2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 13:43:55 +08:00
linux-next/kernel/bpf/inode.c
Daniel Borkmann e8d2bec045 bpf: decouple btf from seq bpf fs dump and enable more maps
Commit a26ca7c982 ("bpf: btf: Add pretty print support to
the basic arraymap") and 699c86d6ec ("bpf: btf: add pretty
print for hash/lru_hash maps") enabled support for BTF and
dumping via BPF fs for array and hash/lru map. However, both
can be decoupled from each other such that regular BPF maps
can be supported for attaching BTF key/value information,
while not all maps necessarily need to dump via map_seq_show_elem()
callback.

The basic sanity check which is a prerequisite for all maps
is that key/value size has to match in any case, and some maps
can have extra checks via map_check_btf() callback, e.g.
probing certain types or indicating no support in general. With
that we can also enable retrieving BTF info for per-cpu map
types and lpm.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
2018-08-13 00:52:45 +02:00

685 lines
14 KiB
C

/*
* Minimal file system backend for holding eBPF maps and programs,
* used by bpf(2) object pinning.
*
* Authors:
*
* Daniel Borkmann <daniel@iogearbox.net>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* version 2 as published by the Free Software Foundation.
*/
#include <linux/init.h>
#include <linux/magic.h>
#include <linux/major.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/fs.h>
#include <linux/kdev_t.h>
#include <linux/parser.h>
#include <linux/filter.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
enum bpf_type {
BPF_TYPE_UNSPEC = 0,
BPF_TYPE_PROG,
BPF_TYPE_MAP,
};
static void *bpf_any_get(void *raw, enum bpf_type type)
{
switch (type) {
case BPF_TYPE_PROG:
raw = bpf_prog_inc(raw);
break;
case BPF_TYPE_MAP:
raw = bpf_map_inc(raw, true);
break;
default:
WARN_ON_ONCE(1);
break;
}
return raw;
}
static void bpf_any_put(void *raw, enum bpf_type type)
{
switch (type) {
case BPF_TYPE_PROG:
bpf_prog_put(raw);
break;
case BPF_TYPE_MAP:
bpf_map_put_with_uref(raw);
break;
default:
WARN_ON_ONCE(1);
break;
}
}
static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type)
{
void *raw;
*type = BPF_TYPE_MAP;
raw = bpf_map_get_with_uref(ufd);
if (IS_ERR(raw)) {
*type = BPF_TYPE_PROG;
raw = bpf_prog_get(ufd);
}
return raw;
}
static const struct inode_operations bpf_dir_iops;
static const struct inode_operations bpf_prog_iops = { };
static const struct inode_operations bpf_map_iops = { };
static struct inode *bpf_get_inode(struct super_block *sb,
const struct inode *dir,
umode_t mode)
{
struct inode *inode;
switch (mode & S_IFMT) {
case S_IFDIR:
case S_IFREG:
case S_IFLNK:
break;
default:
return ERR_PTR(-EINVAL);
}
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOSPC);
inode->i_ino = get_next_ino();
inode->i_atime = current_time(inode);
inode->i_mtime = inode->i_atime;
inode->i_ctime = inode->i_atime;
inode_init_owner(inode, dir, mode);
return inode;
}
static int bpf_inode_type(const struct inode *inode, enum bpf_type *type)
{
*type = BPF_TYPE_UNSPEC;
if (inode->i_op == &bpf_prog_iops)
*type = BPF_TYPE_PROG;
else if (inode->i_op == &bpf_map_iops)
*type = BPF_TYPE_MAP;
else
return -EACCES;
return 0;
}
static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode,
struct inode *dir)
{
d_instantiate(dentry, inode);
dget(dentry);
dir->i_mtime = current_time(dir);
dir->i_ctime = dir->i_mtime;
}
static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct inode *inode;
inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFDIR);
if (IS_ERR(inode))
return PTR_ERR(inode);
inode->i_op = &bpf_dir_iops;
inode->i_fop = &simple_dir_operations;
inc_nlink(inode);
inc_nlink(dir);
bpf_dentry_finalize(dentry, inode, dir);
return 0;
}
struct map_iter {
void *key;
bool done;
};
static struct map_iter *map_iter(struct seq_file *m)
{
return m->private;
}
static struct bpf_map *seq_file_to_map(struct seq_file *m)
{
return file_inode(m->file)->i_private;
}
static void map_iter_free(struct map_iter *iter)
{
if (iter) {
kfree(iter->key);
kfree(iter);
}
}
static struct map_iter *map_iter_alloc(struct bpf_map *map)
{
struct map_iter *iter;
iter = kzalloc(sizeof(*iter), GFP_KERNEL | __GFP_NOWARN);
if (!iter)
goto error;
iter->key = kzalloc(map->key_size, GFP_KERNEL | __GFP_NOWARN);
if (!iter->key)
goto error;
return iter;
error:
map_iter_free(iter);
return NULL;
}
static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
{
struct bpf_map *map = seq_file_to_map(m);
void *key = map_iter(m)->key;
void *prev_key;
if (map_iter(m)->done)
return NULL;
if (unlikely(v == SEQ_START_TOKEN))
prev_key = NULL;
else
prev_key = key;
if (map->ops->map_get_next_key(map, prev_key, key)) {
map_iter(m)->done = true;
return NULL;
}
++(*pos);
return key;
}
static void *map_seq_start(struct seq_file *m, loff_t *pos)
{
if (map_iter(m)->done)
return NULL;
return *pos ? map_iter(m)->key : SEQ_START_TOKEN;
}
static void map_seq_stop(struct seq_file *m, void *v)
{
}
static int map_seq_show(struct seq_file *m, void *v)
{
struct bpf_map *map = seq_file_to_map(m);
void *key = map_iter(m)->key;
if (unlikely(v == SEQ_START_TOKEN)) {
seq_puts(m, "# WARNING!! The output is for debug purpose only\n");
seq_puts(m, "# WARNING!! The output format will change\n");
} else {
map->ops->map_seq_show_elem(map, key, m);
}
return 0;
}
static const struct seq_operations bpffs_map_seq_ops = {
.start = map_seq_start,
.next = map_seq_next,
.show = map_seq_show,
.stop = map_seq_stop,
};
static int bpffs_map_open(struct inode *inode, struct file *file)
{
struct bpf_map *map = inode->i_private;
struct map_iter *iter;
struct seq_file *m;
int err;
iter = map_iter_alloc(map);
if (!iter)
return -ENOMEM;
err = seq_open(file, &bpffs_map_seq_ops);
if (err) {
map_iter_free(iter);
return err;
}
m = file->private_data;
m->private = iter;
return 0;
}
static int bpffs_map_release(struct inode *inode, struct file *file)
{
struct seq_file *m = file->private_data;
map_iter_free(map_iter(m));
return seq_release(inode, file);
}
/* bpffs_map_fops should only implement the basic
* read operation for a BPF map. The purpose is to
* provide a simple user intuitive way to do
* "cat bpffs/pathto/a-pinned-map".
*
* Other operations (e.g. write, lookup...) should be realized by
* the userspace tools (e.g. bpftool) through the
* BPF_OBJ_GET_INFO_BY_FD and the map's lookup/update
* interface.
*/
static const struct file_operations bpffs_map_fops = {
.open = bpffs_map_open,
.read = seq_read,
.release = bpffs_map_release,
};
static int bpffs_obj_open(struct inode *inode, struct file *file)
{
return -EIO;
}
static const struct file_operations bpffs_obj_fops = {
.open = bpffs_obj_open,
};
static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw,
const struct inode_operations *iops,
const struct file_operations *fops)
{
struct inode *dir = dentry->d_parent->d_inode;
struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
inode->i_op = iops;
inode->i_fop = fops;
inode->i_private = raw;
bpf_dentry_finalize(dentry, inode, dir);
return 0;
}
static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg)
{
return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops,
&bpffs_obj_fops);
}
static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
{
struct bpf_map *map = arg;
return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops,
bpf_map_support_seq_show(map) ?
&bpffs_map_fops : &bpffs_obj_fops);
}
static struct dentry *
bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags)
{
/* Dots in names (e.g. "/sys/fs/bpf/foo.bar") are reserved for future
* extensions.
*/
if (strchr(dentry->d_name.name, '.'))
return ERR_PTR(-EPERM);
return simple_lookup(dir, dentry, flags);
}
static int bpf_symlink(struct inode *dir, struct dentry *dentry,
const char *target)
{
char *link = kstrdup(target, GFP_USER | __GFP_NOWARN);
struct inode *inode;
if (!link)
return -ENOMEM;
inode = bpf_get_inode(dir->i_sb, dir, S_IRWXUGO | S_IFLNK);
if (IS_ERR(inode)) {
kfree(link);
return PTR_ERR(inode);
}
inode->i_op = &simple_symlink_inode_operations;
inode->i_link = link;
bpf_dentry_finalize(dentry, inode, dir);
return 0;
}
static const struct inode_operations bpf_dir_iops = {
.lookup = bpf_lookup,
.mkdir = bpf_mkdir,
.symlink = bpf_symlink,
.rmdir = simple_rmdir,
.rename = simple_rename,
.link = simple_link,
.unlink = simple_unlink,
};
static int bpf_obj_do_pin(const struct filename *pathname, void *raw,
enum bpf_type type)
{
struct dentry *dentry;
struct inode *dir;
struct path path;
umode_t mode;
int ret;
dentry = kern_path_create(AT_FDCWD, pathname->name, &path, 0);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask());
ret = security_path_mknod(&path, dentry, mode, 0);
if (ret)
goto out;
dir = d_inode(path.dentry);
if (dir->i_op != &bpf_dir_iops) {
ret = -EPERM;
goto out;
}
switch (type) {
case BPF_TYPE_PROG:
ret = vfs_mkobj(dentry, mode, bpf_mkprog, raw);
break;
case BPF_TYPE_MAP:
ret = vfs_mkobj(dentry, mode, bpf_mkmap, raw);
break;
default:
ret = -EPERM;
}
out:
done_path_create(&path, dentry);
return ret;
}
int bpf_obj_pin_user(u32 ufd, const char __user *pathname)
{
struct filename *pname;
enum bpf_type type;
void *raw;
int ret;
pname = getname(pathname);
if (IS_ERR(pname))
return PTR_ERR(pname);
raw = bpf_fd_probe_obj(ufd, &type);
if (IS_ERR(raw)) {
ret = PTR_ERR(raw);
goto out;
}
ret = bpf_obj_do_pin(pname, raw, type);
if (ret != 0)
bpf_any_put(raw, type);
out:
putname(pname);
return ret;
}
static void *bpf_obj_do_get(const struct filename *pathname,
enum bpf_type *type, int flags)
{
struct inode *inode;
struct path path;
void *raw;
int ret;
ret = kern_path(pathname->name, LOOKUP_FOLLOW, &path);
if (ret)
return ERR_PTR(ret);
inode = d_backing_inode(path.dentry);
ret = inode_permission(inode, ACC_MODE(flags));
if (ret)
goto out;
ret = bpf_inode_type(inode, type);
if (ret)
goto out;
raw = bpf_any_get(inode->i_private, *type);
if (!IS_ERR(raw))
touch_atime(&path);
path_put(&path);
return raw;
out:
path_put(&path);
return ERR_PTR(ret);
}
int bpf_obj_get_user(const char __user *pathname, int flags)
{
enum bpf_type type = BPF_TYPE_UNSPEC;
struct filename *pname;
int ret = -ENOENT;
int f_flags;
void *raw;
f_flags = bpf_get_file_flag(flags);
if (f_flags < 0)
return f_flags;
pname = getname(pathname);
if (IS_ERR(pname))
return PTR_ERR(pname);
raw = bpf_obj_do_get(pname, &type, f_flags);
if (IS_ERR(raw)) {
ret = PTR_ERR(raw);
goto out;
}
if (type == BPF_TYPE_PROG)
ret = bpf_prog_new_fd(raw);
else if (type == BPF_TYPE_MAP)
ret = bpf_map_new_fd(raw, f_flags);
else
goto out;
if (ret < 0)
bpf_any_put(raw, type);
out:
putname(pname);
return ret;
}
static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type)
{
struct bpf_prog *prog;
int ret = inode_permission(inode, MAY_READ | MAY_WRITE);
if (ret)
return ERR_PTR(ret);
if (inode->i_op == &bpf_map_iops)
return ERR_PTR(-EINVAL);
if (inode->i_op != &bpf_prog_iops)
return ERR_PTR(-EACCES);
prog = inode->i_private;
ret = security_bpf_prog(prog);
if (ret < 0)
return ERR_PTR(ret);
if (!bpf_prog_get_ok(prog, &type, false))
return ERR_PTR(-EINVAL);
return bpf_prog_inc(prog);
}
struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type)
{
struct bpf_prog *prog;
struct path path;
int ret = kern_path(name, LOOKUP_FOLLOW, &path);
if (ret)
return ERR_PTR(ret);
prog = __get_prog_inode(d_backing_inode(path.dentry), type);
if (!IS_ERR(prog))
touch_atime(&path);
path_put(&path);
return prog;
}
EXPORT_SYMBOL(bpf_prog_get_type_path);
static void bpf_evict_inode(struct inode *inode)
{
enum bpf_type type;
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (S_ISLNK(inode->i_mode))
kfree(inode->i_link);
if (!bpf_inode_type(inode, &type))
bpf_any_put(inode->i_private, type);
}
/*
* Display the mount options in /proc/mounts.
*/
static int bpf_show_options(struct seq_file *m, struct dentry *root)
{
umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX;
if (mode != S_IRWXUGO)
seq_printf(m, ",mode=%o", mode);
return 0;
}
static const struct super_operations bpf_super_ops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
.show_options = bpf_show_options,
.evict_inode = bpf_evict_inode,
};
enum {
OPT_MODE,
OPT_ERR,
};
static const match_table_t bpf_mount_tokens = {
{ OPT_MODE, "mode=%o" },
{ OPT_ERR, NULL },
};
struct bpf_mount_opts {
umode_t mode;
};
static int bpf_parse_options(char *data, struct bpf_mount_opts *opts)
{
substring_t args[MAX_OPT_ARGS];
int option, token;
char *ptr;
opts->mode = S_IRWXUGO;
while ((ptr = strsep(&data, ",")) != NULL) {
if (!*ptr)
continue;
token = match_token(ptr, bpf_mount_tokens, args);
switch (token) {
case OPT_MODE:
if (match_octal(&args[0], &option))
return -EINVAL;
opts->mode = option & S_IALLUGO;
break;
/* We might like to report bad mount options here, but
* traditionally we've ignored all mount options, so we'd
* better continue to ignore non-existing options for bpf.
*/
}
}
return 0;
}
static int bpf_fill_super(struct super_block *sb, void *data, int silent)
{
static const struct tree_descr bpf_rfiles[] = { { "" } };
struct bpf_mount_opts opts;
struct inode *inode;
int ret;
ret = bpf_parse_options(data, &opts);
if (ret)
return ret;
ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles);
if (ret)
return ret;
sb->s_op = &bpf_super_ops;
inode = sb->s_root->d_inode;
inode->i_op = &bpf_dir_iops;
inode->i_mode &= ~S_IALLUGO;
inode->i_mode |= S_ISVTX | opts.mode;
return 0;
}
static struct dentry *bpf_mount(struct file_system_type *type, int flags,
const char *dev_name, void *data)
{
return mount_nodev(type, flags, data, bpf_fill_super);
}
static struct file_system_type bpf_fs_type = {
.owner = THIS_MODULE,
.name = "bpf",
.mount = bpf_mount,
.kill_sb = kill_litter_super,
};
static int __init bpf_init(void)
{
int ret;
ret = sysfs_create_mount_point(fs_kobj, "bpf");
if (ret)
return ret;
ret = register_filesystem(&bpf_fs_type);
if (ret)
sysfs_remove_mount_point(fs_kobj, "bpf");
return ret;
}
fs_initcall(bpf_init);