4.4-stable review patch. If anyone has any objections, please let me know. ------------------ From: Daniel Borkmann <daniel@xxxxxxxxxxxxx> [ Upstream commit 5a5abb1fa3b05dd6aa821525832644c1e7d2905f ] Sasha Levin reported a suspicious rcu_dereference_protected() warning found while fuzzing with trinity that is similar to this one: [ 52.765684] net/core/filter.c:2262 suspicious rcu_dereference_protected() usage! [ 52.765688] other info that might help us debug this: [ 52.765695] rcu_scheduler_active = 1, debug_locks = 1 [ 52.765701] 1 lock held by a.out/1525: [ 52.765704] #0: (rtnl_mutex){+.+.+.}, at: [<ffffffff816a64b7>] rtnl_lock+0x17/0x20 [ 52.765721] stack backtrace: [ 52.765728] CPU: 1 PID: 1525 Comm: a.out Not tainted 4.5.0+ #264 [...] [ 52.765768] Call Trace: [ 52.765775] [<ffffffff813e488d>] dump_stack+0x85/0xc8 [ 52.765784] [<ffffffff810f2fa5>] lockdep_rcu_suspicious+0xd5/0x110 [ 52.765792] [<ffffffff816afdc2>] sk_detach_filter+0x82/0x90 [ 52.765801] [<ffffffffa0883425>] tun_detach_filter+0x35/0x90 [tun] [ 52.765810] [<ffffffffa0884ed4>] __tun_chr_ioctl+0x354/0x1130 [tun] [ 52.765818] [<ffffffff8136fed0>] ? selinux_file_ioctl+0x130/0x210 [ 52.765827] [<ffffffffa0885ce3>] tun_chr_ioctl+0x13/0x20 [tun] [ 52.765834] [<ffffffff81260ea6>] do_vfs_ioctl+0x96/0x690 [ 52.765843] [<ffffffff81364af3>] ? security_file_ioctl+0x43/0x60 [ 52.765850] [<ffffffff81261519>] SyS_ioctl+0x79/0x90 [ 52.765858] [<ffffffff81003ba2>] do_syscall_64+0x62/0x140 [ 52.765866] [<ffffffff817d563f>] entry_SYSCALL64_slow_path+0x25/0x25 Same can be triggered with PROVE_RCU (+ PROVE_RCU_REPEATEDLY) enabled from tun_attach_filter() when user space calls ioctl(tun_fd, TUN{ATTACH, DETACH}FILTER, ...) for adding/removing a BPF filter on tap devices. Since the fix in f91ff5b9ff52 ("net: sk_{detach|attach}_filter() rcu fixes") sk_attach_filter()/sk_detach_filter() now dereferences the filter with rcu_dereference_protected(), checking whether socket lock is held in control path. Since its introduction in 994051625981 ("tun: socket filter support"), tap filters are managed under RTNL lock from __tun_chr_ioctl(). Thus the sock_owned_by_user(sk) doesn't apply in this specific case and therefore triggers the false positive. Extend the BPF API with __sk_attach_filter()/__sk_detach_filter() pair that is used by tap filters and pass in lockdep_rtnl_is_held() for the rcu_dereference_protected() checks instead. Reported-by: Sasha Levin <sasha.levin@xxxxxxxxxx> Signed-off-by: Daniel Borkmann <daniel@xxxxxxxxxxxxx> Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- drivers/net/tun.c | 8 +++++--- include/linux/filter.h | 4 ++++ net/core/filter.c | 33 +++++++++++++++++++++------------ 3 files changed, 30 insertions(+), 15 deletions(-) --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -621,7 +621,8 @@ static int tun_attach(struct tun_struct /* Re-attach the filter to persist device */ if (!skip_filter && (tun->filter_attached == true)) { - err = sk_attach_filter(&tun->fprog, tfile->socket.sk); + err = __sk_attach_filter(&tun->fprog, tfile->socket.sk, + lockdep_rtnl_is_held()); if (!err) goto out; } @@ -1804,7 +1805,7 @@ static void tun_detach_filter(struct tun for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); - sk_detach_filter(tfile->socket.sk); + __sk_detach_filter(tfile->socket.sk, lockdep_rtnl_is_held()); } tun->filter_attached = false; @@ -1817,7 +1818,8 @@ static int tun_attach_filter(struct tun_ for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); - ret = sk_attach_filter(&tun->fprog, tfile->socket.sk); + ret = __sk_attach_filter(&tun->fprog, tfile->socket.sk, + lockdep_rtnl_is_held()); if (ret) { tun_detach_filter(tun, i); return ret; --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -446,8 +446,12 @@ int bpf_prog_create_from_user(struct bpf void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); +int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk, + bool locked); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_detach_filter(struct sock *sk); +int __sk_detach_filter(struct sock *sk, bool locked); + int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1139,7 +1139,8 @@ void bpf_prog_destroy(struct bpf_prog *f } EXPORT_SYMBOL_GPL(bpf_prog_destroy); -static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) +static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk, + bool locked) { struct sk_filter *fp, *old_fp; @@ -1155,10 +1156,8 @@ static int __sk_attach_prog(struct bpf_p return -ENOMEM; } - old_fp = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + old_fp = rcu_dereference_protected(sk->sk_filter, locked); rcu_assign_pointer(sk->sk_filter, fp); - if (old_fp) sk_filter_uncharge(sk, old_fp); @@ -1175,7 +1174,8 @@ static int __sk_attach_prog(struct bpf_p * occurs or there is insufficient memory for the filter a negative * errno code is returned. On success the return is zero. */ -int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk, + bool locked) { unsigned int fsize = bpf_classic_proglen(fprog); unsigned int bpf_fsize = bpf_prog_size(fprog->len); @@ -1213,7 +1213,7 @@ int sk_attach_filter(struct sock_fprog * if (IS_ERR(prog)) return PTR_ERR(prog); - err = __sk_attach_prog(prog, sk); + err = __sk_attach_prog(prog, sk, locked); if (err < 0) { __bpf_prog_release(prog); return err; @@ -1221,7 +1221,12 @@ int sk_attach_filter(struct sock_fprog * return 0; } -EXPORT_SYMBOL_GPL(sk_attach_filter); +EXPORT_SYMBOL_GPL(__sk_attach_filter); + +int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +{ + return __sk_attach_filter(fprog, sk, sock_owned_by_user(sk)); +} int sk_attach_bpf(u32 ufd, struct sock *sk) { @@ -1240,7 +1245,7 @@ int sk_attach_bpf(u32 ufd, struct sock * return -EINVAL; } - err = __sk_attach_prog(prog, sk); + err = __sk_attach_prog(prog, sk, sock_owned_by_user(sk)); if (err < 0) { bpf_prog_put(prog); return err; @@ -1913,7 +1918,7 @@ static int __init register_sk_filter_ops } late_initcall(register_sk_filter_ops); -int sk_detach_filter(struct sock *sk) +int __sk_detach_filter(struct sock *sk, bool locked) { int ret = -ENOENT; struct sk_filter *filter; @@ -1921,8 +1926,7 @@ int sk_detach_filter(struct sock *sk) if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; - filter = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + filter = rcu_dereference_protected(sk->sk_filter, locked); if (filter) { RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); @@ -1931,7 +1935,12 @@ int sk_detach_filter(struct sock *sk) return ret; } -EXPORT_SYMBOL_GPL(sk_detach_filter); +EXPORT_SYMBOL_GPL(__sk_detach_filter); + +int sk_detach_filter(struct sock *sk) +{ + return __sk_detach_filter(sk, sock_owned_by_user(sk)); +} int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len) -- To unsubscribe from this list: send the line "unsubscribe stable" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html