^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1) // SPDX-License-Identifier: GPL-2.0-only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 3) * Minimal file system backend for holding eBPF maps and programs,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 4) * used by bpf(2) object pinning.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 5) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 6) * Authors:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 7) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 8) * Daniel Borkmann <daniel@iogearbox.net>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 9) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 10)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 11) #include <linux/init.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 12) #include <linux/magic.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 13) #include <linux/major.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 14) #include <linux/mount.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 15) #include <linux/namei.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 16) #include <linux/fs.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 17) #include <linux/fs_context.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 18) #include <linux/fs_parser.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 19) #include <linux/kdev_t.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 20) #include <linux/filter.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 21) #include <linux/bpf.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 22) #include <linux/bpf_trace.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 23) #include "preload/bpf_preload.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 24)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 25) enum bpf_type {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 26) BPF_TYPE_UNSPEC = 0,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 27) BPF_TYPE_PROG,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 28) BPF_TYPE_MAP,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 29) BPF_TYPE_LINK,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 30) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 31)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 32) static void *bpf_any_get(void *raw, enum bpf_type type)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 33) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 34) switch (type) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 35) case BPF_TYPE_PROG:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 36) bpf_prog_inc(raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 37) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 38) case BPF_TYPE_MAP:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 39) bpf_map_inc_with_uref(raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 40) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 41) case BPF_TYPE_LINK:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 42) bpf_link_inc(raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 43) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 44) default:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 45) WARN_ON_ONCE(1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 46) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 47) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 48)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 49) return raw;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 50) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 51)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 52) static void bpf_any_put(void *raw, enum bpf_type type)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 53) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 54) switch (type) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 55) case BPF_TYPE_PROG:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 56) bpf_prog_put(raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 57) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 58) case BPF_TYPE_MAP:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 59) bpf_map_put_with_uref(raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 60) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 61) case BPF_TYPE_LINK:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 62) bpf_link_put(raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 63) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 64) default:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 65) WARN_ON_ONCE(1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 66) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 67) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 68) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 69)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 70) static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 71) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 72) void *raw;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 73)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 74) raw = bpf_map_get_with_uref(ufd);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 75) if (!IS_ERR(raw)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 76) *type = BPF_TYPE_MAP;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 77) return raw;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 78) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 79)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 80) raw = bpf_prog_get(ufd);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 81) if (!IS_ERR(raw)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 82) *type = BPF_TYPE_PROG;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 83) return raw;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 84) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 85)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 86) raw = bpf_link_get_from_fd(ufd);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 87) if (!IS_ERR(raw)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 88) *type = BPF_TYPE_LINK;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 89) return raw;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 90) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 91)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 92) return ERR_PTR(-EINVAL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 93) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 94)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 95) static const struct inode_operations bpf_dir_iops;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 96)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 97) static const struct inode_operations bpf_prog_iops = { };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 98) static const struct inode_operations bpf_map_iops = { };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 99) static const struct inode_operations bpf_link_iops = { };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 101) static struct inode *bpf_get_inode(struct super_block *sb,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 102) const struct inode *dir,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 103) umode_t mode)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 104) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 105) struct inode *inode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 106)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 107) switch (mode & S_IFMT) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 108) case S_IFDIR:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 109) case S_IFREG:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 110) case S_IFLNK:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 111) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 112) default:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 113) return ERR_PTR(-EINVAL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 114) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 115)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 116) inode = new_inode(sb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 117) if (!inode)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 118) return ERR_PTR(-ENOSPC);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 119)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 120) inode->i_ino = get_next_ino();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 121) inode->i_atime = current_time(inode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 122) inode->i_mtime = inode->i_atime;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 123) inode->i_ctime = inode->i_atime;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 124)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 125) inode_init_owner(inode, dir, mode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 126)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 127) return inode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 128) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 129)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 130) static int bpf_inode_type(const struct inode *inode, enum bpf_type *type)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 131) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 132) *type = BPF_TYPE_UNSPEC;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 133) if (inode->i_op == &bpf_prog_iops)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 134) *type = BPF_TYPE_PROG;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 135) else if (inode->i_op == &bpf_map_iops)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 136) *type = BPF_TYPE_MAP;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 137) else if (inode->i_op == &bpf_link_iops)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 138) *type = BPF_TYPE_LINK;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 139) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 140) return -EACCES;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 141)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 142) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 143) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 144)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 145) static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 146) struct inode *dir)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 147) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 148) d_instantiate(dentry, inode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 149) dget(dentry);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 150)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 151) dir->i_mtime = current_time(dir);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 152) dir->i_ctime = dir->i_mtime;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 153) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 154)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 155) static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 156) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 157) struct inode *inode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 158)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 159) inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFDIR);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 160) if (IS_ERR(inode))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 161) return PTR_ERR(inode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 162)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 163) inode->i_op = &bpf_dir_iops;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 164) inode->i_fop = &simple_dir_operations;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 165)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 166) inc_nlink(inode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 167) inc_nlink(dir);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 168)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 169) bpf_dentry_finalize(dentry, inode, dir);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 170) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 171) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 172)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 173) struct map_iter {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 174) void *key;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 175) bool done;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 176) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 177)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 178) static struct map_iter *map_iter(struct seq_file *m)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 179) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 180) return m->private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 181) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 182)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 183) static struct bpf_map *seq_file_to_map(struct seq_file *m)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 184) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 185) return file_inode(m->file)->i_private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 186) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 187)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 188) static void map_iter_free(struct map_iter *iter)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 189) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 190) if (iter) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 191) kfree(iter->key);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 192) kfree(iter);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 193) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 194) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 195)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 196) static struct map_iter *map_iter_alloc(struct bpf_map *map)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 197) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 198) struct map_iter *iter;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 199)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 200) iter = kzalloc(sizeof(*iter), GFP_KERNEL | __GFP_NOWARN);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 201) if (!iter)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 202) goto error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 203)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 204) iter->key = kzalloc(map->key_size, GFP_KERNEL | __GFP_NOWARN);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 205) if (!iter->key)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 206) goto error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 207)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 208) return iter;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 209)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 210) error:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 211) map_iter_free(iter);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 212) return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 213) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 214)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 215) static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 216) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 217) struct bpf_map *map = seq_file_to_map(m);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 218) void *key = map_iter(m)->key;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 219) void *prev_key;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 220)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 221) (*pos)++;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 222) if (map_iter(m)->done)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 223) return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 224)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 225) if (unlikely(v == SEQ_START_TOKEN))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 226) prev_key = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 227) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 228) prev_key = key;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 229)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 230) rcu_read_lock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 231) if (map->ops->map_get_next_key(map, prev_key, key)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 232) map_iter(m)->done = true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 233) key = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 234) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 235) rcu_read_unlock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 236) return key;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 237) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 238)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 239) static void *map_seq_start(struct seq_file *m, loff_t *pos)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 240) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 241) if (map_iter(m)->done)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 242) return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 243)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 244) return *pos ? map_iter(m)->key : SEQ_START_TOKEN;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 245) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 246)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 247) static void map_seq_stop(struct seq_file *m, void *v)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 248) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 249) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 250)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 251) static int map_seq_show(struct seq_file *m, void *v)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 252) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 253) struct bpf_map *map = seq_file_to_map(m);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 254) void *key = map_iter(m)->key;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 255)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 256) if (unlikely(v == SEQ_START_TOKEN)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 257) seq_puts(m, "# WARNING!! The output is for debug purpose only\n");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 258) seq_puts(m, "# WARNING!! The output format will change\n");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 259) } else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 260) map->ops->map_seq_show_elem(map, key, m);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 261) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 262)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 263) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 264) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 265)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 266) static const struct seq_operations bpffs_map_seq_ops = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 267) .start = map_seq_start,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 268) .next = map_seq_next,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 269) .show = map_seq_show,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 270) .stop = map_seq_stop,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 271) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 272)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 273) static int bpffs_map_open(struct inode *inode, struct file *file)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 274) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 275) struct bpf_map *map = inode->i_private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 276) struct map_iter *iter;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 277) struct seq_file *m;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 278) int err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 279)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 280) iter = map_iter_alloc(map);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 281) if (!iter)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 282) return -ENOMEM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 283)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 284) err = seq_open(file, &bpffs_map_seq_ops);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 285) if (err) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 286) map_iter_free(iter);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 287) return err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 288) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 289)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 290) m = file->private_data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 291) m->private = iter;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 292)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 293) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 294) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 295)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 296) static int bpffs_map_release(struct inode *inode, struct file *file)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 297) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 298) struct seq_file *m = file->private_data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 299)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 300) map_iter_free(map_iter(m));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 301)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 302) return seq_release(inode, file);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 303) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 304)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 305) /* bpffs_map_fops should only implement the basic
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 306) * read operation for a BPF map. The purpose is to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 307) * provide a simple user intuitive way to do
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 308) * "cat bpffs/pathto/a-pinned-map".
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 309) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 310) * Other operations (e.g. write, lookup...) should be realized by
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 311) * the userspace tools (e.g. bpftool) through the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 312) * BPF_OBJ_GET_INFO_BY_FD and the map's lookup/update
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 313) * interface.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 314) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 315) static const struct file_operations bpffs_map_fops = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 316) .open = bpffs_map_open,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 317) .read = seq_read,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 318) .release = bpffs_map_release,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 319) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 320)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 321) static int bpffs_obj_open(struct inode *inode, struct file *file)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 322) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 323) return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 324) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 325)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 326) static const struct file_operations bpffs_obj_fops = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 327) .open = bpffs_obj_open,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 328) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 329)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 330) static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 331) const struct inode_operations *iops,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 332) const struct file_operations *fops)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 333) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 334) struct inode *dir = dentry->d_parent->d_inode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 335) struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 336) if (IS_ERR(inode))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 337) return PTR_ERR(inode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 338)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 339) inode->i_op = iops;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 340) inode->i_fop = fops;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 341) inode->i_private = raw;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 342)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 343) bpf_dentry_finalize(dentry, inode, dir);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 344) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 345) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 346)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 347) static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 348) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 349) return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 350) &bpffs_obj_fops);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 351) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 352)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 353) static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 354) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 355) struct bpf_map *map = arg;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 356)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 357) return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 358) bpf_map_support_seq_show(map) ?
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 359) &bpffs_map_fops : &bpffs_obj_fops);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 360) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 361)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 362) static int bpf_mklink(struct dentry *dentry, umode_t mode, void *arg)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 363) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 364) struct bpf_link *link = arg;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 365)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 366) return bpf_mkobj_ops(dentry, mode, arg, &bpf_link_iops,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 367) bpf_link_is_iter(link) ?
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 368) &bpf_iter_fops : &bpffs_obj_fops);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 369) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 370)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 371) static struct dentry *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 372) bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 373) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 374) /* Dots in names (e.g. "/sys/fs/bpf/foo.bar") are reserved for future
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 375) * extensions. That allows popoulate_bpffs() create special files.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 376) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 377) if ((dir->i_mode & S_IALLUGO) &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 378) strchr(dentry->d_name.name, '.'))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 379) return ERR_PTR(-EPERM);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 380)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 381) return simple_lookup(dir, dentry, flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 382) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 383)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 384) static int bpf_symlink(struct inode *dir, struct dentry *dentry,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 385) const char *target)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 386) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 387) char *link = kstrdup(target, GFP_USER | __GFP_NOWARN);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 388) struct inode *inode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 389)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 390) if (!link)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 391) return -ENOMEM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 392)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 393) inode = bpf_get_inode(dir->i_sb, dir, S_IRWXUGO | S_IFLNK);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 394) if (IS_ERR(inode)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 395) kfree(link);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 396) return PTR_ERR(inode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 397) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 398)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 399) inode->i_op = &simple_symlink_inode_operations;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 400) inode->i_link = link;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 401)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 402) bpf_dentry_finalize(dentry, inode, dir);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 403) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 404) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 405)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 406) static const struct inode_operations bpf_dir_iops = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 407) .lookup = bpf_lookup,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 408) .mkdir = bpf_mkdir,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 409) .symlink = bpf_symlink,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 410) .rmdir = simple_rmdir,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 411) .rename = simple_rename,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 412) .link = simple_link,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 413) .unlink = simple_unlink,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 414) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 415)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 416) /* pin iterator link into bpffs */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 417) static int bpf_iter_link_pin_kernel(struct dentry *parent,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 418) const char *name, struct bpf_link *link)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 419) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 420) umode_t mode = S_IFREG | S_IRUSR;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 421) struct dentry *dentry;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 422) int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 423)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 424) inode_lock(parent->d_inode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 425) dentry = lookup_one_len(name, parent, strlen(name));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 426) if (IS_ERR(dentry)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 427) inode_unlock(parent->d_inode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 428) return PTR_ERR(dentry);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 429) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 430) ret = bpf_mkobj_ops(dentry, mode, link, &bpf_link_iops,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 431) &bpf_iter_fops);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 432) dput(dentry);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 433) inode_unlock(parent->d_inode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 434) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 435) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 436)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 437) static int bpf_obj_do_pin(const char __user *pathname, void *raw,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 438) enum bpf_type type)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 439) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 440) struct dentry *dentry;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 441) struct inode *dir;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 442) struct path path;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 443) umode_t mode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 444) int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 445)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 446) dentry = user_path_create(AT_FDCWD, pathname, &path, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 447) if (IS_ERR(dentry))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 448) return PTR_ERR(dentry);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 449)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 450) mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask());
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 451)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 452) ret = security_path_mknod(&path, dentry, mode, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 453) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 454) goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 455)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 456) dir = d_inode(path.dentry);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 457) if (dir->i_op != &bpf_dir_iops) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 458) ret = -EPERM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 459) goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 460) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 461)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 462) switch (type) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 463) case BPF_TYPE_PROG:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 464) ret = vfs_mkobj(dentry, mode, bpf_mkprog, raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 465) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 466) case BPF_TYPE_MAP:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 467) ret = vfs_mkobj(dentry, mode, bpf_mkmap, raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 468) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 469) case BPF_TYPE_LINK:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 470) ret = vfs_mkobj(dentry, mode, bpf_mklink, raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 471) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 472) default:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 473) ret = -EPERM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 474) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 475) out:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 476) done_path_create(&path, dentry);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 477) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 478) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 479)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 480) int bpf_obj_pin_user(u32 ufd, const char __user *pathname)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 481) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 482) enum bpf_type type;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 483) void *raw;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 484) int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 485)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 486) raw = bpf_fd_probe_obj(ufd, &type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 487) if (IS_ERR(raw))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 488) return PTR_ERR(raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 489)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 490) ret = bpf_obj_do_pin(pathname, raw, type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 491) if (ret != 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 492) bpf_any_put(raw, type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 493)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 494) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 495) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 496)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 497) static void *bpf_obj_do_get(const char __user *pathname,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 498) enum bpf_type *type, int flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 499) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 500) struct inode *inode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 501) struct path path;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 502) void *raw;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 503) int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 504)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 505) ret = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW, &path);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 506) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 507) return ERR_PTR(ret);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 508)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 509) inode = d_backing_inode(path.dentry);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 510) ret = inode_permission(inode, ACC_MODE(flags));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 511) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 512) goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 513)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 514) ret = bpf_inode_type(inode, type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 515) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 516) goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 517)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 518) raw = bpf_any_get(inode->i_private, *type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 519) if (!IS_ERR(raw))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 520) touch_atime(&path);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 521)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 522) path_put(&path);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 523) return raw;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 524) out:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 525) path_put(&path);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 526) return ERR_PTR(ret);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 527) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 528)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 529) int bpf_obj_get_user(const char __user *pathname, int flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 530) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 531) enum bpf_type type = BPF_TYPE_UNSPEC;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 532) int f_flags;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 533) void *raw;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 534) int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 535)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 536) f_flags = bpf_get_file_flag(flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 537) if (f_flags < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 538) return f_flags;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 539)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 540) raw = bpf_obj_do_get(pathname, &type, f_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 541) if (IS_ERR(raw))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 542) return PTR_ERR(raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 543)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 544) if (type == BPF_TYPE_PROG)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 545) ret = bpf_prog_new_fd(raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 546) else if (type == BPF_TYPE_MAP)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 547) ret = bpf_map_new_fd(raw, f_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 548) else if (type == BPF_TYPE_LINK)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 549) ret = (f_flags != O_RDWR) ? -EINVAL : bpf_link_new_fd(raw);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 550) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 551) return -ENOENT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 552)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 553) if (ret < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 554) bpf_any_put(raw, type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 555) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 556) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 557)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 558) static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 559) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 560) struct bpf_prog *prog;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 561) int ret = inode_permission(inode, MAY_READ);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 562) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 563) return ERR_PTR(ret);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 564)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 565) if (inode->i_op == &bpf_map_iops)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 566) return ERR_PTR(-EINVAL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 567) if (inode->i_op == &bpf_link_iops)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 568) return ERR_PTR(-EINVAL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 569) if (inode->i_op != &bpf_prog_iops)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 570) return ERR_PTR(-EACCES);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 571)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 572) prog = inode->i_private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 573)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 574) ret = security_bpf_prog(prog);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 575) if (ret < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 576) return ERR_PTR(ret);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 577)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 578) if (!bpf_prog_get_ok(prog, &type, false))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 579) return ERR_PTR(-EINVAL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 580)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 581) bpf_prog_inc(prog);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 582) return prog;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 583) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 584)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 585) struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 586) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 587) struct bpf_prog *prog;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 588) struct path path;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 589) int ret = kern_path(name, LOOKUP_FOLLOW, &path);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 590) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 591) return ERR_PTR(ret);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 592) prog = __get_prog_inode(d_backing_inode(path.dentry), type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 593) if (!IS_ERR(prog))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 594) touch_atime(&path);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 595) path_put(&path);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 596) return prog;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 597) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 598) EXPORT_SYMBOL(bpf_prog_get_type_path);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 599)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 600) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 601) * Display the mount options in /proc/mounts.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 602) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 603) static int bpf_show_options(struct seq_file *m, struct dentry *root)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 604) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 605) umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 606)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 607) if (mode != S_IRWXUGO)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 608) seq_printf(m, ",mode=%o", mode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 609) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 610) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 611)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 612) static void bpf_free_inode(struct inode *inode)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 613) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 614) enum bpf_type type;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 615)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 616) if (S_ISLNK(inode->i_mode))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 617) kfree(inode->i_link);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 618) if (!bpf_inode_type(inode, &type))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 619) bpf_any_put(inode->i_private, type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 620) free_inode_nonrcu(inode);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 621) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 622)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 623) static const struct super_operations bpf_super_ops = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 624) .statfs = simple_statfs,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 625) .drop_inode = generic_delete_inode,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 626) .show_options = bpf_show_options,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 627) .free_inode = bpf_free_inode,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 628) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 629)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 630) enum {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 631) OPT_MODE,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 632) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 633)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 634) static const struct fs_parameter_spec bpf_fs_parameters[] = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 635) fsparam_u32oct ("mode", OPT_MODE),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 636) {}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 637) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 638)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 639) struct bpf_mount_opts {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 640) umode_t mode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 641) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 642)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 643) static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 644) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 645) struct bpf_mount_opts *opts = fc->fs_private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 646) struct fs_parse_result result;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 647) int opt;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 648)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 649) opt = fs_parse(fc, bpf_fs_parameters, param, &result);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 650) if (opt < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 651) /* We might like to report bad mount options here, but
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 652) * traditionally we've ignored all mount options, so we'd
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 653) * better continue to ignore non-existing options for bpf.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 654) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 655) return opt == -ENOPARAM ? 0 : opt;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 656)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 657) switch (opt) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 658) case OPT_MODE:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 659) opts->mode = result.uint_32 & S_IALLUGO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 660) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 661) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 662)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 663) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 664) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 665)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 666) struct bpf_preload_ops *bpf_preload_ops;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 667) EXPORT_SYMBOL_GPL(bpf_preload_ops);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 668)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 669) static bool bpf_preload_mod_get(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 670) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 671) /* If bpf_preload.ko wasn't loaded earlier then load it now.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 672) * When bpf_preload is built into vmlinux the module's __init
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 673) * function will populate it.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 674) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 675) if (!bpf_preload_ops) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 676) request_module("bpf_preload");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 677) if (!bpf_preload_ops)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 678) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 679) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 680) /* And grab the reference, so the module doesn't disappear while the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 681) * kernel is interacting with the kernel module and its UMD.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 682) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 683) if (!try_module_get(bpf_preload_ops->owner)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 684) pr_err("bpf_preload module get failed.\n");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 685) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 686) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 687) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 688) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 689)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 690) static void bpf_preload_mod_put(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 691) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 692) if (bpf_preload_ops)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 693) /* now user can "rmmod bpf_preload" if necessary */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 694) module_put(bpf_preload_ops->owner);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 695) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 696)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 697) static DEFINE_MUTEX(bpf_preload_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 698)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 699) static int populate_bpffs(struct dentry *parent)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 700) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 701) struct bpf_preload_info objs[BPF_PRELOAD_LINKS] = {};
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 702) struct bpf_link *links[BPF_PRELOAD_LINKS] = {};
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 703) int err = 0, i;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 704)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 705) /* grab the mutex to make sure the kernel interactions with bpf_preload
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 706) * UMD are serialized
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 707) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 708) mutex_lock(&bpf_preload_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 709)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 710) /* if bpf_preload.ko wasn't built into vmlinux then load it */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 711) if (!bpf_preload_mod_get())
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 712) goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 713)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 714) if (!bpf_preload_ops->info.tgid) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 715) /* preload() will start UMD that will load BPF iterator programs */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 716) err = bpf_preload_ops->preload(objs);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 717) if (err)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 718) goto out_put;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 719) for (i = 0; i < BPF_PRELOAD_LINKS; i++) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 720) links[i] = bpf_link_by_id(objs[i].link_id);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 721) if (IS_ERR(links[i])) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 722) err = PTR_ERR(links[i]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 723) goto out_put;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 724) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 725) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 726) for (i = 0; i < BPF_PRELOAD_LINKS; i++) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 727) err = bpf_iter_link_pin_kernel(parent,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 728) objs[i].link_name, links[i]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 729) if (err)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 730) goto out_put;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 731) /* do not unlink successfully pinned links even
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 732) * if later link fails to pin
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 733) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 734) links[i] = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 735) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 736) /* finish() will tell UMD process to exit */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 737) err = bpf_preload_ops->finish();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 738) if (err)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 739) goto out_put;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 740) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 741) out_put:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 742) bpf_preload_mod_put();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 743) out:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 744) mutex_unlock(&bpf_preload_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 745) for (i = 0; i < BPF_PRELOAD_LINKS && err; i++)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 746) if (!IS_ERR_OR_NULL(links[i]))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 747) bpf_link_put(links[i]);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 748) return err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 749) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 750)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 751) static int bpf_fill_super(struct super_block *sb, struct fs_context *fc)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 752) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 753) static const struct tree_descr bpf_rfiles[] = { { "" } };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 754) struct bpf_mount_opts *opts = fc->fs_private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 755) struct inode *inode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 756) int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 757)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 758) ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 759) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 760) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 761)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 762) sb->s_op = &bpf_super_ops;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 763)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 764) inode = sb->s_root->d_inode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 765) inode->i_op = &bpf_dir_iops;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 766) inode->i_mode &= ~S_IALLUGO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 767) populate_bpffs(sb->s_root);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 768) inode->i_mode |= S_ISVTX | opts->mode;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 769) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 770) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 771)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 772) static int bpf_get_tree(struct fs_context *fc)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 773) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 774) return get_tree_nodev(fc, bpf_fill_super);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 775) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 776)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 777) static void bpf_free_fc(struct fs_context *fc)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 778) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 779) kfree(fc->fs_private);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 780) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 781)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 782) static const struct fs_context_operations bpf_context_ops = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 783) .free = bpf_free_fc,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 784) .parse_param = bpf_parse_param,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 785) .get_tree = bpf_get_tree,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 786) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 787)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 788) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 789) * Set up the filesystem mount context.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 790) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 791) static int bpf_init_fs_context(struct fs_context *fc)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 792) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 793) struct bpf_mount_opts *opts;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 794)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 795) opts = kzalloc(sizeof(struct bpf_mount_opts), GFP_KERNEL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 796) if (!opts)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 797) return -ENOMEM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 798)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 799) opts->mode = S_IRWXUGO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 800)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 801) fc->fs_private = opts;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 802) fc->ops = &bpf_context_ops;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 803) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 804) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 805)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 806) static struct file_system_type bpf_fs_type = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 807) .owner = THIS_MODULE,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 808) .name = "bpf",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 809) .init_fs_context = bpf_init_fs_context,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 810) .parameters = bpf_fs_parameters,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 811) .kill_sb = kill_litter_super,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 812) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 813)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 814) static int __init bpf_init(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 815) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 816) int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 817)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 818) mutex_init(&bpf_preload_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 819)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 820) ret = sysfs_create_mount_point(fs_kobj, "bpf");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 821) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 822) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 823)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 824) ret = register_filesystem(&bpf_fs_type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 825) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 826) sysfs_remove_mount_point(fs_kobj, "bpf");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 827)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 828) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 829) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 830) fs_initcall(bpf_init);