archive_write_disk_set_standard_lookup.c revision 344673 
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/11/contrib/libarchive/libarchive/archive_write_disk_set_standard_lookup.c 344673 2019-02-28 22:56:15Z 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	free(b->name);
118	b->name = strdup(gname);
119	/* Note: If strdup fails, that's okay; we just won't cache. */
120	b->hash = h;
121#if HAVE_GRP_H
122#  if HAVE_GETGRNAM_R
123	{
124		char _buffer[128];
125		size_t bufsize = 128;
126		char *buffer = _buffer;
127		char *allocated = NULL;
128		struct group	grent, *result;
129		int r;
130
131		for (;;) {
132			result = &grent; /* Old getgrnam_r ignores last arg. */
133			r = getgrnam_r(gname, &grent, buffer, bufsize, &result);
134			if (r == 0)
135				break;
136			if (r != ERANGE)
137				break;
138			bufsize *= 2;
139			free(allocated);
140			allocated = malloc(bufsize);
141			if (allocated == NULL)
142				break;
143			buffer = allocated;
144		}
145		if (result != NULL)
146			gid = result->gr_gid;
147		free(allocated);
148	}
149#  else /* HAVE_GETGRNAM_R */
150	{
151		struct group *result;
152
153		result = getgrnam(gname);
154		if (result != NULL)
155			gid = result->gr_gid;
156	}
157#  endif /* HAVE_GETGRNAM_R */
158#elif defined(_WIN32) && !defined(__CYGWIN__)
159	/* TODO: do a gname->gid lookup for Windows. */
160#else
161	#error No way to perform gid lookups on this platform
162#endif
163	b->id = (gid_t)gid;
164
165	return (gid);
166}
167
168static int64_t
169lookup_uid(void *private_data, const char *uname, int64_t uid)
170{
171	int h;
172	struct bucket *b;
173	struct bucket *ucache = (struct bucket *)private_data;
174
175	/* If no uname, just use the uid provided. */
176	if (uname == NULL || *uname == '\0')
177		return (uid);
178
179	/* Try to find uname in the cache. */
180	h = hash(uname);
181	b = &ucache[h % cache_size ];
182	if (b->name != NULL && b->hash == h && strcmp(uname, b->name) == 0)
183		return ((uid_t)b->id);
184
185	/* Free the cache slot for a new entry. */
186	free(b->name);
187	b->name = strdup(uname);
188	/* Note: If strdup fails, that's okay; we just won't cache. */
189	b->hash = h;
190#if HAVE_PWD_H
191#  if HAVE_GETPWNAM_R
192	{
193		char _buffer[128];
194		size_t bufsize = 128;
195		char *buffer = _buffer;
196		char *allocated = NULL;
197		struct passwd	pwent, *result;
198		int r;
199
200		for (;;) {
201			result = &pwent; /* Old getpwnam_r ignores last arg. */
202			r = getpwnam_r(uname, &pwent, buffer, bufsize, &result);
203			if (r == 0)
204				break;
205			if (r != ERANGE)
206				break;
207			bufsize *= 2;
208			free(allocated);
209			allocated = malloc(bufsize);
210			if (allocated == NULL)
211				break;
212			buffer = allocated;
213		}
214		if (result != NULL)
215			uid = result->pw_uid;
216		free(allocated);
217	}
218#  else /* HAVE_GETPWNAM_R */
219	{
220		struct passwd *result;
221
222		result = getpwnam(uname);
223		if (result != NULL)
224			uid = result->pw_uid;
225	}
226#endif	/* HAVE_GETPWNAM_R */
227#elif defined(_WIN32) && !defined(__CYGWIN__)
228	/* TODO: do a uname->uid lookup for Windows. */
229#else
230	#error No way to look up uids on this platform
231#endif
232	b->id = (uid_t)uid;
233
234	return (uid);
235}
236
237static void
238cleanup(void *private)
239{
240	size_t i;
241	struct bucket *cache = (struct bucket *)private;
242
243	for (i = 0; i < cache_size; i++)
244		free(cache[i].name);
245	free(cache);
246}
247
248
249static unsigned int
250hash(const char *p)
251{
252	/* A 32-bit version of Peter Weinberger's (PJW) hash algorithm,
253	   as used by ELF for hashing function names. */
254	unsigned g, h = 0;
255	while (*p != '\0') {
256		h = (h << 4) + *p++;
257		if ((g = h & 0xF0000000) != 0) {
258			h ^= g >> 24;
259			h &= 0x0FFFFFFF;
260		}
261	}
262	return h;
263}
264