archive_write_disk_set_standard_lookup.c revision 311042 
1/*-
2 * Copyright (c) 2003-2007 Tim Kientzle
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * 1. Redistributions of source code must retain the above copyright
9 *    notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 *    notice, this list of conditions and the following disclaimer in the
12 *    documentation and/or other materials provided with the distribution.
13 *
14 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR(S) ``AS IS'' AND ANY EXPRESS OR
15 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
16 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
17 * IN NO EVENT SHALL THE AUTHOR(S) BE LIABLE FOR ANY DIRECT, INDIRECT,
18 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
19 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
20 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
21 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
22 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
23 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
24 */
25
26#include "archive_platform.h"
27__FBSDID("$FreeBSD: stable/10/contrib/libarchive/libarchive/archive_write_disk_set_standard_lookup.c 311042 2017-01-02 01:43:11Z mm $");
28
29#ifdef HAVE_SYS_TYPES_H
30#include <sys/types.h>
31#endif
32#ifdef HAVE_ERRNO_H
33#include <errno.h>
34#endif
35#ifdef HAVE_GRP_H
36#include <grp.h>
37#endif
38#ifdef HAVE_PWD_H
39#include <pwd.h>
40#endif
41#ifdef HAVE_STDLIB_H
42#include <stdlib.h>
43#endif
44#ifdef HAVE_STRING_H
45#include <string.h>
46#endif
47
48#include "archive.h"
49#include "archive_private.h"
50#include "archive_read_private.h"
51#include "archive_write_disk_private.h"
52
53struct bucket {
54	char	*name;
55	int	 hash;
56	id_t	 id;
57};
58
59static const size_t cache_size = 127;
60static unsigned int	hash(const char *);
61static int64_t	lookup_gid(void *, const char *uname, int64_t);
62static int64_t	lookup_uid(void *, const char *uname, int64_t);
63static void	cleanup(void *);
64
65/*
66 * Installs functions that use getpwnam()/getgrnam()---along with
67 * a simple cache to accelerate such lookups---into the archive_write_disk
68 * object.  This is in a separate file because getpwnam()/getgrnam()
69 * can pull in a LOT of library code (including NIS/LDAP functions, which
70 * pull in DNS resolvers, etc).  This can easily top 500kB, which makes
71 * it inappropriate for some space-constrained applications.
72 *
73 * Applications that are size-sensitive may want to just use the
74 * real default functions (defined in archive_write_disk.c) that just
75 * use the uid/gid without the lookup.  Or define your own custom functions
76 * if you prefer.
77 *
78 * TODO: Replace these hash tables with simpler move-to-front LRU
79 * lists with a bounded size (128 items?).  The hash is a bit faster,
80 * but has a bad pathology in which it thrashes a single bucket.  Even
81 * walking a list of 128 items is a lot faster than calling
82 * getpwnam()!
83 */
84int
85archive_write_disk_set_standard_lookup(struct archive *a)
86{
87	struct bucket *ucache = calloc(cache_size, sizeof(struct bucket));
88	struct bucket *gcache = calloc(cache_size, sizeof(struct bucket));
89	if (ucache == NULL || gcache == NULL) {
90		free(ucache);
91		free(gcache);
92		return (ARCHIVE_FATAL);
93	}
94	archive_write_disk_set_group_lookup(a, gcache, lookup_gid, cleanup);
95	archive_write_disk_set_user_lookup(a, ucache, lookup_uid, cleanup);
96	return (ARCHIVE_OK);
97}
98
99static int64_t
100lookup_gid(void *private_data, const char *gname, int64_t gid)
101{
102	int h;
103	struct bucket *b;
104	struct bucket *gcache = (struct bucket *)private_data;
105
106	/* If no gname, just use the gid provided. */
107	if (gname == NULL || *gname == '\0')
108		return (gid);
109
110	/* Try to find gname in the cache. */
111	h = hash(gname);
112	b = &gcache[h % cache_size ];
113	if (b->name != NULL && b->hash == h && strcmp(gname, b->name) == 0)
114		return ((gid_t)b->id);
115
116	/* Free the cache slot for a new entry. */
117	if (b->name != NULL)
118		free(b->name);
119	b->name = strdup(gname);
120	/* Note: If strdup fails, that's okay; we just won't cache. */
121	b->hash = h;
122#if HAVE_GRP_H
123#  if HAVE_GETGRNAM_R
124	{
125		char _buffer[128];
126		size_t bufsize = 128;
127		char *buffer = _buffer;
128		char *allocated = NULL;
129		struct group	grent, *result;
130		int r;
131
132		for (;;) {
133			result = &grent; /* Old getgrnam_r ignores last arg. */
134			r = getgrnam_r(gname, &grent, buffer, bufsize, &result);
135			if (r == 0)
136				break;
137			if (r != ERANGE)
138				break;
139			bufsize *= 2;
140			free(allocated);
141			allocated = malloc(bufsize);
142			if (allocated == NULL)
143				break;
144			buffer = allocated;
145		}
146		if (result != NULL)
147			gid = result->gr_gid;
148		free(allocated);
149	}
150#  else /* HAVE_GETGRNAM_R */
151	{
152		struct group *result;
153
154		result = getgrnam(gname);
155		if (result != NULL)
156			gid = result->gr_gid;
157	}
158#  endif /* HAVE_GETGRNAM_R */
159#elif defined(_WIN32) && !defined(__CYGWIN__)
160	/* TODO: do a gname->gid lookup for Windows. */
161#else
162	#error No way to perform gid lookups on this platform
163#endif
164	b->id = (gid_t)gid;
165
166	return (gid);
167}
168
169static int64_t
170lookup_uid(void *private_data, const char *uname, int64_t uid)
171{
172	int h;
173	struct bucket *b;
174	struct bucket *ucache = (struct bucket *)private_data;
175
176	/* If no uname, just use the uid provided. */
177	if (uname == NULL || *uname == '\0')
178		return (uid);
179
180	/* Try to find uname in the cache. */
181	h = hash(uname);
182	b = &ucache[h % cache_size ];
183	if (b->name != NULL && b->hash == h && strcmp(uname, b->name) == 0)
184		return ((uid_t)b->id);
185
186	/* Free the cache slot for a new entry. */
187	if (b->name != NULL)
188		free(b->name);
189	b->name = strdup(uname);
190	/* Note: If strdup fails, that's okay; we just won't cache. */
191	b->hash = h;
192#if HAVE_PWD_H
193#  if HAVE_GETPWNAM_R
194	{
195		char _buffer[128];
196		size_t bufsize = 128;
197		char *buffer = _buffer;
198		char *allocated = NULL;
199		struct passwd	pwent, *result;
200		int r;
201
202		for (;;) {
203			result = &pwent; /* Old getpwnam_r ignores last arg. */
204			r = getpwnam_r(uname, &pwent, buffer, bufsize, &result);
205			if (r == 0)
206				break;
207			if (r != ERANGE)
208				break;
209			bufsize *= 2;
210			free(allocated);
211			allocated = malloc(bufsize);
212			if (allocated == NULL)
213				break;
214			buffer = allocated;
215		}
216		if (result != NULL)
217			uid = result->pw_uid;
218		free(allocated);
219	}
220#  else /* HAVE_GETPWNAM_R */
221	{
222		struct passwd *result;
223
224		result = getpwnam(uname);
225		if (result != NULL)
226			uid = result->pw_uid;
227	}
228#endif	/* HAVE_GETPWNAM_R */
229#elif defined(_WIN32) && !defined(__CYGWIN__)
230	/* TODO: do a uname->uid lookup for Windows. */
231#else
232	#error No way to look up uids on this platform
233#endif
234	b->id = (uid_t)uid;
235
236	return (uid);
237}
238
239static void
240cleanup(void *private)
241{
242	size_t i;
243	struct bucket *cache = (struct bucket *)private;
244
245	for (i = 0; i < cache_size; i++)
246		free(cache[i].name);
247	free(cache);
248}
249
250
251static unsigned int
252hash(const char *p)
253{
254	/* A 32-bit version of Peter Weinberger's (PJW) hash algorithm,
255	   as used by ELF for hashing function names. */
256	unsigned g, h = 0;
257	while (*p != '\0') {
258		h = (h << 4) + *p++;
259		if ((g = h & 0xF0000000) != 0) {
260			h ^= g >> 24;
261			h &= 0x0FFFFFFF;
262		}
263	}
264	return h;
265}
266