From f4979fcea7fd36d8e2f556abef86f80e0d5af1ba Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 12 Jul 2016 18:18:56 -0400 Subject: rose: limit sk_filter trim to payload Sockets can have a filter program attached that drops or trims incoming packets based on the filter program return value. Rose requires data packets to have at least ROSE_MIN_LEN bytes. It verifies this on arrival in rose_route_frame and unconditionally pulls the bytes in rose_recvmsg. The filter can trim packets to below this value in-between, causing pull to fail, leaving the partial header at the time of skb_copy_datagram_msg. Place a lower bound on the size to which sk_filter may trim packets by introducing sk_filter_trim_cap and call this for rose packets. Signed-off-by: Willem de Bruijn Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/filter.h | 6 +++++- net/core/filter.c | 10 +++++----- net/rose/rose_in.c | 3 ++- 3 files changed, 12 insertions(+), 7 deletions(-) diff --git a/include/linux/filter.h b/include/linux/filter.h index 6fc31ef1da2d..8f74f3d61894 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -467,7 +467,11 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) } #endif /* CONFIG_DEBUG_SET_MODULE_RONX */ -int sk_filter(struct sock *sk, struct sk_buff *skb); +int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); +static inline int sk_filter(struct sock *sk, struct sk_buff *skb) +{ + return sk_filter_trim_cap(sk, skb, 1); +} struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err); void bpf_prog_free(struct bpf_prog *fp); diff --git a/net/core/filter.c b/net/core/filter.c index c4b330c85c02..e759d90e8cef 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -53,9 +53,10 @@ #include /** - * sk_filter - run a packet through a socket filter + * sk_filter_trim_cap - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter + * @cap: limit on how short the eBPF program may trim the packet * * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller @@ -64,7 +65,7 @@ * be accepted or -EPERM if the packet should be tossed. * */ -int sk_filter(struct sock *sk, struct sk_buff *skb) +int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) { int err; struct sk_filter *filter; @@ -85,14 +86,13 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) filter = rcu_dereference(sk->sk_filter); if (filter) { unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb); - - err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; + err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM; } rcu_read_unlock(); return err; } -EXPORT_SYMBOL(sk_filter); +EXPORT_SYMBOL(sk_filter_trim_cap); static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c index 79c4abcfa6b4..0a6394754e81 100644 --- a/net/rose/rose_in.c +++ b/net/rose/rose_in.c @@ -164,7 +164,8 @@ static int rose_state3_machine(struct sock *sk, struct sk_buff *skb, int framety rose_frames_acked(sk, nr); if (ns == rose->vr) { rose_start_idletimer(sk); - if (sock_queue_rcv_skb(sk, skb) == 0) { + if (sk_filter_trim_cap(sk, skb, ROSE_MIN_LEN) == 0 && + __sock_queue_rcv_skb(sk, skb) == 0) { rose->vr = (rose->vr + 1) % ROSE_MODULUS; queued = 1; } else { -- cgit From 4f0c40d94461cfd23893a17335b2ab78ecb333c8 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 12 Jul 2016 18:18:57 -0400 Subject: dccp: limit sk_filter trim to payload Dccp verifies packet integrity, including length, at initial rcv in dccp_invalid_packet, later pulls headers in dccp_enqueue_skb. A call to sk_filter in-between can cause __skb_pull to wrap skb->len. skb_copy_datagram_msg interprets this as a negative value, so (correctly) fails with EFAULT. The negative length is reported in ioctl SIOCINQ or possibly in a DCCP_WARN in dccp_close. Introduce an sk_receive_skb variant that caps how small a filter program can trim packets, and call this in dccp with the header length. Excessively trimmed packets are now processed normally and queued for reception as 0B payloads. Fixes: 7c657876b63c ("[DCCP]: Initial implementation") Signed-off-by: Willem de Bruijn Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/sock.h | 8 +++++++- net/core/sock.c | 7 ++++--- net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 2 +- 4 files changed, 13 insertions(+), 6 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 649d2a8c17fc..ff5be7e8ddea 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1576,7 +1576,13 @@ static inline void sock_put(struct sock *sk) */ void sock_gen_put(struct sock *sk); -int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested); +int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, + unsigned int trim_cap); +static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, + const int nested) +{ + return __sk_receive_skb(sk, skb, nested, 1); +} static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { diff --git a/net/core/sock.c b/net/core/sock.c index b7f12639c26a..25dab8b60223 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -452,11 +452,12 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(sock_queue_rcv_skb); -int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) +int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, + const int nested, unsigned int trim_cap) { int rc = NET_RX_SUCCESS; - if (sk_filter(sk, skb)) + if (sk_filter_trim_cap(sk, skb, trim_cap)) goto discard_and_relse; skb->dev = NULL; @@ -492,7 +493,7 @@ discard_and_relse: kfree_skb(skb); goto out; } -EXPORT_SYMBOL(sk_receive_skb); +EXPORT_SYMBOL(__sk_receive_skb); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 25dd25b47d41..345a3aeb8c7e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -868,7 +868,7 @@ lookup: goto discard_and_relse; nf_reset(skb); - return sk_receive_skb(sk, skb, 1); + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4); no_dccp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index d176f4e66369..3ff137d9471d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -732,7 +732,7 @@ lookup: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - return sk_receive_skb(sk, skb, 1) ? -1 : 0; + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0; no_dccp_socket: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) -- cgit