry *next;
 	char name[FLEX_ARRAY]; /* more */
 };

@@ -203,7 +203,9 @@ static inline void copy_cache_entry(struct cache_entry *dst,
 	unsigned int state = dst->ce_flags & CE_STATE_MASK;
 
 	/* Don't copy hash chain and name */
-	memcpy(dst, src, offsetof(struct cache_entry, next));
+	memcpy(&dst->ce_stat_data, &src->ce_stat_data,
+			offsetof(struct cache_entry, name) -
+			offsetof(struct cache_entry, ce_stat_data));
 
 	/* Restore the hash state */
 	dst->ce_flags = (dst->ce_flags & ~CE_STATE_MASK) | state;

@@ -278,7 +280,7 @@ struct index_state {
 	struct cache_time timestamp;
 	unsigned name_hash_initialized : 1,
 		 initialized : 1;
-	struct hash_table name_hash;
+	struct hashmap name_hash;
 	struct hashmap dir_hash;
 };

name-hash.c +8 ~~-16~~

index effe96d..488eccf 100644
@@ -100,19 +100,11 @@ static void remove_dir_entry(struct index_state *istate, struct cache_entry *ce)
 
 static void hash_index_entry(struct index_state *istate, struct cache_entry *ce)
 {
-	void **pos;
-	unsigned int hash;
-
 	if (ce->ce_flags & CE_HASHED)
 		return;
 	ce->ce_flags |= CE_HASHED;
-	ce->next = NULL;
-	hash = memihash(ce->name, ce_namelen(ce));
-	pos = insert_hash(hash, ce, &istate->name_hash);
-	if (pos) {
-		ce->next = *pos;
-		*pos = ce;
-	}
+	hashmap_entry_init(ce, memihash(ce->name, ce_namelen(ce)));
+	hashmap_add(&istate->name_hash, ce);
 
 	if (ignore_case && !(ce->ce_flags & CE_UNHASHED))
 		add_dir_entry(istate, ce);

@@ -124,8 +116,7 @@ static void lazy_init_name_hash(struct index_state *istate)
 
 	if (istate->name_hash_initialized)
 		return;
-	if (istate->cache_nr)
-		preallocate_hash(&istate->name_hash, istate->cache_nr);
+	hashmap_init(&istate->name_hash, NULL, istate->cache_nr);
 	hashmap_init(&istate->dir_hash, (hashmap_cmp_fn) dir_entry_cmp, 0);
 	for (nr = 0; nr < istate->cache_nr; nr++)
 		hash_index_entry(istate, istate->cache[nr]);

@@ -221,18 +212,19 @@ struct cache_entry *index_dir_exists(struct index_state *istate, const char *nam
 
 struct cache_entry *index_file_exists(struct index_state *istate, const char *name, int namelen, int icase)
 {
-	unsigned int hash = memihash(name, namelen);
 	struct cache_entry *ce;
+	struct hashmap_entry key;
 
 	lazy_init_name_hash(istate);
-	ce = lookup_hash(hash, &istate->name_hash);
 
+	hashmap_entry_init(&key, memihash(name, namelen));
+	ce = hashmap_get(&istate->name_hash, &key, NULL);
 	while (ce) {
 		if (!(ce->ce_flags & CE_UNHASHED)) {
 			if (same_name(ce, name, namelen, icase))
 				return ce;
 		}
-		ce = ce->next;
+		ce = hashmap_get_next(&istate->name_hash, ce);
 	}
 	return NULL;
 }

@@ -250,6 +242,6 @@ void free_name_hash(struct index_state *istate)
 		return;
 	istate->name_hash_initialized = 0;
 
-	free_hash(&istate->name_hash);
+	hashmap_free(&istate->name_hash, 0);
 	hashmap_free(&istate->dir_hash, 1);
 }

unpack-trees.c +0 -1

index ad3e9a0..f8985d4 100644
@@ -110,7 +110,6 @@ static void do_add_entry(struct unpack_trees_options *o, struct cache_entry *ce,
 	if (set & CE_REMOVE)
 		set |= CE_WT_REMOVE;
 
-	ce->next = NULL;
 	ce->ce_flags = (ce->ce_flags & ~clear) | set;
 	add_index_entry(&o->result, ce,
 			ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE);

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #14 lore raw

PATCH v5 10/14 name-hash.c: remove cache entries instead of marking them CE_UNHASHED

The new hashmap implementation supports remove, so really remove unused cache entries from the name hashmap instead of just marking them.

The CE_UNHASHED flag and CE_STATE_MASK are no longer needed.

Keep the CE_HASHED flag to prevent adding entries twice.

---
 cache.h        |  6 ++----
 name-hash.c    | 46 ++++++++++++++++++++++------------------------
 read-cache.c   |  2 +-
 unpack-trees.c |  2 +-
 4 files changed, 26 insertions(+), 30 deletions(-)

cache.h +2 -4

index cedc7ae..05b8011 100644
@@ -160,7 +160,6 @@ struct cache_entry {
 #define CE_ADDED             (1 << 19)
 
 #define CE_HASHED            (1 << 20)
-#define CE_UNHASHED          (1 << 21)
 #define CE_WT_REMOVE         (1 << 22) /* remove in work directory */
 #define CE_CONFLICTED        (1 << 23)

@@ -196,11 +195,10 @@ struct pathspec;
  * Copy the sha1 and stat state of a cache entry from one to
  * another. But we never change the name, or the hash state!
  */
-#define CE_STATE_MASK (CE_HASHED | CE_UNHASHED)
 static inline void copy_cache_entry(struct cache_entry *dst,
 				    const struct cache_entry *src)
 {
-	unsigned int state = dst->ce_flags & CE_STATE_MASK;
+	unsigned int state = dst->ce_flags & CE_HASHED;
 
 	/* Don't copy hash chain and name */
 	memcpy(&dst->ce_stat_data, &src->ce_stat_data,

@@ -208,7 +206,7 @@ static inline void copy_cache_entry(struct cache_entry *dst,
 			offsetof(struct cache_entry, ce_stat_data));
 
 	/* Restore the hash state */
-	dst->ce_flags = (dst->ce_flags & ~CE_STATE_MASK) | state;
+	dst->ce_flags = (dst->ce_flags & ~CE_HASHED) | state;
 }
 
 static inline unsigned create_ce_flags(unsigned stage)

name-hash.c +22 ~~-24~~

80 lines not on this page · raw message

read-cache.c +1 -1

index 33dd676..00af9ad 100644
@@ -58,7 +58,7 @@ void rename_index_entry_at(struct index_state *istate, int nr, const char *new_n
 
 	new = xmalloc(cache_entry_size(namelen));
 	copy_cache_entry(new, old);
-	new->ce_flags &= ~CE_STATE_MASK;
+	new->ce_flags &= ~CE_HASHED;
 	new->ce_namelen = namelen;
 	memcpy(new->name, new_name, namelen + 1);

unpack-trees.c +1 -1

index f8985d4..82b652f 100644
@@ -105,7 +105,7 @@ void setup_unpack_trees_porcelain(struct unpack_trees_options *opts,
 static void do_add_entry(struct unpack_trees_options *o, struct cache_entry *ce,
 			 unsigned int set, unsigned int clear)
 {
-	clear |= CE_HASHED | CE_UNHASHED;
+	clear |= CE_HASHED;
 
 	if (set & CE_REMOVE)
 		set |= CE_WT_REMOVE;

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #15 lore raw

PATCH v5 11/14 remove old hash.[ch] implementation

---
 Documentation/technical/api-hash.txt |  52 -----------------
 Makefile                             |   2 -
 cache.h                              |   1 -
 hash.c                               | 110 -----------------------------------
 hash.h                               |  50 ----------------
 test-hashmap.c                       |  84 --------------------------
 6 files changed, 299 deletions(-)
 delete mode 100644 Documentation/technical/api-hash.txt
 delete mode 100644 hash.c
 delete mode 100644 hash.h

Documentation/technical/api-hash.txt deleted +0 ~~-52~~

deleted file mode 100644
index e5061e0..0000000
@@ -1,52 +0,0 @@
-hash API
-========
-
-The hash API is a collection of simple hash table functions. Users are expected
-to implement their own hashing.
-
-Data Structures
----------------
-
-`struct hash_table`::
-
-	The hash table structure. The `array` member points to the hash table
-	entries. The `size` member counts the total number of valid and invalid
-	entries in the table. The `nr` member keeps track of the number of
-	valid entries.
-
-`struct hash_table_entry`::
-
-	An opaque structure representing an entry in the hash table. The `hash`
-	member is the entry's hash key and the `ptr` member is the entry's
-	value.
-
-Functions
----------
-
-`init_hash`::
-
-	Initialize the hash table.
-
-`free_hash`::
-
-	Release memory associated with the hash table.
-
-`insert_hash`::
-
-	Insert a pointer into the hash table. If an entry with that hash
-	already exists, a pointer to the existing entry's value is returned.
-	Otherwise NULL is returned.  This allows callers to implement
-	chaining, etc.
-
-`lookup_hash`::
-
-	Lookup an entry in the hash table. If an entry with that hash exists
-	the entry's value is returned. Otherwise NULL is returned.
-
-`for_each_hash`::
-
-	Call a function for each entry in the hash table. The function is
-	expected to take the entry's value as its only argument and return an
-	int. If the function returns a negative int the loop is aborted
-	immediately.  Otherwise, the return value is accumulated and the sum
-	returned upon completion of the loop.

Makefile +0 -2

index 75bb1a6..d566768 100644
@@ -673,7 +673,6 @@ LIB_H += git-compat-util.h
 LIB_H += gpg-interface.h
 LIB_H += graph.h
 LIB_H += grep.h
-LIB_H += hash.h
 LIB_H += hashmap.h
 LIB_H += help.h
 LIB_H += http.h

@@ -805,7 +804,6 @@ LIB_OBJS += gettext.o
 LIB_OBJS += gpg-interface.o
 LIB_OBJS += graph.o
 LIB_OBJS += grep.o
-LIB_OBJS += hash.o
 LIB_OBJS += hashmap.o
 LIB_OBJS += help.o
 LIB_OBJS += hex.o

cache.h +0 -1

index 05b8011..27067b8 100644
@@ -3,7 +3,6 @@
 
 #include "git-compat-util.h"
 #include "strbuf.h"
-#include "hash.h"
 #include "hashmap.h"
 #include "advice.h"
 #include "gettext.h"

hash.c deleted +0 ~~-110~~

110 lines not on this page · raw message

hash.h deleted +0 ~~-50~~

50 lines not on this page · raw message

test-hashmap.c +0 ~~-84~~

102 lines not on this page · raw message

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #16 lore raw

PATCH v5 12/14 fix 'git update-index --verbose --again' output

'git update-index --verbose' consistently reports paths relative to the work-tree root. The only exception is the '--again' option, which reports paths relative to the current working directory.

Change do_reupdate to use non-prefixed paths.

---
 builtin/update-index.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

builtin/update-index.c +1 -1

index e3a10d7..d180d80 100644
@@ -579,7 +579,7 @@ static int do_reupdate(int ac, const char **av,
 		 * or worse yet 'allow_replace', active_nr may decrease.
 		 */
 		save_nr = active_nr;
-		update_one(ce->name + prefix_length, prefix, prefix_length);
+		update_one(ce->name, NULL, 0);
 		if (save_nr != active_nr)
 			goto redo;
 	}

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #17 lore raw

PATCH v5 13/14 builtin/update-index.c: cleanup update_one

do_reupdate calls update_one with a cache_entry.name, there's no need for the extra sanitation / normalization that happens in prefix_path. cmd_update_index calls update_one with an already prefixed path, no need to prefix_path twice.

Remove the extra prefix_path from update_one. Also remove the now unused 'prefix' and 'prefix_length' parameters.

As of d089eba "setup: sanitize absolute and funny paths in get_pathspec()", prefix_path uncoditionally returns a copy, even if the passed in path isn't changed. Lets unconditionally free() the result.

---
 builtin/update-index.c | 36 +++++++++++++++---------------------
 1 file changed, 15 insertions(+), 21 deletions(-)

builtin/update-index.c +15 ~~-21~~

index d180d80..c8f0d5f 100644
@@ -274,36 +274,32 @@ static void chmod_path(int flip, const char *path)
 	die("git update-index: cannot chmod %cx '%s'", flip, path);
 }
 
-static void update_one(const char *path, const char *prefix, int prefix_length)
+static void update_one(const char *path)
 {
-	const char *p = prefix_path(prefix, prefix_length, path);
-	if (!verify_path(p)) {
+	if (!verify_path(path)) {
 		fprintf(stderr, "Ignoring path %s\n", path);
-		goto free_return;
+		return;
 	}
 	if (mark_valid_only) {
-		if (mark_ce_flags(p, CE_VALID, mark_valid_only == MARK_FLAG))
+		if (mark_ce_flags(path, CE_VALID, mark_valid_only == MARK_FLAG))
 			die("Unable to mark file %s", path);
-		goto free_return;
+		return;
 	}
 	if (mark_skip_worktree_only) {
-		if (mark_ce_flags(p, CE_SKIP_WORKTREE, mark_skip_worktree_only == MARK_FLAG))
+		if (mark_ce_flags(path, CE_SKIP_WORKTREE, mark_skip_worktree_only == MARK_FLAG))
 			die("Unable to mark file %s", path);
-		goto free_return;
+		return;
 	}
 
 	if (force_remove) {
-		if (remove_file_from_cache(p))
+		if (remove_file_from_cache(path))
 			die("git update-index: unable to remove %s", path);
 		report("remove '%s'", path);
-		goto free_return;
+		return;
 	}
-	if (process_path(p))
+	if (process_path(path))
 		die("Unable to process path %s", path);
 	report("add '%s'", path);
- free_return:
-	if (p < path || p > path + strlen(path))
-		free((char *)p);
 }
 
 static void read_index_info(int line_termination)

@@ -579,7 +575,7 @@ static int do_reupdate(int ac, const char **av,
 		 * or worse yet 'allow_replace', active_nr may decrease.
 		 */
 		save_nr = active_nr;
-		update_one(ce->name, NULL, 0);
+		update_one(ce->name);
 		if (save_nr != active_nr)
 			goto redo;
 	}

@@ -836,11 +832,10 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 
 			setup_work_tree();
 			p = prefix_path(prefix, prefix_length, path);
-			update_one(p, NULL, 0);
+			update_one(p);
 			if (set_executable_bit)
 				chmod_path(set_executable_bit, p);
-			if (p < path || p > path + strlen(path))
-				free((char *)p);
+			free((char *)p);
 			ctx.argc--;
 			ctx.argv++;
 			break;

@@ -879,11 +874,10 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 				strbuf_swap(&buf, &nbuf);
 			}
 			p = prefix_path(prefix, prefix_length, buf.buf);
-			update_one(p, NULL, 0);
+			update_one(p);
 			if (set_executable_bit)
 				chmod_path(set_executable_bit, p);
-			if (p < buf.buf || p > buf.buf + buf.len)
-				free((char *)p);
+			free((char *)p);
 		}
 		strbuf_release(&nbuf);
 		strbuf_release(&buf);

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #18 lore raw

PATCH v5 14/14 read-cache.c: fix memory leaks caused by removed cache entries

When cache_entry structs are removed from index_state.cache, they are not properly freed. Freeing those entries wasn't possible before because we couldn't remove them from index_state.name_hash.

Now that we _do_ remove the entries from name_hash, we can also free them. Add 'free(cache_entry)' to all call sites of name-hash.c::remove_name_hash in read-cache.c (we could free() directly in remove_name_hash(), but name-hash.c isn't concerned with cache_entry allocation at all).

Accessing a cache_entry after removing it from the index is now no longer allowed, as the memory has been freed. The following functions need minor fixes (typically by copying ce->name before use):
- builtin/rm.c::cmd_rm
- builtin/update-index.c::do_reupdate
- read-cache.c::read_index_unmerged
- resolve-undo.c::unmerge_index_entry_at

---
 builtin/rm.c           | 2 +-
 builtin/update-index.c | 5 ++++-
 read-cache.c           | 8 ++++++--
 resolve-undo.c         | 7 +++++--
 4 files changed, 16 insertions(+), 6 deletions(-)

builtin/rm.c +1 -1

index 3a0e0ea..171f37c 100644
@@ -311,7 +311,7 @@ int cmd_rm(int argc, const char **argv, const char *prefix)
 		if (!match_pathspec_depth(&pathspec, ce->name, ce_namelen(ce), 0, seen))
 			continue;
 		ALLOC_GROW(list.entry, list.nr + 1, list.alloc);
-		list.entry[list.nr].name = ce->name;
+		list.entry[list.nr].name = xstrdup(ce->name);
 		list.entry[list.nr].is_submodule = S_ISGITLINK(ce->ce_mode);
 		if (list.entry[list.nr++].is_submodule &&
 		    !is_staging_gitmodules_ok())

builtin/update-index.c +4 -1

index c8f0d5f..00313f3 100644
@@ -559,6 +559,7 @@ static int do_reupdate(int ac, const char **av,
 		const struct cache_entry *ce = active_cache[pos];
 		struct cache_entry *old = NULL;
 		int save_nr;
+		char *path;
 
 		if (ce_stage(ce) || !ce_path_match(ce, &pathspec))
 			continue;

@@ -575,7 +576,9 @@ static int do_reupdate(int ac, const char **av,
 		 * or worse yet 'allow_replace', active_nr may decrease.
 		 */
 		save_nr = active_nr;
-		update_one(ce->name);
+		path = xstrdup(ce->name);
+		update_one(path);
+		free(path);
 		if (save_nr != active_nr)
 			goto redo;
 	}

read-cache.c +6 -2

index 00af9ad..3f735f3 100644
@@ -47,6 +47,7 @@ static void replace_index_entry(struct index_state *istate, int nr, struct cache
 	struct cache_entry *old = istate->cache[nr];
 
 	remove_name_hash(istate, old);
+	free(old);
 	set_index_entry(istate, nr, ce);
 	istate->cache_changed = 1;
 }

@@ -478,6 +479,7 @@ int remove_index_entry_at(struct index_state *istate, int pos)
 
 	record_resolve_undo(istate, ce);
 	remove_name_hash(istate, ce);
+	free(ce);
 	istate->cache_changed = 1;
 	istate->cache_nr--;
 	if (pos >= istate->cache_nr)

@@ -499,8 +501,10 @@ void remove_marked_cache_entries(struct index_state *istate)
 	unsigned int i, j;
 
 	for (i = j = 0; i < istate->cache_nr; i++) {
-		if (ce_array[i]->ce_flags & CE_REMOVE)
+		if (ce_array[i]->ce_flags & CE_REMOVE) {
 			remove_name_hash(istate, ce_array[i]);
+			free(ce_array[i]);
+		}
 		else
 			ce_array[j++] = ce_array[i];
 	}

@@ -1894,7 +1898,7 @@ int read_index_unmerged(struct index_state *istate)
 		new_ce->ce_mode = ce->ce_mode;
 		if (add_index_entry(istate, new_ce, 0))
 			return error("%s: cannot drop to stage #0",
-				     ce->name);
+				     new_ce->name);
 		i = index_name_pos(istate, new_ce->name, len);
 	}
 	return unmerged;

resolve-undo.c +5 -2

index c09b006..49ebaaf 100644
@@ -119,6 +119,7 @@ int unmerge_index_entry_at(struct index_state *istate, int pos)
 	struct string_list_item *item;
 	struct resolve_undo_info *ru;
 	int i, err = 0, matched;
+	char *name;
 
 	if (!istate->resolve_undo)
 		return pos;

@@ -138,20 +139,22 @@ int unmerge_index_entry_at(struct index_state *istate, int pos)
 	if (!ru)
 		return pos;
 	matched = ce->ce_flags & CE_MATCHED;
+	name = xstrdup(ce->name);
 	remove_index_entry_at(istate, pos);
 	for (i = 0; i < 3; i++) {
 		struct cache_entry *nce;
 		if (!ru->mode[i])
 			continue;
 		nce = make_cache_entry(ru->mode[i], ru->sha1[i],
-				       ce->name, i + 1, 0);
+				       name, i + 1, 0);
 		if (matched)
 			nce->ce_flags |= CE_MATCHED;
 		if (add_index_entry(istate, nce, ADD_CACHE_OK_TO_ADD)) {
 			err = 1;
-			error("cannot unmerge '%s'", ce->name);
+			error("cannot unmerge '%s'", name);
 		}
 	}
+	free(name);
 	if (err)
 		return pos;
 	free(ru);

Signature · 1 line

1.8.5.rc0.333.g5394214

Karsten Blees

author

2016-06-15 22:59 UTC #19 lore raw