1 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
2 /* Copyright (c) 2021 Facebook */
3 #include <stdint.h>
4 #include <stdlib.h>
5 #include <stdio.h>
6 #include <errno.h>
7 #include <linux/err.h>
8 #include "hashmap.h"
9 #include "libbpf_internal.h"
10 #include "strset.h"
11
12 struct strset {
13 void *strs_data;
14 size_t strs_data_len;
15 size_t strs_data_cap;
16 size_t strs_data_max_len;
17
18 /* lookup index for each unique string in strings set */
19 struct hashmap *strs_hash;
20 };
21
strset_hash_fn(const void * key,void * ctx)22 static size_t strset_hash_fn(const void *key, void *ctx)
23 {
24 const struct strset *s = ctx;
25 const char *str = s->strs_data + (long)key;
26
27 return str_hash(str);
28 }
29
strset_equal_fn(const void * key1,const void * key2,void * ctx)30 static bool strset_equal_fn(const void *key1, const void *key2, void *ctx)
31 {
32 const struct strset *s = ctx;
33 const char *str1 = s->strs_data + (long)key1;
34 const char *str2 = s->strs_data + (long)key2;
35
36 return strcmp(str1, str2) == 0;
37 }
38
strset__new(size_t max_data_sz,const char * init_data,size_t init_data_sz)39 struct strset *strset__new(size_t max_data_sz, const char *init_data, size_t init_data_sz)
40 {
41 struct strset *set = calloc(1, sizeof(*set));
42 struct hashmap *hash;
43 int err = -ENOMEM;
44
45 if (!set)
46 return ERR_PTR(-ENOMEM);
47
48 hash = hashmap__new(strset_hash_fn, strset_equal_fn, set);
49 if (IS_ERR(hash))
50 goto err_out;
51
52 set->strs_data_max_len = max_data_sz;
53 set->strs_hash = hash;
54
55 if (init_data) {
56 long off;
57
58 set->strs_data = malloc(init_data_sz);
59 if (!set->strs_data)
60 goto err_out;
61
62 memcpy(set->strs_data, init_data, init_data_sz);
63 set->strs_data_len = init_data_sz;
64 set->strs_data_cap = init_data_sz;
65
66 for (off = 0; off < set->strs_data_len; off += strlen(set->strs_data + off) + 1) {
67 /* hashmap__add() returns EEXIST if string with the same
68 * content already is in the hash map
69 */
70 err = hashmap__add(hash, (void *)off, (void *)off);
71 if (err == -EEXIST)
72 continue; /* duplicate */
73 if (err)
74 goto err_out;
75 }
76 }
77
78 return set;
79 err_out:
80 strset__free(set);
81 return ERR_PTR(err);
82 }
83
strset__free(struct strset * set)84 void strset__free(struct strset *set)
85 {
86 if (IS_ERR_OR_NULL(set))
87 return;
88
89 hashmap__free(set->strs_hash);
90 free(set->strs_data);
91 free(set);
92 }
93
strset__data_size(const struct strset * set)94 size_t strset__data_size(const struct strset *set)
95 {
96 return set->strs_data_len;
97 }
98
strset__data(const struct strset * set)99 const char *strset__data(const struct strset *set)
100 {
101 return set->strs_data;
102 }
103
strset_add_str_mem(struct strset * set,size_t add_sz)104 static void *strset_add_str_mem(struct strset *set, size_t add_sz)
105 {
106 return libbpf_add_mem(&set->strs_data, &set->strs_data_cap, 1,
107 set->strs_data_len, set->strs_data_max_len, add_sz);
108 }
109
110 /* Find string offset that corresponds to a given string *s*.
111 * Returns:
112 * - >0 offset into string data, if string is found;
113 * - -ENOENT, if string is not in the string data;
114 * - <0, on any other error.
115 */
strset__find_str(struct strset * set,const char * s)116 int strset__find_str(struct strset *set, const char *s)
117 {
118 long old_off, new_off, len;
119 void *p;
120
121 /* see strset__add_str() for why we do this */
122 len = strlen(s) + 1;
123 p = strset_add_str_mem(set, len);
124 if (!p)
125 return -ENOMEM;
126
127 new_off = set->strs_data_len;
128 memcpy(p, s, len);
129
130 if (hashmap__find(set->strs_hash, (void *)new_off, (void **)&old_off))
131 return old_off;
132
133 return -ENOENT;
134 }
135
136 /* Add a string s to the string data. If the string already exists, return its
137 * offset within string data.
138 * Returns:
139 * - > 0 offset into string data, on success;
140 * - < 0, on error.
141 */
strset__add_str(struct strset * set,const char * s)142 int strset__add_str(struct strset *set, const char *s)
143 {
144 long old_off, new_off, len;
145 void *p;
146 int err;
147
148 /* Hashmap keys are always offsets within set->strs_data, so to even
149 * look up some string from the "outside", we need to first append it
150 * at the end, so that it can be addressed with an offset. Luckily,
151 * until set->strs_data_len is incremented, that string is just a piece
152 * of garbage for the rest of the code, so no harm, no foul. On the
153 * other hand, if the string is unique, it's already appended and
154 * ready to be used, only a simple set->strs_data_len increment away.
155 */
156 len = strlen(s) + 1;
157 p = strset_add_str_mem(set, len);
158 if (!p)
159 return -ENOMEM;
160
161 new_off = set->strs_data_len;
162 memcpy(p, s, len);
163
164 /* Now attempt to add the string, but only if the string with the same
165 * contents doesn't exist already (HASHMAP_ADD strategy). If such
166 * string exists, we'll get its offset in old_off (that's old_key).
167 */
168 err = hashmap__insert(set->strs_hash, (void *)new_off, (void *)new_off,
169 HASHMAP_ADD, (const void **)&old_off, NULL);
170 if (err == -EEXIST)
171 return old_off; /* duplicated string, return existing offset */
172 if (err)
173 return err;
174
175 set->strs_data_len += len; /* new unique string, adjust data length */
176 return new_off;
177 }
178