From eb70db8756717b90c01ccc765fdefc4dd969fc74 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 1 Jul 2016 16:07:50 -0400 Subject: packet: Use symmetric hash for PACKET_FANOUT_HASH. People who use PACKET_FANOUT_HASH want a symmetric hash, meaning that they want packets going in both directions on a flow to hash to the same bucket. The core kernel SKB hash became non-symmetric when the ipv6 flow label and other entities were incorporated into the standard flow hash order to increase entropy. But there are no users of PACKET_FANOUT_HASH who want an assymetric hash, they all want a symmetric one. Therefore, use the flow dissector to compute a flat symmetric hash over only the protocol, addresses and ports. This hash does not get installed into and override the normal skb hash, so this change has no effect whatsoever on the rest of the stack. Reported-by: Eric Leblond Tested-by: Eric Leblond Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'net/core') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index a669dea146c6..61ad43f61c5e 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -651,6 +651,23 @@ void make_flow_keys_digest(struct flow_keys_digest *digest, } EXPORT_SYMBOL(make_flow_keys_digest); +static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; + +u32 __skb_get_hash_symmetric(struct sk_buff *skb) +{ + struct flow_keys keys; + + __flow_hash_secret_init(); + + memset(&keys, 0, sizeof(keys)); + __skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys, + NULL, 0, 0, 0, + FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + + return __flow_hash_from_keys(&keys, hashrnd); +} +EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); + /** * __skb_get_hash: calculate a flow hash * @skb: sk_buff to calculate flow hash from @@ -868,6 +885,29 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = { }, }; +static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { + { + .key_id = FLOW_DISSECTOR_KEY_CONTROL, + .offset = offsetof(struct flow_keys, control), + }, + { + .key_id = FLOW_DISSECTOR_KEY_BASIC, + .offset = offsetof(struct flow_keys, basic), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v4addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v6addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_PORTS, + .offset = offsetof(struct flow_keys, ports), + }, +}; + static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, @@ -889,6 +929,9 @@ static int __init init_default_flow_dissectors(void) skb_flow_dissector_init(&flow_keys_dissector, flow_keys_dissector_keys, ARRAY_SIZE(flow_keys_dissector_keys)); + skb_flow_dissector_init(&flow_keys_dissector_symmetric, + flow_keys_dissector_symmetric_keys, + ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); skb_flow_dissector_init(&flow_keys_buf_dissector, flow_keys_buf_dissector_keys, ARRAY_SIZE(flow_keys_buf_dissector_keys)); -- cgit v1.2.3-70-g09d2 From 82a31b9231f02d9c1b7b290a46999d517b0d312a Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 30 Jun 2016 10:15:22 -0700 Subject: net_sched: fix mirrored packets checksum Similar to commit 9b368814b336 ("net: fix bridge multicast packet checksum validation") we need to fixup the checksum for CHECKSUM_COMPLETE when pushing skb on RX path. Otherwise we get similar splats. Cc: Jamal Hadi Salim Cc: Tom Herbert Signed-off-by: Cong Wang Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/skbuff.h | 19 +++++++++++++++++++ net/core/skbuff.c | 18 ------------------ net/sched/act_mirred.c | 2 +- 3 files changed, 20 insertions(+), 19 deletions(-) (limited to 'net/core') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 24859d40acde..f39b37180c41 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2870,6 +2870,25 @@ static inline void skb_postpush_rcsum(struct sk_buff *skb, skb->csum = csum_partial(start, len, skb->csum); } +/** + * skb_push_rcsum - push skb and update receive checksum + * @skb: buffer to update + * @len: length of data pulled + * + * This function performs an skb_push on the packet and updates + * the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_push unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. + */ +static inline unsigned char *skb_push_rcsum(struct sk_buff *skb, + unsigned int len) +{ + skb_push(skb, len); + skb_postpush_rcsum(skb, skb->data, len); + return skb->data; +} + /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f2b77e549c03..eb12d2161fb2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3015,24 +3015,6 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, } EXPORT_SYMBOL_GPL(skb_append_pagefrags); -/** - * skb_push_rcsum - push skb and update receive checksum - * @skb: buffer to update - * @len: length of data pulled - * - * This function performs an skb_push on the packet and updates - * the CHECKSUM_COMPLETE checksum. It should be used on - * receive path processing instead of skb_push unless you know - * that the checksum difference is zero (e.g., a valid IP header) - * or you are setting ip_summed to CHECKSUM_NONE. - */ -static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len) -{ - skb_push(skb, len); - skb_postpush_rcsum(skb, skb->data, len); - return skb->data; -} - /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 128942bc9e42..1f5bd6ccbd2c 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -181,7 +181,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, if (!(at & AT_EGRESS)) { if (m->tcfm_ok_push) - skb_push(skb2, skb->mac_len); + skb_push_rcsum(skb2, skb->mac_len); } /* mirror is always swallowed */ -- cgit v1.2.3-70-g09d2 From 779f1edec664a7b32b71f7b4702e085a08d60592 Mon Sep 17 00:00:00 2001 From: Soheil Hassas Yeganeh Date: Mon, 11 Jul 2016 16:51:26 -0400 Subject: sock: ignore SCM_RIGHTS and SCM_CREDENTIALS in __sock_cmsg_send Sergei Trofimovich reported that pulse audio sends SCM_CREDENTIALS as a control message to TCP. Since __sock_cmsg_send does not support SCM_RIGHTS and SCM_CREDENTIALS, it returns an error and hence breaks pulse audio over TCP. SCM_RIGHTS and SCM_CREDENTIALS are sent on the SOL_SOCKET layer but they semantically belong to SOL_UNIX. Since all cmsg-processing functions including sock_cmsg_send ignore control messages of other layers, it is best to ignore SCM_RIGHTS and SCM_CREDENTIALS for consistency (and also for fixing pulse audio over TCP). Fixes: c14ac9451c34 ("sock: enable timestamping using control messages") Signed-off-by: Soheil Hassas Yeganeh Reported-by: Sergei Trofimovich Tested-by: Sergei Trofimovich Cc: Eric Dumazet Cc: Willem de Bruijn Signed-off-by: David S. Miller --- net/core/sock.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/core') diff --git a/net/core/sock.c b/net/core/sock.c index 08bf97eceeb3..b7f12639c26a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1938,6 +1938,10 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; sockc->tsflags |= tsflags; break; + /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ + case SCM_RIGHTS: + case SCM_CREDENTIALS: + break; default: return -EINVAL; } -- cgit v1.2.3-70-g09d2 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(-) (limited to 'net/core') 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 v1.2.3-70-g09d2 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(-) (limited to 'net/core') 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 v1.2.3-70-g09d2