Andrii Nakryiko <andrii.nakryiko@xxxxxxxxx> writes:
> On Mon, Mar 2, 2020 at 2:13 AM Toke Høiland-Jørgensen <toke@xxxxxxxxxx> wrote:
>>
>> Andrii Nakryiko <andriin@xxxxxx> writes:
>>
>> > Introduce bpf_link abstraction, representing an attachment of BPF program to
>> > a BPF hook point (e.g., tracepoint, perf event, etc). bpf_link encapsulates
>> > ownership of attached BPF program, reference counting of a link itself, when
>> > reference from multiple anonymous inodes, as well as ensures that release
>> > callback will be called from a process context, so that users can safely take
>> > mutex locks and sleep.
>> >
>> > Additionally, with a new abstraction it's now possible to generalize pinning
>> > of a link object in BPF FS, allowing to explicitly prevent BPF program
>> > detachment on process exit by pinning it in a BPF FS and let it open from
>> > independent other process to keep working with it.
>> >
>> > Convert two existing bpf_link-like objects (raw tracepoint and tracing BPF
>> > program attachments) into utilizing bpf_link framework, making them pinnable
>> > in BPF FS. More FD-based bpf_links will be added in follow up patches.
>> >
>> > Signed-off-by: Andrii Nakryiko <andriin@xxxxxx>
>> > ---
>> > include/linux/bpf.h | 13 +++
>> > kernel/bpf/inode.c | 42 ++++++++-
>> > kernel/bpf/syscall.c | 209 ++++++++++++++++++++++++++++++++++++-------
>> > 3 files changed, 226 insertions(+), 38 deletions(-)
>> >
>> > diff --git a/include/linux/bpf.h b/include/linux/bpf.h
>> > index 6015a4daf118..f13c78c6f29d 100644
>> > --- a/include/linux/bpf.h
>> > +++ b/include/linux/bpf.h
>> > @@ -1056,6 +1056,19 @@ extern int sysctl_unprivileged_bpf_disabled;
>> > int bpf_map_new_fd(struct bpf_map *map, int flags);
>> > int bpf_prog_new_fd(struct bpf_prog *prog);
>> >
>> > +struct bpf_link;
>> > +
>> > +struct bpf_link_ops {
>> > + void (*release)(struct bpf_link *link);
>> > +};
>> > +
>> > +void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops,
>> > + struct bpf_prog *prog);
>> > +void bpf_link_inc(struct bpf_link *link);
>> > +void bpf_link_put(struct bpf_link *link);
>> > +int bpf_link_new_fd(struct bpf_link *link);
>> > +struct bpf_link *bpf_link_get_from_fd(u32 ufd);
>> > +
>> > int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
>> > int bpf_obj_get_user(const char __user *pathname, int flags);
>> >
>> > diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
>> > index 5e40e7fccc21..95087d9f4ed3 100644
>> > --- a/kernel/bpf/inode.c
>> > +++ b/kernel/bpf/inode.c
>> > @@ -25,6 +25,7 @@ enum bpf_type {
>> > BPF_TYPE_UNSPEC = 0,
>> > BPF_TYPE_PROG,
>> > BPF_TYPE_MAP,
>> > + BPF_TYPE_LINK,
>> > };
>> >
>> > static void *bpf_any_get(void *raw, enum bpf_type type)
>> > @@ -36,6 +37,9 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
>> > case BPF_TYPE_MAP:
>> > bpf_map_inc_with_uref(raw);
>> > break;
>> > + case BPF_TYPE_LINK:
>> > + bpf_link_inc(raw);
>> > + break;
>> > default:
>> > WARN_ON_ONCE(1);
>> > break;
>> > @@ -53,6 +57,9 @@ static void bpf_any_put(void *raw, enum bpf_type type)
>> > case BPF_TYPE_MAP:
>> > bpf_map_put_with_uref(raw);
>> > break;
>> > + case BPF_TYPE_LINK:
>> > + bpf_link_put(raw);
>> > + break;
>> > default:
>> > WARN_ON_ONCE(1);
>> > break;
>> > @@ -63,20 +70,32 @@ 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)) {
>> > + if (!IS_ERR(raw)) {
>> > + *type = BPF_TYPE_MAP;
>> > + return raw;
>> > + }
>> > +
>> > + raw = bpf_prog_get(ufd);
>> > + if (!IS_ERR(raw)) {
>> > *type = BPF_TYPE_PROG;
>> > - raw = bpf_prog_get(ufd);
>> > + return raw;
>> > }
>> >
>> > - return raw;
>> > + raw = bpf_link_get_from_fd(ufd);
>> > + if (!IS_ERR(raw)) {
>> > + *type = BPF_TYPE_LINK;
>> > + return raw;
>> > + }
>> > +
>> > + return ERR_PTR(-EINVAL);
>> > }
>> >
>> > 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 const struct inode_operations bpf_link_iops = { };
>> >
>> > static struct inode *bpf_get_inode(struct super_block *sb,
>> > const struct inode *dir,
>> > @@ -114,6 +133,8 @@ static int bpf_inode_type(const struct inode *inode, enum bpf_type *type)
>> > *type = BPF_TYPE_PROG;
>> > else if (inode->i_op == &bpf_map_iops)
>> > *type = BPF_TYPE_MAP;
>> > + else if (inode->i_op == &bpf_link_iops)
>> > + *type = BPF_TYPE_LINK;
>> > else
>> > return -EACCES;
>> >
>> > @@ -335,6 +356,12 @@ static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
>> > &bpffs_map_fops : &bpffs_obj_fops);
>> > }
>> >
>> > +static int bpf_mklink(struct dentry *dentry, umode_t mode, void *arg)
>> > +{
>> > + return bpf_mkobj_ops(dentry, mode, arg, &bpf_link_iops,
>> > + &bpffs_obj_fops);
>> > +}
>> > +
>> > static struct dentry *
>> > bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags)
>> > {
>> > @@ -411,6 +438,9 @@ static int bpf_obj_do_pin(const char __user *pathname, void *raw,
>> > case BPF_TYPE_MAP:
>> > ret = vfs_mkobj(dentry, mode, bpf_mkmap, raw);
>> > break;
>> > + case BPF_TYPE_LINK:
>> > + ret = vfs_mkobj(dentry, mode, bpf_mklink, raw);
>> > + break;
>> > default:
>> > ret = -EPERM;
>> > }
>> > @@ -487,6 +517,8 @@ int bpf_obj_get_user(const char __user *pathname, int flags)
>> > ret = bpf_prog_new_fd(raw);
>> > else if (type == BPF_TYPE_MAP)
>> > ret = bpf_map_new_fd(raw, f_flags);
>> > + else if (type == BPF_TYPE_LINK)
>> > + ret = bpf_link_new_fd(raw);
>> > else
>> > return -ENOENT;
>> >
>> > @@ -504,6 +536,8 @@ static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type
>> >
>> > if (inode->i_op == &bpf_map_iops)
>> > return ERR_PTR(-EINVAL);
>> > + if (inode->i_op == &bpf_link_iops)
>> > + return ERR_PTR(-EINVAL);
>> > if (inode->i_op != &bpf_prog_iops)
>> > return ERR_PTR(-EACCES);
>> >
>> > diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
>> > index c536c65256ad..fca8de7e7872 100644
>> > --- a/kernel/bpf/syscall.c
>> > +++ b/kernel/bpf/syscall.c
>> > @@ -2173,23 +2173,153 @@ static int bpf_obj_get(const union bpf_attr *attr)
>> > attr->file_flags);
>> > }
>> >
>> > -static int bpf_tracing_prog_release(struct inode *inode, struct file *filp)
>> > +struct bpf_link {
>> > + atomic64_t refcnt;
>>
>> refcount_t ?
>
> Both bpf_map and bpf_prog stick to atomic64 for their refcounting, so
> I'd like to stay consistent and use refcount that can't possible leak
> resources (which refcount_t can, if it's overflown).
refcount_t is specifically supposed to turn a possible use-after-free on
under/overflow into a warning, isn't it? Not going to insist or anything
here, just found it odd that you'd prefer the other...
-Toke
