Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752931AbcDZSn0 (ORCPT ); Tue, 26 Apr 2016 14:43:26 -0400 Received: from youngberry.canonical.com ([91.189.89.112]:56282 "EHLO youngberry.canonical.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752719AbcDZSSQ (ORCPT ); Tue, 26 Apr 2016 14:18:16 -0400 From: Kamal Mostafa To: linux-kernel@vger.kernel.org, stable@vger.kernel.org, kernel-team@lists.ubuntu.com Cc: Daniel Borkmann , "David S . Miller" , Kamal Mostafa Subject: [PATCH 4.2.y-ckt 20/93] tun, bpf: fix suspicious RCU usage in tun_{attach, detach}_filter Date: Tue, 26 Apr 2016 11:16:20 -0700 Message-Id: <1461694653-29506-21-git-send-email-kamal@canonical.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1461694653-29506-1-git-send-email-kamal@canonical.com> References: <1461694653-29506-1-git-send-email-kamal@canonical.com> X-Extended-Stable: 4.2 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 8000 Lines: 214 4.2.8-ckt9 -stable review patch. If anyone has any objections, please let me know. ---8<------------------------------------------------------------ From: Daniel Borkmann [ 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: [] 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] [] dump_stack+0x85/0xc8 [ 52.765784] [] lockdep_rcu_suspicious+0xd5/0x110 [ 52.765792] [] sk_detach_filter+0x82/0x90 [ 52.765801] [] tun_detach_filter+0x35/0x90 [tun] [ 52.765810] [] __tun_chr_ioctl+0x354/0x1130 [tun] [ 52.765818] [] ? selinux_file_ioctl+0x130/0x210 [ 52.765827] [] tun_chr_ioctl+0x13/0x20 [tun] [ 52.765834] [] do_vfs_ioctl+0x96/0x690 [ 52.765843] [] ? security_file_ioctl+0x43/0x60 [ 52.765850] [] SyS_ioctl+0x79/0x90 [ 52.765858] [] do_syscall_64+0x62/0x140 [ 52.765866] [] 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 Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller Signed-off-by: Kamal Mostafa --- drivers/net/tun.c | 8 +++++--- include/linux/filter.h | 4 ++++ net/core/filter.c | 33 +++++++++++++++++++++------------ 3 files changed, 30 insertions(+), 15 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 06a0394..6049086 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -621,7 +621,8 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte /* 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; } @@ -1803,7 +1804,7 @@ static void tun_detach_filter(struct tun_struct *tun, int n) 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; @@ -1816,7 +1817,8 @@ static int tun_attach_filter(struct tun_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; diff --git a/include/linux/filter.h b/include/linux/filter.h index 137b10c..4ae54cc 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -401,8 +401,12 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, 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); diff --git a/net/core/filter.c b/net/core/filter.c index 515b50b..762812f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1134,7 +1134,8 @@ void bpf_prog_destroy(struct bpf_prog *fp) } 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; @@ -1150,10 +1151,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) 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); @@ -1170,7 +1169,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) * 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); @@ -1208,7 +1208,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) 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; @@ -1216,7 +1216,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) 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) { @@ -1235,7 +1240,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) 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; @@ -1673,7 +1678,7 @@ static int __init register_sk_filter_ops(void) } 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; @@ -1681,8 +1686,7 @@ 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); @@ -1691,7 +1695,12 @@ 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) -- 2.7.4