Current UAPI of BPF_OBJ_PIN and BPF_OBJ_GET commands of bpf() syscall forces users to specify pinning location as a string-based absolute or relative (to current working directory) path. This has various implications related to security (e.g., symlink-based attacks), forces BPF FS to be exposed in the file system, which can cause races with other applications. One of the feedbacks we got from folks working with containers heavily was that inability to use purely FD-based location specification was an unfortunate limitation and hindrance for BPF_OBJ_PIN and BPF_OBJ_GET commands. This patch closes this oversight, adding path_fd field to BPF_OBJ_PIN and BPF_OBJ_GET UAPI, following conventions established by *at() syscalls for dirfd + pathname combinations. This now allows interesting possibilities like working with detached BPF FS mount (e.g., to perform multiple pinnings without running a risk of someone interfering with them), and generally making pinning/getting more secure and not prone to any races and/or security attacks. This is demonstrated by a selftest added in subsequent patch that takes advantage of new mount APIs (fsopen, fsconfig, fsmount) to demonstrate creating detached BPF FS mount, pinning, and then getting BPF map out of it, all while never exposing this private instance of BPF FS to outside worlds. Signed-off-by: Andrii Nakryiko <andrii@xxxxxxxxxx> --- include/linux/bpf.h | 4 ++-- include/uapi/linux/bpf.h | 5 +++++ kernel/bpf/inode.c | 16 ++++++++-------- kernel/bpf/syscall.c | 8 +++++--- tools/include/uapi/linux/bpf.h | 5 +++++ 5 files changed, 25 insertions(+), 13 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 36e4b2d8cca2..f58895830ada 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2077,8 +2077,8 @@ struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); -int bpf_obj_pin_user(u32 ufd, const char __user *pathname); -int bpf_obj_get_user(const char __user *pathname, int flags); +int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); +int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1bb11a6ee667..db2870a52ce0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1420,6 +1420,11 @@ union bpf_attr { __aligned_u64 pathname; __u32 bpf_fd; __u32 file_flags; + /* same as dirfd in openat() syscall; see openat(2) + * manpage for details of dirfd/path_fd and pathname semantics; + * zero path_fd implies AT_FDCWD behavior + */ + __u32 path_fd; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 9948b542a470..13bb54f6bd17 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -435,7 +435,7 @@ static int bpf_iter_link_pin_kernel(struct dentry *parent, return ret; } -static int bpf_obj_do_pin(const char __user *pathname, void *raw, +static int bpf_obj_do_pin(int path_fd, const char __user *pathname, void *raw, enum bpf_type type) { struct dentry *dentry; @@ -444,7 +444,7 @@ static int bpf_obj_do_pin(const char __user *pathname, void *raw, umode_t mode; int ret; - dentry = user_path_create(AT_FDCWD, pathname, &path, 0); + dentry = user_path_create(path_fd, pathname, &path, 0); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -478,7 +478,7 @@ static int bpf_obj_do_pin(const char __user *pathname, void *raw, return ret; } -int bpf_obj_pin_user(u32 ufd, const char __user *pathname) +int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname) { enum bpf_type type; void *raw; @@ -488,14 +488,14 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname) if (IS_ERR(raw)) return PTR_ERR(raw); - ret = bpf_obj_do_pin(pathname, raw, type); + ret = bpf_obj_do_pin(path_fd, pathname, raw, type); if (ret != 0) bpf_any_put(raw, type); return ret; } -static void *bpf_obj_do_get(const char __user *pathname, +static void *bpf_obj_do_get(int path_fd, const char __user *pathname, enum bpf_type *type, int flags) { struct inode *inode; @@ -503,7 +503,7 @@ static void *bpf_obj_do_get(const char __user *pathname, void *raw; int ret; - ret = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW, &path); + ret = user_path_at(path_fd, pathname, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); @@ -527,7 +527,7 @@ static void *bpf_obj_do_get(const char __user *pathname, return ERR_PTR(ret); } -int bpf_obj_get_user(const char __user *pathname, int flags) +int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; int f_flags; @@ -538,7 +538,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags) if (f_flags < 0) return f_flags; - raw = bpf_obj_do_get(pathname, &type, f_flags); + raw = bpf_obj_do_get(path_fd, pathname, &type, f_flags); if (IS_ERR(raw)) return PTR_ERR(raw); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 909c112ef537..65a46f6d4be0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2697,14 +2697,15 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) return err; } -#define BPF_OBJ_LAST_FIELD file_flags +#define BPF_OBJ_LAST_FIELD path_fd static int bpf_obj_pin(const union bpf_attr *attr) { if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0) return -EINVAL; - return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname)); + return bpf_obj_pin_user(attr->bpf_fd, attr->path_fd ?: AT_FDCWD, + u64_to_user_ptr(attr->pathname)); } static int bpf_obj_get(const union bpf_attr *attr) @@ -2713,7 +2714,8 @@ static int bpf_obj_get(const union bpf_attr *attr) attr->file_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; - return bpf_obj_get_user(u64_to_user_ptr(attr->pathname), + return bpf_obj_get_user(attr->path_fd ?: AT_FDCWD, + u64_to_user_ptr(attr->pathname), attr->file_flags); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1bb11a6ee667..db2870a52ce0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1420,6 +1420,11 @@ union bpf_attr { __aligned_u64 pathname; __u32 bpf_fd; __u32 file_flags; + /* same as dirfd in openat() syscall; see openat(2) + * manpage for details of dirfd/path_fd and pathname semantics; + * zero path_fd implies AT_FDCWD behavior + */ + __u32 path_fd; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ -- 2.34.1