iptables: open eBPF programs in read only mode

Adjust the mode eBPF programs are opened in so 0400 pinned bpf programs
work without requiring CAP_DAC_OVERRIDE.

This matches Linux 5.2's:
  commit e547ff3f803e779a3898f1f48447b29f43c54085
  Author: Chenbo Feng <fengc@google.com>
  Date:   Tue May 14 19:42:57 2019 -0700

    bpf: relax inode permission check for retrieving bpf program

    For iptable module to load a bpf program from a pinned location, it
    only retrieve a loaded program and cannot change the program content so
    requiring a write permission for it might not be necessary.
    Also when adding or removing an unrelated iptable rule, it might need to
    flush and reload the xt_bpf related rules as well and triggers the inode
    permission check. It might be better to remove the write premission
    check for the inode so we won't need to grant write access to all the
    processes that flush and restore iptables rules.

  kernel/bpf/inode.c:
  - int ret = inode_permission(inode, MAY_READ | MAY_WRITE);
  + int ret = inode_permission(inode, MAY_READ);

In practice, AFAICT, the xt_bpf match .fd field isn't even used by new
kernels, but I believe it might be needed for compatibility with old ones
(though I'm pretty sure table modifications on them will outright fail).

Test: builds, passes Android test suite (albeit on an older iptables base),
  git grep bpf_obj_get - finds no other users
Cc: Chenbo Feng <fengc@google.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/extensions/libxt_bpf.c b/extensions/libxt_bpf.c
index 92958247c7565b752c7b049ba156b777586a9310..eeae86e5504c0902a22c88fa2fa248cd25209a07 100644 (file)
--- a/extensions/libxt_bpf.c
+++ b/extensions/libxt_bpf.c
@@ -61,14 +61,26 @@ static const struct xt_option_entry bpf_opts_v1[] = {
        XTOPT_TABLEEND,
 };
 
-static int bpf_obj_get(const char *filepath)
+static int bpf_obj_get_readonly(const char *filepath)
 {
 #if defined HAVE_LINUX_BPF_H && defined __NR_bpf && defined BPF_FS_MAGIC
-       union bpf_attr attr;
-
-       memset(&attr, 0, sizeof(attr));
-       attr.pathname = (__u64) filepath;
-
+       /* union bpf_attr includes this in an anonymous struct, but the
+        * file_flags field and the BPF_F_RDONLY constant are only present
+        * in Linux 4.15+ kernel headers (include/uapi/linux/bpf.h)
+        */
+       struct {   // this part of union bpf_attr is for BPF_OBJ_* commands
+               __aligned_u64   pathname;
+               __u32           bpf_fd;
+               __u32           file_flags;
+       } attr = {
+               .pathname = (__u64)filepath,
+               .file_flags = (1U << 3),   // BPF_F_RDONLY
+       };
+       int fd = syscall(__NR_bpf, BPF_OBJ_GET, &attr, sizeof(attr));
+       if (fd >= 0) return fd;
+
+       /* on any error fallback to default R/W access for pre-4.15-rc1 kernels */
+       attr.file_flags = 0;
        return syscall(__NR_bpf, BPF_OBJ_GET, &attr, sizeof(attr));
 #else
        xtables_error(OTHER_PROBLEM,
@@ -125,7 +137,7 @@ static void bpf_parse_string(struct sock_filter *pc, __u16 *lenp, __u16 len_max,
 static void bpf_parse_obj_pinned(struct xt_bpf_info_v1 *bi,
                                 const char *filepath)
 {
-       bi->fd = bpf_obj_get(filepath);
+       bi->fd = bpf_obj_get_readonly(filepath);
        if (bi->fd < 0)
                xtables_error(PARAMETER_PROBLEM,
                              "bpf: failed to get bpf object");