summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/appletalk/ddp.c1
-rw-r--r--net/bridge/netfilter/ebtables.c3
-rw-r--r--net/ipv4/esp4.c20
-rw-r--r--net/ipv4/esp4_offload.c8
-rw-r--r--net/ipv4/ip_output.c1
-rw-r--r--net/ipv4/ip_vti.c9
-rw-r--r--net/ipv4/route.c32
-rw-r--r--net/ipv4/sysctl_net_ipv4.c5
-rw-r--r--net/ipv4/tcp_ipv4.c13
-rw-r--r--net/ipv4/udp_offload.c16
-rw-r--r--net/ipv4/xfrm4_policy.c24
-rw-r--r--net/ipv6/addrlabel.c2
-rw-r--r--net/ipv6/esp6_offload.c8
-rw-r--r--net/ipv6/ip6_fib.c4
-rw-r--r--net/ipv6/ip6_flowlabel.c22
-rw-r--r--net/ipv6/route.c70
-rw-r--r--net/ipv6/xfrm6_tunnel.c6
-rw-r--r--net/key/af_key.c4
-rw-r--r--net/l2tp/l2tp_core.c10
-rw-r--r--net/mac80211/debugfs_netdev.c2
-rw-r--r--net/mac80211/ht.c5
-rw-r--r--net/mac80211/iface.c3
-rw-r--r--net/ncsi/ncsi-rsp.c6
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c2
-rw-r--r--net/netfilter/nf_conntrack_core.c43
-rw-r--r--net/netfilter/nf_conntrack_netlink.c34
-rw-r--r--net/netfilter/nf_conntrack_proto.c2
-rw-r--r--net/netfilter/nf_conntrack_proto_icmp.c93
-rw-r--r--net/netfilter/nf_conntrack_proto_icmpv6.c52
-rw-r--r--net/netfilter/nf_nat_core.c11
-rw-r--r--net/netfilter/nf_tables_api.c2
-rw-r--r--net/netfilter/nfnetlink_log.c2
-rw-r--r--net/netfilter/nfnetlink_queue.c2
-rw-r--r--net/netfilter/xt_time.c23
-rw-r--r--net/netlink/genetlink.c4
-rw-r--r--net/packet/af_packet.c37
-rw-r--r--net/rds/ib_fmr.c11
-rw-r--r--net/rds/ib_rdma.c3
-rw-r--r--net/rds/ib_recv.c8
-rw-r--r--net/rose/rose_loopback.c27
-rw-r--r--net/rxrpc/call_object.c32
-rw-r--r--net/rxrpc/input.c12
-rw-r--r--net/rxrpc/local_object.c3
-rw-r--r--net/sctp/sm_sideeffect.c29
-rw-r--r--net/sctp/sm_statefuns.c35
-rw-r--r--net/sunrpc/cache.c3
-rw-r--r--net/sunrpc/clnt.c7
-rw-r--r--net/tls/tls_device.c43
-rw-r--r--net/tls/tls_device_fallback.c16
-rw-r--r--net/tls/tls_main.c5
-rw-r--r--net/tls/tls_sw.c3
-rw-r--r--net/wireless/reg.c5
-rw-r--r--net/xfrm/xfrm_interface.c17
-rw-r--r--net/xfrm/xfrm_policy.c2
-rw-r--r--net/xfrm/xfrm_state.c2
-rw-r--r--net/xfrm/xfrm_user.c16
56 files changed, 531 insertions, 329 deletions
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 709d2542f729..dbe8b1993be9 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1920,6 +1920,7 @@ static int __init atalk_init(void)
ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv);
if (!ddp_dl) {
pr_crit("Unable to register DDP with SNAP.\n");
+ rc = -ENOMEM;
goto out_sock;
}
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index eb15891f8b9f..3cad01ac64e4 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -2032,7 +2032,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32,
if (match_kern)
match_kern->match_size = ret;
- if (WARN_ON(type == EBT_COMPAT_TARGET && size_left))
+ /* rule should have no remaining data after target */
+ if (type == EBT_COMPAT_TARGET && size_left)
return -EINVAL;
match32 = (struct compat_ebt_entry_mwt *) buf;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 10e809b296ec..fb065a8937ea 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -226,7 +226,7 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
tail[plen - 1] = proto;
}
-static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
+static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
{
int encap_type;
struct udphdr *uh;
@@ -234,6 +234,7 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru
__be16 sport, dport;
struct xfrm_encap_tmpl *encap = x->encap;
struct ip_esp_hdr *esph = esp->esph;
+ unsigned int len;
spin_lock_bh(&x->lock);
sport = encap->encap_sport;
@@ -241,11 +242,14 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru
encap_type = encap->encap_type;
spin_unlock_bh(&x->lock);
+ len = skb->len + esp->tailen - skb_transport_offset(skb);
+ if (len + sizeof(struct iphdr) >= IP_MAX_MTU)
+ return -EMSGSIZE;
+
uh = (struct udphdr *)esph;
uh->source = sport;
uh->dest = dport;
- uh->len = htons(skb->len + esp->tailen
- - skb_transport_offset(skb));
+ uh->len = htons(len);
uh->check = 0;
switch (encap_type) {
@@ -262,6 +266,8 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru
*skb_mac_header(skb) = IPPROTO_UDP;
esp->esph = esph;
+
+ return 0;
}
int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
@@ -275,8 +281,12 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
int tailen = esp->tailen;
/* this is non-NULL only with UDP Encapsulation */
- if (x->encap)
- esp_output_udp_encap(x, skb, esp);
+ if (x->encap) {
+ int err = esp_output_udp_encap(x, skb, esp);
+
+ if (err < 0)
+ return err;
+ }
if (!skb_cloned(skb)) {
if (tailen <= skb_tailroom(skb)) {
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 8756e0e790d2..d3170a8001b2 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -52,13 +52,13 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
goto out;
if (sp->len == XFRM_MAX_DEPTH)
- goto out;
+ goto out_reset;
x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
(xfrm_address_t *)&ip_hdr(skb)->daddr,
spi, IPPROTO_ESP, AF_INET);
if (!x)
- goto out;
+ goto out_reset;
sp->xvec[sp->len++] = x;
sp->olen++;
@@ -66,7 +66,7 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
xo = xfrm_offload(skb);
if (!xo) {
xfrm_state_put(x);
- goto out;
+ goto out_reset;
}
}
@@ -82,6 +82,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
xfrm_input(skb, IPPROTO_ESP, spi, -2);
return ERR_PTR(-EINPROGRESS);
+out_reset:
+ secpath_reset(skb);
out:
skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c80188875f39..e8bb2e85c5a4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -519,6 +519,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->pkt_type = from->pkt_type;
to->priority = from->priority;
to->protocol = from->protocol;
+ to->skb_iif = from->skb_iif;
skb_dst_drop(to);
skb_dst_copy(to, from);
to->dev = from->dev;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 68a21bf75dd0..35d8346742e2 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -646,10 +646,8 @@ static int __init vti_init(void)
msg = "ipip tunnel";
err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
- if (err < 0) {
- pr_info("%s: cant't register tunnel\n",__func__);
+ if (err < 0)
goto xfrm_tunnel_failed;
- }
msg = "netlink interface";
err = rtnl_link_register(&vti_link_ops);
@@ -659,9 +657,9 @@ static int __init vti_init(void)
return err;
rtnl_link_failed:
- xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
-xfrm_tunnel_failed:
xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+xfrm_tunnel_failed:
+ xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
xfrm_proto_comp_failed:
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
@@ -676,6 +674,7 @@ pernet_dev_failed:
static void __exit vti_fini(void)
{
rtnl_link_unregister(&vti_link_ops);
+ xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 88ce038dd495..6fdf1c195d8e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1183,25 +1183,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
return dst;
}
-static void ipv4_link_failure(struct sk_buff *skb)
+static void ipv4_send_dest_unreach(struct sk_buff *skb)
{
struct ip_options opt;
- struct rtable *rt;
int res;
/* Recompile ip options since IPCB may not be valid anymore.
+ * Also check we have a reasonable ipv4 header.
*/
- memset(&opt, 0, sizeof(opt));
- opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) ||
+ ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5)
+ return;
- rcu_read_lock();
- res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
- rcu_read_unlock();
+ memset(&opt, 0, sizeof(opt));
+ if (ip_hdr(skb)->ihl > 5) {
+ if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4))
+ return;
+ opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
- if (res)
- return;
+ rcu_read_lock();
+ res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+ rcu_read_unlock();
+ if (res)
+ return;
+ }
__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
+}
+
+static void ipv4_link_failure(struct sk_buff *skb)
+{
+ struct rtable *rt;
+
+ ipv4_send_dest_unreach(skb);
rt = skb_rtable(skb);
if (rt)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index ba0fc4b18465..eeb4041fa5f9 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -49,6 +49,7 @@ static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
static int comp_sack_nr_max = 255;
static u32 u32_max_div_HZ = UINT_MAX / HZ;
+static int one_day_secs = 24 * 3600;
/* obsolete */
static int sysctl_tcp_low_latency __read_mostly;
@@ -1151,7 +1152,9 @@ static struct ctl_table ipv4_net_table[] = {
.data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one_day_secs
},
{
.procname = "tcp_autocorking",
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2f8039a26b08..a2896944aa37 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1673,7 +1673,9 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq ||
TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield ||
((TCP_SKB_CB(tail)->tcp_flags |
- TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_URG) ||
+ TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) ||
+ !((TCP_SKB_CB(tail)->tcp_flags &
+ TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) ||
((TCP_SKB_CB(tail)->tcp_flags ^
TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
#ifdef CONFIG_TLS_DEVICE
@@ -1692,6 +1694,15 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))
TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq;
+ /* We have to update both TCP_SKB_CB(tail)->tcp_flags and
+ * thtail->fin, so that the fast path in tcp_rcv_established()
+ * is not entered if we append a packet with a FIN.
+ * SYN, RST, URG are not present.
+ * ACK is set on both packets.
+ * PSH : we do not really care in TCP stack,
+ * at least for 'GRO' packets.
+ */
+ thtail->fin |= th->fin;
TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
if (TCP_SKB_CB(skb)->has_rxtstamp) {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 64f9715173ac..065334b41d57 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -352,6 +352,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
struct sk_buff *pp = NULL;
struct udphdr *uh2;
struct sk_buff *p;
+ unsigned int ulen;
/* requires non zero csum, for symmetry with GSO */
if (!uh->check) {
@@ -359,6 +360,12 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
return NULL;
}
+ /* Do not deal with padded or malicious packets, sorry ! */
+ ulen = ntohs(uh->len);
+ if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) {
+ NAPI_GRO_CB(skb)->flush = 1;
+ return NULL;
+ }
/* pull encapsulating udp header */
skb_gro_pull(skb, sizeof(struct udphdr));
skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
@@ -377,13 +384,14 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
/* Terminate the flow on len mismatch or if it grow "too much".
* Under small packet flood GRO count could elsewhere grow a lot
- * leading to execessive truesize values
+ * leading to excessive truesize values.
+ * On len mismatch merge the first packet shorter than gso_size,
+ * otherwise complete the GRO packet.
*/
- if (!skb_gro_receive(p, skb) &&
+ if (ulen > ntohs(uh2->len) || skb_gro_receive(p, skb) ||
+ ulen != ntohs(uh2->len) ||
NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
pp = p;
- else if (uh->len != uh2->len)
- pp = p;
return pp;
}
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index d73a6d6652f6..2b144b92ae46 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -111,7 +111,8 @@ static void
_decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
{
const struct iphdr *iph = ip_hdr(skb);
- u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
+ int ihl = iph->ihl;
+ u8 *xprth = skb_network_header(skb) + ihl * 4;
struct flowi4 *fl4 = &fl->u.ip4;
int oif = 0;
@@ -122,6 +123,11 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
fl4->flowi4_mark = skb->mark;
fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
+ fl4->flowi4_proto = iph->protocol;
+ fl4->daddr = reverse ? iph->saddr : iph->daddr;
+ fl4->saddr = reverse ? iph->daddr : iph->saddr;
+ fl4->flowi4_tos = iph->tos;
+
if (!ip_is_fragment(iph)) {
switch (iph->protocol) {
case IPPROTO_UDP:
@@ -133,7 +139,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be16 *ports;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
ports = (__be16 *)xprth;
fl4->fl4_sport = ports[!!reverse];
@@ -146,7 +152,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
pskb_may_pull(skb, xprth + 2 - skb->data)) {
u8 *icmp;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
icmp = xprth;
fl4->fl4_icmp_type = icmp[0];
@@ -159,7 +165,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be32 *ehdr;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
ehdr = (__be32 *)xprth;
fl4->fl4_ipsec_spi = ehdr[0];
@@ -171,7 +177,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
pskb_may_pull(skb, xprth + 8 - skb->data)) {
__be32 *ah_hdr;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
ah_hdr = (__be32 *)xprth;
fl4->fl4_ipsec_spi = ah_hdr[1];
@@ -183,7 +189,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be16 *ipcomp_hdr;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
ipcomp_hdr = (__be16 *)xprth;
fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
@@ -196,7 +202,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
__be16 *greflags;
__be32 *gre_hdr;
- xprth = skb_network_header(skb) + iph->ihl * 4;
+ xprth = skb_network_header(skb) + ihl * 4;
greflags = (__be16 *)xprth;
gre_hdr = (__be32 *)xprth;
@@ -213,10 +219,6 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
break;
}
}
- fl4->flowi4_proto = iph->protocol;
- fl4->daddr = reverse ? iph->saddr : iph->daddr;
- fl4->saddr = reverse ? iph->daddr : iph->saddr;
- fl4->flowi4_tos = iph->tos;
}
static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index d43d076c98f5..1766325423b5 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -476,7 +476,7 @@ static int ip6addrlbl_valid_dump_req(const struct nlmsghdr *nlh,
}
if (nlmsg_attrlen(nlh, sizeof(*ifal))) {
- NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump requewst");
+ NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump request");
return -EINVAL;
}
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index d46b4eb645c2..cb99f6fb79b7 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -74,13 +74,13 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
goto out;
if (sp->len == XFRM_MAX_DEPTH)
- goto out;
+ goto out_reset;
x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
(xfrm_address_t *)&ipv6_hdr(skb)->daddr,
spi, IPPROTO_ESP, AF_INET6);
if (!x)
- goto out;
+ goto out_reset;
sp->xvec[sp->len++] = x;
sp->olen++;
@@ -88,7 +88,7 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
xo = xfrm_offload(skb);
if (!xo) {
xfrm_state_put(x);
- goto out;
+ goto out_reset;
}
}
@@ -109,6 +109,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
xfrm_input(skb, IPPROTO_ESP, spi, -2);
return ERR_PTR(-EINPROGRESS);
+out_reset:
+ secpath_reset(skb);
out:
skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 6613d8dbb0e5..91247a6fc67f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -921,9 +921,7 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
if (pcpu_rt) {
struct fib6_info *from;
- from = rcu_dereference_protected(pcpu_rt->from,
- lockdep_is_held(&table->tb6_lock));
- rcu_assign_pointer(pcpu_rt->from, NULL);
+ from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
fib6_info_release(from);
}
}
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index cb54a8a3c273..be5f3d7ceb96 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -94,15 +94,21 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label)
return fl;
}
+static void fl_free_rcu(struct rcu_head *head)
+{
+ struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu);
+
+ if (fl->share == IPV6_FL_S_PROCESS)
+ put_pid(fl->owner.pid);
+ kfree(fl->opt);
+ kfree(fl);
+}
+
static void fl_free(struct ip6_flowlabel *fl)
{
- if (fl) {
- if (fl->share == IPV6_FL_S_PROCESS)
- put_pid(fl->owner.pid);
- kfree(fl->opt);
- kfree_rcu(fl, rcu);
- }
+ if (fl)
+ call_rcu(&fl->rcu, fl_free_rcu);
}
static void fl_release(struct ip6_flowlabel *fl)
@@ -633,9 +639,9 @@ recheck:
if (fl1->share == IPV6_FL_S_EXCL ||
fl1->share != fl->share ||
((fl1->share == IPV6_FL_S_PROCESS) &&
- (fl1->owner.pid == fl->owner.pid)) ||
+ (fl1->owner.pid != fl->owner.pid)) ||
((fl1->share == IPV6_FL_S_USER) &&
- uid_eq(fl1->owner.uid, fl->owner.uid)))
+ !uid_eq(fl1->owner.uid, fl->owner.uid)))
goto release;
err = -ENOMEM;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7178e32eb15d..0520aca3354b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -379,11 +379,8 @@ static void ip6_dst_destroy(struct dst_entry *dst)
in6_dev_put(idev);
}
- rcu_read_lock();
- from = rcu_dereference(rt->from);
- rcu_assign_pointer(rt->from, NULL);
+ from = xchg((__force struct fib6_info **)&rt->from, NULL);
fib6_info_release(from);
- rcu_read_unlock();
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -1288,9 +1285,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
/* purge completely the exception to allow releasing the held resources:
* some [sk] cache may keep the dst around for unlimited time
*/
- from = rcu_dereference_protected(rt6_ex->rt6i->from,
- lockdep_is_held(&rt6_exception_lock));
- rcu_assign_pointer(rt6_ex->rt6i->from, NULL);
+ from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
fib6_info_release(from);
dst_dev_put(&rt6_ex->rt6i->dst);
@@ -3397,11 +3392,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
rcu_read_lock();
from = rcu_dereference(rt->from);
- /* This fib6_info_hold() is safe here because we hold reference to rt
- * and rt already holds reference to fib6_info.
- */
- fib6_info_hold(from);
- rcu_read_unlock();
+ if (!from)
+ goto out;
nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL);
if (!nrt)
@@ -3413,10 +3405,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
- /* No need to remove rt from the exception table if rt is
- * a cached route because rt6_insert_exception() will
- * takes care of it
- */
+ /* rt6_insert_exception() will take care of duplicated exceptions */
if (rt6_insert_exception(nrt, from)) {
dst_release_immediate(&nrt->dst);
goto out;
@@ -3429,7 +3418,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
out:
- fib6_info_release(from);
+ rcu_read_unlock();
neigh_release(neigh);
}
@@ -3668,23 +3657,34 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
{
- int type;
struct dst_entry *dst = skb_dst(skb);
+ struct net *net = dev_net(dst->dev);
+ struct inet6_dev *idev;
+ int type;
+
+ if (netif_is_l3_master(skb->dev) &&
+ dst->dev == net->loopback_dev)
+ idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
+ else
+ idev = ip6_dst_idev(dst);
+
switch (ipstats_mib_noroutes) {
case IPSTATS_MIB_INNOROUTES:
type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
if (type == IPV6_ADDR_ANY) {
- IP6_INC_STATS(dev_net(dst->dev),
- __in6_dev_get_safely(skb->dev),
- IPSTATS_MIB_INADDRERRORS);
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS);
break;
}
/* FALLTHROUGH */
case IPSTATS_MIB_OUTNOROUTES:
- IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
- ipstats_mib_noroutes);
+ IP6_INC_STATS(net, idev, ipstats_mib_noroutes);
break;
}
+
+ /* Start over by dropping the dst for l3mdev case */
+ if (netif_is_l3_master(skb->dev))
+ skb_dst_drop(skb);
+
icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0);
kfree_skb(skb);
return 0;
@@ -5017,16 +5017,20 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
rcu_read_lock();
from = rcu_dereference(rt->from);
-
- if (fibmatch)
- err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif,
- RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, 0);
- else
- err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
- &fl6.saddr, iif, RTM_NEWROUTE,
- NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
- 0);
+ if (from) {
+ if (fibmatch)
+ err = rt6_fill_node(net, skb, from, NULL, NULL, NULL,
+ iif, RTM_NEWROUTE,
+ NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, 0);
+ else
+ err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
+ &fl6.saddr, iif, RTM_NEWROUTE,
+ NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, 0);
+ } else {
+ err = -ENETUNREACH;
+ }
rcu_read_unlock();
if (err < 0) {
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index bc65db782bfb..d9e5f6808811 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -345,7 +345,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net)
unsigned int i;
xfrm_flush_gc();
- xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
+ xfrm_state_flush(net, 0, false, true);
for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i]));
@@ -402,6 +402,10 @@ static void __exit xfrm6_tunnel_fini(void)
xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6);
xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6);
unregister_pernet_subsys(&xfrm6_tunnel_net_ops);
+ /* Someone maybe has gotten the xfrm6_tunnel_spi.
+ * So need to wait it.
+ */
+ rcu_barrier();
kmem_cache_destroy(xfrm6_tunnel_spi_kmem);
}
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 5651c29cb5bd..4af1e1d60b9f 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1951,8 +1951,10 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq)
if (rq->sadb_x_ipsecrequest_mode == 0)
return -EINVAL;
+ if (!xfrm_id_proto_valid(rq->sadb_x_ipsecrequest_proto))
+ return -EINVAL;
- t->id.proto = rq->sadb_x_ipsecrequest_proto; /* XXX check proto */
+ t->id.proto = rq->sadb_x_ipsecrequest_proto;
if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0)
return -EINVAL;
t->mode = mode;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index fed6becc5daf..52b5a2797c0c 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -169,8 +169,8 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
rcu_read_lock_bh();
list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (tunnel->tunnel_id == tunnel_id) {
- l2tp_tunnel_inc_refcount(tunnel);
+ if (tunnel->tunnel_id == tunnel_id &&
+ refcount_inc_not_zero(&tunnel->ref_count)) {
rcu_read_unlock_bh();
return tunnel;
@@ -190,8 +190,8 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
rcu_read_lock_bh();
list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (++count > nth) {
- l2tp_tunnel_inc_refcount(tunnel);
+ if (++count > nth &&
+ refcount_inc_not_zero(&tunnel->ref_count)) {
rcu_read_unlock_bh();
return tunnel;
}
@@ -909,7 +909,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
struct l2tp_tunnel *tunnel;
- tunnel = l2tp_tunnel(sk);
+ tunnel = rcu_dereference_sk_user_data(sk);
if (tunnel == NULL)
goto pass_up;
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index cff0fb3578c9..deb3faf08337 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -841,7 +841,7 @@ void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata)
dir = sdata->vif.debugfs_dir;
- if (!dir)
+ if (IS_ERR_OR_NULL(dir))
return;
sprintf(buf, "netdev:%s", sdata->name);
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index e03c46ac8e4d..c62101857b9b 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -112,8 +112,9 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
IEEE80211_HT_CAP_TX_STBC);
/* Allow user to configure RX STBC bits */
- if (ht_capa_mask->cap_info & IEEE80211_HT_CAP_RX_STBC)
- ht_cap->cap |= ht_capa->cap_info & IEEE80211_HT_CAP_RX_STBC;
+ if (ht_capa_mask->cap_info & cpu_to_le16(IEEE80211_HT_CAP_RX_STBC))
+ ht_cap->cap |= le16_to_cpu(ht_capa->cap_info) &
+ IEEE80211_HT_CAP_RX_STBC;
/* Allow user to decrease AMPDU factor */
if (ht_capa_mask->ampdu_params_info &
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 4a6ff1482a9f..02d2e6f11e93 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1908,6 +1908,9 @@ void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata)
list_del_rcu(&sdata->list);
mutex_unlock(&sdata->local->iflist_mtx);
+ if (sdata->vif.txq)
+ ieee80211_txq_purge(sdata->local, to_txq_info(sdata->vif.txq));
+
synchronize_rcu();
if (sdata->dev) {
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index dc07fcc7938e..802db01e3075 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <net/ncsi.h>
@@ -667,7 +668,10 @@ static int ncsi_rsp_handler_oem_bcm_gma(struct ncsi_request *nr)
ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
memcpy(saddr.sa_data, &rsp->data[BCM_MAC_ADDR_OFFSET], ETH_ALEN);
/* Increase mac address by 1 for BMC's address */
- saddr.sa_data[ETH_ALEN - 1]++;
+ eth_addr_inc((u8 *)saddr.sa_data);
+ if (!is_valid_ether_addr((const u8 *)saddr.sa_data))
+ return -ENXIO;
+
ret = ops->ndo_set_mac_address(ndev, &saddr);
if (ret < 0)
netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n");
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 43bbaa32b1d6..14457551bcb4 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1678,7 +1678,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
if (!cp) {
int v;
- if (!sysctl_schedule_icmp(ipvs))
+ if (ipip || !sysctl_schedule_icmp(ipvs))
return NF_ACCEPT;
if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph))
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 82bfbeef46af..2a714527cde1 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -25,6 +25,7 @@
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/jhash.h>
+#include <linux/siphash.h>
#include <linux/err.h>
#include <linux/percpu.h>
#include <linux/moduleparam.h>
@@ -449,6 +450,40 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
}
EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
+/* Generate a almost-unique pseudo-id for a given conntrack.
+ *
+ * intentionally doesn't re-use any of the seeds used for hash
+ * table location, we assume id gets exposed to userspace.
+ *
+ * Following nf_conn items do not change throughout lifetime
+ * of the nf_conn after it has been committed to main hash table:
+ *
+ * 1. nf_conn address
+ * 2. nf_conn->ext address
+ * 3. nf_conn->master address (normally NULL)
+ * 4. tuple
+ * 5. the associated net namespace
+ */
+u32 nf_ct_get_id(const struct nf_conn *ct)
+{
+ static __read_mostly siphash_key_t ct_id_seed;
+ unsigned long a, b, c, d;
+
+ net_get_random_once(&ct_id_seed, sizeof(ct_id_seed));
+
+ a = (unsigned long)ct;
+ b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct));
+ c = (unsigned long)ct->ext;
+ d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash),
+ &ct_id_seed);
+#ifdef CONFIG_64BIT
+ return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed);
+#else
+ return siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &ct_id_seed);
+#endif
+}
+EXPORT_SYMBOL_GPL(nf_ct_get_id);
+
static void
clean_from_lists(struct nf_conn *ct)
{
@@ -982,12 +1017,9 @@ __nf_conntrack_confirm(struct sk_buff *skb)
/* set conntrack timestamp, if enabled. */
tstamp = nf_conn_tstamp_find(ct);
- if (tstamp) {
- if (skb->tstamp == 0)
- __net_timestamp(skb);
+ if (tstamp)
+ tstamp->start = ktime_get_real_ns();
- tstamp->start = ktime_to_ns(skb->tstamp);
- }
/* Since the lookup is lockless, hash insertion must be done after
* starting the timer and setting the CONFIRMED bit. The RCU barriers
* guarantee that no other CPU can find the conntrack before the above
@@ -1350,6 +1382,7 @@ __nf_conntrack_alloc(struct net *net,
/* save hash for reusing when confirming */
*(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;
ct->status = 0;
+ ct->timeout = 0;
write_pnet(&ct->ct_net, net);
memset(&ct->__nfct_init_offset[0], 0,
offsetof(struct nf_conn, proto) -
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 66c596d287a5..d7f61b0547c6 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -29,6 +29,7 @@
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
+#include <linux/siphash.h>
#include <linux/netfilter.h>
#include <net/netlink.h>
@@ -485,7 +486,9 @@ nla_put_failure:
static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct)
{
- if (nla_put_be32(skb, CTA_ID, htonl((unsigned long)ct)))
+ __be32 id = (__force __be32)nf_ct_get_id(ct);
+
+ if (nla_put_be32(skb, CTA_ID, id))
goto nla_put_failure;
return 0;
@@ -1286,8 +1289,9 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl,
}
if (cda[CTA_ID]) {
- u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID]));
- if (id != (u32)(unsigned long)ct) {
+ __be32 id = nla_get_be32(cda[CTA_ID]);
+
+ if (id != (__force __be32)nf_ct_get_id(ct)) {
nf_ct_put(ct);
return -ENOENT;
}
@@ -2692,6 +2696,25 @@ nla_put_failure:
static const union nf_inet_addr any_addr;
+static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp)
+{
+ static __read_mostly siphash_key_t exp_id_seed;
+ unsigned long a, b, c, d;
+
+ net_get_random_once(&exp_id_seed, sizeof(exp_id_seed));
+
+ a = (unsigned long)exp;
+ b = (unsigned long)exp->helper;
+ c = (unsigned long)exp->master;
+ d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed);
+
+#ifdef CONFIG_64BIT
+ return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed);
+#else
+ return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed);
+#endif
+}
+
static int
ctnetlink_exp_dump_expect(struct sk_buff *skb,
const struct nf_conntrack_expect *exp)
@@ -2739,7 +2762,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
}
#endif
if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) ||
- nla_put_be32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)) ||
+ nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) ||
nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) ||
nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class)))
goto nla_put_failure;
@@ -3044,7 +3067,8 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl,
if (cda[CTA_EXPECT_ID]) {
__be32 id = nla_get_be32(cda[CTA_EXPECT_ID]);
- if (ntohl(id) != (u32)(unsigned long)exp) {
+
+ if (id != nf_expect_get_id(exp)) {
nf_ct_expect_put(exp);
return -ENOENT;
}
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index b9403a266a2e..37bb530d848f 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -55,7 +55,7 @@ void nf_l4proto_log_invalid(const struct sk_buff *skb,
struct va_format vaf;
va_list args;
- if (net->ct.sysctl_log_invalid != protonum ||
+ if (net->ct.sysctl_log_invalid != protonum &&
net->ct.sysctl_log_invalid != IPPROTO_RAW)
return;
diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c
index 7df477996b16..9becac953587 100644
--- a/net/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/netfilter/nf_conntrack_proto_icmp.c
@@ -103,49 +103,94 @@ int nf_conntrack_icmp_packet(struct nf_conn *ct,
return NF_ACCEPT;
}
-/* Returns conntrack if it dealt with ICMP, and filled in skb fields */
-static int
-icmp_error_message(struct nf_conn *tmpl, struct sk_buff *skb,
- const struct nf_hook_state *state)
+/* Check inner header is related to any of the existing connections */
+int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb,
+ unsigned int dataoff,
+ const struct nf_hook_state *state,
+ u8 l4proto, union nf_inet_addr *outer_daddr)
{
struct nf_conntrack_tuple innertuple, origtuple;
const struct nf_conntrack_tuple_hash *h;
const struct nf_conntrack_zone *zone;
enum ip_conntrack_info ctinfo;
struct nf_conntrack_zone tmp;
+ union nf_inet_addr *ct_daddr;
+ enum ip_conntrack_dir dir;
+ struct nf_conn *ct;
WARN_ON(skb_nfct(skb));
zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
/* Are they talking about one of our connections? */
- if (!nf_ct_get_tuplepr(skb,
- skb_network_offset(skb) + ip_hdrlen(skb)
- + sizeof(struct icmphdr),
- PF_INET, state->net, &origtuple)) {
- pr_debug("icmp_error_message: failed to get tuple\n");
+ if (!nf_ct_get_tuplepr(skb, dataoff,
+ state->pf, state->net, &origtuple))
return -NF_ACCEPT;
- }
/* Ordinarily, we'd expect the inverted tupleproto, but it's
been preserved inside the ICMP. */
- if (!nf_ct_invert_tuple(&innertuple, &origtuple)) {
- pr_debug("icmp_error_message: no match\n");
+ if (!nf_ct_invert_tuple(&innertuple, &origtuple))
return -NF_ACCEPT;
- }
-
- ctinfo = IP_CT_RELATED;
h = nf_conntrack_find_get(state->net, zone, &innertuple);
- if (!h) {
- pr_debug("icmp_error_message: no match\n");
+ if (!h)
+ return -NF_ACCEPT;
+
+ /* Consider: A -> T (=This machine) -> B
+ * Conntrack entry will look like this:
+ * Original: A->B
+ * Reply: B->T (SNAT case) OR A
+ *
+ * When this function runs, we got packet that looks like this:
+ * iphdr|icmphdr|inner_iphdr|l4header (tcp, udp, ..).
+ *
+ * Above nf_conntrack_find_get() makes lookup based on inner_hdr,
+ * so we should expect that destination of the found connection
+ * matches outer header destination address.
+ *
+ * In above example, we can consider these two cases:
+ * 1. Error coming in reply direction from B or M (middle box) to
+ * T (SNAT case) or A.
+ * Inner saddr will be B, dst will be T or A.
+ * The found conntrack will be reply tuple (B->T/A).
+ * 2. Error coming in original direction from A or M to B.
+ * Inner saddr will be A, inner daddr will be B.
+ * The found conntrack will be original tuple (A->B).
+ *
+ * In both cases, conntrack[dir].dst == inner.dst.
+ *
+ * A bogus packet could look like this:
+ * Inner: B->T
+ * Outer: B->X (other machine reachable by T).
+ *
+ * In this case, lookup yields connection A->B and will
+ * set packet from B->X as *RELATED*, even though no connection
+ * from X was ever seen.
+ */
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ dir = NF_CT_DIRECTION(h);
+ ct_daddr = &ct->tuplehash[dir].tuple.dst.u3;
+ if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) {
+ if (state->pf == AF_INET) {
+ nf_l4proto_log_invalid(skb, state->net, state->pf,
+ l4proto,
+ "outer daddr %pI4 != inner %pI4",
+ &outer_daddr->ip, &ct_daddr->ip);
+ } else if (state->pf == AF_INET6) {
+ nf_l4proto_log_invalid(skb, state->net, state->pf,
+ l4proto,
+ "outer daddr %pI6 != inner %pI6",
+ &outer_daddr->ip6, &ct_daddr->ip6);
+ }
+ nf_ct_put(ct);
return -NF_ACCEPT;
}
- if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
+ ctinfo = IP_CT_RELATED;
+ if (dir == IP_CT_DIR_REPLY)
ctinfo += IP_CT_IS_REPLY;
/* Update skb to refer to this connection */
- nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
+ nf_ct_set(skb, ct, ctinfo);
return NF_ACCEPT;
}
@@ -162,11 +207,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
struct sk_buff *skb, unsigned int dataoff,
const struct nf_hook_state *state)
{
+ union nf_inet_addr outer_daddr;
const struct icmphdr *icmph;
struct icmphdr _ih;
/* Not enough header? */
- icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih);
+ icmph = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
if (icmph == NULL) {
icmp_error_log(skb, state, "short packet");
return -NF_ACCEPT;
@@ -199,7 +245,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
icmph->type != ICMP_REDIRECT)
return NF_ACCEPT;
- return icmp_error_message(tmpl, skb, state);
+ memset(&outer_daddr, 0, sizeof(outer_daddr));
+ outer_daddr.ip = ip_hdr(skb)->daddr;
+
+ dataoff += sizeof(*icmph);
+ return nf_conntrack_inet_error(tmpl, skb, dataoff, state,
+ IPPROTO_ICMP, &outer_daddr);
}
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c
index bec4a3211658..c63ee3612855 100644
--- a/net/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/netfilter/nf_conntrack_proto_icmpv6.c
@@ -123,51 +123,6 @@ int nf_conntrack_icmpv6_packet(struct nf_conn *ct,
return NF_ACCEPT;
}
-static int
-icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
- struct sk_buff *skb,
- unsigned int icmp6off)
-{
- struct nf_conntrack_tuple intuple, origtuple;
- const struct nf_conntrack_tuple_hash *h;
- enum ip_conntrack_info ctinfo;
- struct nf_conntrack_zone tmp;
-
- WARN_ON(skb_nfct(skb));
-
- /* Are they talking about one of our connections? */
- if (!nf_ct_get_tuplepr(skb,
- skb_network_offset(skb)
- + sizeof(struct ipv6hdr)
- + sizeof(struct icmp6hdr),
- PF_INET6, net, &origtuple)) {
- pr_debug("icmpv6_error: Can't get tuple\n");
- return -NF_ACCEPT;
- }
-
- /* Ordinarily, we'd expect the inverted tupleproto, but it's
- been preserved inside the ICMP. */
- if (!nf_ct_invert_tuple(&intuple, &origtuple)) {
- pr_debug("icmpv6_error: Can't invert tuple\n");
- return -NF_ACCEPT;
- }
-
- ctinfo = IP_CT_RELATED;
-
- h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp),
- &intuple);
- if (!h) {
- pr_debug("icmpv6_error: no match\n");
- return -NF_ACCEPT;
- } else {
- if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
- ctinfo += IP_CT_IS_REPLY;
- }
-
- /* Update skb to refer to this connection */
- nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
- return NF_ACCEPT;
-}
static void icmpv6_error_log(const struct sk_buff *skb,
const struct nf_hook_state *state,
@@ -182,6 +137,7 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl,
unsigned int dataoff,
const struct nf_hook_state *state)
{
+ union nf_inet_addr outer_daddr;
const struct icmp6hdr *icmp6h;
struct icmp6hdr _ih;
int type;
@@ -210,7 +166,11 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl,
if (icmp6h->icmp6_type >= 128)
return NF_ACCEPT;
- return icmpv6_error_message(state->net, tmpl, skb, dataoff);
+ memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr,
+ sizeof(outer_daddr.ip6));
+ dataoff += sizeof(*icmp6h);
+ return nf_conntrack_inet_error(tmpl, skb, dataoff, state,
+ IPPROTO_ICMPV6, &outer_daddr);
}
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index af7dc6537758..000952719adf 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -415,9 +415,14 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
case IPPROTO_ICMPV6:
/* id is same for either direction... */
keyptr = &tuple->src.u.icmp.id;
- min = range->min_proto.icmp.id;
- range_size = ntohs(range->max_proto.icmp.id) -
- ntohs(range->min_proto.icmp.id) + 1;
+ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
+ min = 0;
+ range_size = 65536;
+ } else {
+ min = ntohs(range->min_proto.icmp.id);
+ range_size = ntohs(range->max_proto.icmp.id) -
+ ntohs(range->min_proto.icmp.id) + 1;
+ }
goto find_free_id;
#if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE)
case IPPROTO_GRE:
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ef7772e976cc..1606eaa5ae0d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1545,7 +1545,7 @@ static int nft_chain_parse_hook(struct net *net,
if (IS_ERR(type))
return PTR_ERR(type);
}
- if (!(type->hook_mask & (1 << hook->num)))
+ if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num)))
return -EOPNOTSUPP;
if (type->type == NFT_CHAIN_T_NAT &&
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index b1f9c5303f02..0b3347570265 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -540,7 +540,7 @@ __build_packet_message(struct nfnl_log_net *log,
goto nla_put_failure;
}
- if (skb->tstamp) {
+ if (hooknum <= NF_INET_FORWARD && skb->tstamp) {
struct nfulnl_msg_packet_timestamp ts;
struct timespec64 kts = ktime_to_timespec64(skb->tstamp);
ts.sec = cpu_to_be64(kts.tv_sec);
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 0dcc3592d053..e057b2961d31 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -582,7 +582,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
if (nfqnl_put_bridge(entry, skb) < 0)
goto nla_put_failure;
- if (entskb->tstamp) {
+ if (entry->state.hook <= NF_INET_FORWARD && entskb->tstamp) {
struct nfqnl_msg_packet_timestamp ts;
struct timespec64 kts = ktime_to_timespec64(entskb->tstamp);
diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c
index c13bcd0ab491..8dbb4d48f2ed 100644
--- a/net/netfilter/xt_time.c
+++ b/net/netfilter/xt_time.c
@@ -163,19 +163,24 @@ time_mt(const struct sk_buff *skb, struct xt_action_param *par)
s64 stamp;
/*
- * We cannot use get_seconds() instead of __net_timestamp() here.
+ * We need real time here, but we can neither use skb->tstamp
+ * nor __net_timestamp().
+ *
+ * skb->tstamp and skb->skb_mstamp_ns overlap, however, they
+ * use different clock types (real vs monotonic).
+ *
* Suppose you have two rules:
- * 1. match before 13:00
- * 2. match after 13:00
+ * 1. match before 13:00
+ * 2. match after 13:00
+ *
* If you match against processing time (get_seconds) it
* may happen that the same packet matches both rules if
- * it arrived at the right moment before 13:00.
+ * it arrived at the right moment before 13:00, so it would be
+ * better to check skb->tstamp and set it via __net_timestamp()
+ * if needed. This however breaks outgoing packets tx timestamp,
+ * and causes them to get delayed forever by fq packet scheduler.
*/
- if (skb->tstamp == 0)
- __net_timestamp((struct sk_buff *)skb);
-
- stamp = ktime_to_ns(skb->tstamp);
- stamp = div_s64(stamp, NSEC_PER_SEC);
+ stamp = get_seconds();
if (info->flags & XT_TIME_LOCAL_TZ)
/* Adjust for local timezone */
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index f0ec068e1d02..cb69d35c8e6a 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -362,8 +362,8 @@ int genl_register_family(struct genl_family *family)
} else
family->attrbuf = NULL;
- family->id = idr_alloc(&genl_fam_idr, family,
- start, end + 1, GFP_KERNEL);
+ family->id = idr_alloc_cyclic(&genl_fam_idr, family,
+ start, end + 1, GFP_KERNEL);
if (family->id < 0) {
err = family->id;
goto errout_free;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9419c5cf4de5..9b81813dd16a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2602,8 +2602,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
void *ph;
DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name);
bool need_wait = !(msg->msg_flags & MSG_DONTWAIT);
+ unsigned char *addr = NULL;
int tp_len, size_max;
- unsigned char *addr;
void *data;
int len_sum = 0;
int status = TP_STATUS_AVAILABLE;
@@ -2614,7 +2614,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
if (likely(saddr == NULL)) {
dev = packet_cached_dev_get(po);
proto = po->num;
- addr = NULL;
} else {
err = -EINVAL;
if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -2624,10 +2623,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
sll_addr)))
goto out;
proto = saddr->sll_protocol;
- addr = saddr->sll_halen ? saddr->sll_addr : NULL;
dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
- if (addr && dev && saddr->sll_halen < dev->addr_len)
- goto out_put;
+ if (po->sk.sk_socket->type == SOCK_DGRAM) {
+ if (dev && msg->msg_namelen < dev->addr_len +
+ offsetof(struct sockaddr_ll, sll_addr))
+ goto out_put;
+ addr = saddr->sll_addr;
+ }
}
err = -ENXIO;
@@ -2799,7 +2801,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
struct sk_buff *skb;
struct net_device *dev;
__be16 proto;
- unsigned char *addr;
+ unsigned char *addr = NULL;
int err, reserve = 0;
struct sockcm_cookie sockc;
struct virtio_net_hdr vnet_hdr = { 0 };
@@ -2816,7 +2818,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
if (likely(saddr == NULL)) {
dev = packet_cached_dev_get(po);
proto = po->num;
- addr = NULL;
} else {
err = -EINVAL;
if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -2824,10 +2825,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr)))
goto out;
proto = saddr->sll_protocol;
- addr = saddr->sll_halen ? saddr->sll_addr : NULL;
dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
- if (addr && dev && saddr->sll_halen < dev->addr_len)
- goto out_unlock;
+ if (sock->type == SOCK_DGRAM) {
+ if (dev && msg->msg_namelen < dev->addr_len +
+ offsetof(struct sockaddr_ll, sll_addr))
+ goto out_unlock;
+ addr = saddr->sll_addr;
+ }
}
err = -ENXIO;
@@ -3344,20 +3348,29 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
sock_recv_ts_and_drops(msg, sk, skb);
if (msg->msg_name) {
+ int copy_len;
+
/* If the address length field is there to be filled
* in, we fill it in now.
*/
if (sock->type == SOCK_PACKET) {
__sockaddr_check_size(sizeof(struct sockaddr_pkt));
msg->msg_namelen = sizeof(struct sockaddr_pkt);
+ copy_len = msg->msg_namelen;
} else {
struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
msg->msg_namelen = sll->sll_halen +
offsetof(struct sockaddr_ll, sll_addr);
+ copy_len = msg->msg_namelen;
+ if (msg->msg_namelen < sizeof(struct sockaddr_ll)) {
+ memset(msg->msg_name +
+ offsetof(struct sockaddr_ll, sll_addr),
+ 0, sizeof(sll->sll_addr));
+ msg->msg_namelen = sizeof(struct sockaddr_ll);
+ }
}
- memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
- msg->msg_namelen);
+ memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len);
}
if (pkt_sk(sk)->auxdata) {
diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c
index 31cf37da4510..93c0437e6a5f 100644
--- a/net/rds/ib_fmr.c
+++ b/net/rds/ib_fmr.c
@@ -44,6 +44,17 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages)
else
pool = rds_ibdev->mr_1m_pool;
+ if (atomic_read(&pool->dirty_count) >= pool->max_items / 10)
+ queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
+
+ /* Switch pools if one of the pool is reaching upper limit */
+ if (atomic_read(&pool->dirty_count) >= pool->max_items * 9 / 10) {
+ if (pool->pool_type == RDS_IB_MR_8K_POOL)
+ pool = rds_ibdev->mr_1m_pool;
+ else
+ pool = rds_ibdev->mr_8k_pool;
+ }
+
ibmr = rds_ib_try_reuse_ibmr(pool);
if (ibmr)
return ibmr;
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 63c8d107adcf..d664e9ade74d 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -454,9 +454,6 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool)
struct rds_ib_mr *ibmr = NULL;
int iter = 0;
- if (atomic_read(&pool->dirty_count) >= pool->max_items_soft / 10)
- queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
-
while (1) {
ibmr = rds_ib_reuse_mr(pool);
if (ibmr)
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 70559854837e..8946c89d7392 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -772,7 +772,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn,
unsigned long frag_off;
unsigned long to_copy;
unsigned long copied;
- uint64_t uncongested = 0;
+ __le64 uncongested = 0;
void *addr;
/* catch completely corrupt packets */
@@ -789,7 +789,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn,
copied = 0;
while (copied < RDS_CONG_MAP_BYTES) {
- uint64_t *src, *dst;
+ __le64 *src, *dst;
unsigned int k;
to_copy = min(RDS_FRAG_SIZE - frag_off, PAGE_SIZE - map_off);
@@ -824,9 +824,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn,
}
/* the congestion map is in little endian order */
- uncongested = le64_to_cpu(uncongested);
-
- rds_cong_map_updated(map, uncongested);
+ rds_cong_map_updated(map, le64_to_cpu(uncongested));
}
static void rds_ib_process_recv(struct rds_connection *conn,
diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c
index 7af4f99c4a93..094a6621f8e8 100644
--- a/net/rose/rose_loopback.c
+++ b/net/rose/rose_loopback.c
@@ -16,6 +16,7 @@
#include <linux/init.h>
static struct sk_buff_head loopback_queue;
+#define ROSE_LOOPBACK_LIMIT 1000
static struct timer_list loopback_timer;
static void rose_set_loopback_timer(void);
@@ -35,29 +36,27 @@ static int rose_loopback_running(void)
int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh)
{
- struct sk_buff *skbn;
+ struct sk_buff *skbn = NULL;
- skbn = skb_clone(skb, GFP_ATOMIC);
+ if (skb_queue_len(&loopback_queue) < ROSE_LOOPBACK_LIMIT)
+ skbn = skb_clone(skb, GFP_ATOMIC);
- kfree_skb(skb);
-
- if (skbn != NULL) {
+ if (skbn) {
+ consume_skb(skb);
skb_queue_tail(&loopback_queue, skbn);
if (!rose_loopback_running())
rose_set_loopback_timer();
+ } else {
+ kfree_skb(skb);
}
return 1;
}
-
static void rose_set_loopback_timer(void)
{
- del_timer(&loopback_timer);
-
- loopback_timer.expires = jiffies + 10;
- add_timer(&loopback_timer);
+ mod_timer(&loopback_timer, jiffies + 10);
}
static void rose_loopback_timer(struct timer_list *unused)
@@ -68,8 +67,12 @@ static void rose_loopback_timer(struct timer_list *unused)
struct sock *sk;
unsigned short frametype;
unsigned int lci_i, lci_o;
+ int count;
- while ((skb = skb_dequeue(&loopback_queue)) != NULL) {
+ for (count = 0; count < ROSE_LOOPBACK_LIMIT; count++) {
+ skb = skb_dequeue(&loopback_queue);
+ if (!skb)
+ return;
if (skb->len < ROSE_MIN_LEN) {
kfree_skb(skb);
continue;
@@ -106,6 +109,8 @@ static void rose_loopback_timer(struct timer_list *unused)
kfree_skb(skb);
}
}
+ if (!skb_queue_empty(&loopback_queue))
+ mod_timer(&loopback_timer, jiffies + 1);
}
void __exit rose_loopback_clear(void)
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 8aa2937b069f..fe96881a334d 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -604,30 +604,30 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
_enter("");
- if (list_empty(&rxnet->calls))
- return;
+ if (!list_empty(&rxnet->calls)) {
+ write_lock(&rxnet->call_lock);
- write_lock(&rxnet->call_lock);
+ while (!list_empty(&rxnet->calls)) {
+ call = list_entry(rxnet->calls.next,
+ struct rxrpc_call, link);
+ _debug("Zapping call %p", call);
- while (!list_empty(&rxnet->calls)) {
- call = list_entry(rxnet->calls.next, struct rxrpc_call, link);
- _debug("Zapping call %p", call);
+ rxrpc_see_call(call);
+ list_del_init(&call->link);
- rxrpc_see_call(call);
- list_del_init(&call->link);
+ pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
+ call, atomic_read(&call->usage),
+ rxrpc_call_states[call->state],
+ call->flags, call->events);
- pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
- call, atomic_read(&call->usage),
- rxrpc_call_states[call->state],
- call->flags, call->events);
+ write_unlock(&rxnet->call_lock);
+ cond_resched();
+ write_lock(&rxnet->call_lock);
+ }
write_unlock(&rxnet->call_lock);
- cond_resched();
- write_lock(&rxnet->call_lock);
}
- write_unlock(&rxnet->call_lock);
-
atomic_dec(&rxnet->nr_calls);
wait_var_event(&rxnet->nr_calls, !atomic_read(&rxnet->nr_calls));
}
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 4c6f9d0a00e7..c2c35cf4e308 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1161,19 +1161,19 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
* handle data received on the local endpoint
* - may be called in interrupt context
*
- * The socket is locked by the caller and this prevents the socket from being
- * shut down and the local endpoint from going away, thus sk_user_data will not
- * be cleared until this function returns.
+ * [!] Note that as this is called from the encap_rcv hook, the socket is not
+ * held locked by the caller and nothing prevents sk_user_data on the UDP from
+ * being cleared in the middle of processing this function.
*
* Called with the RCU read lock held from the IP layer via UDP.
*/
int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
{
+ struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk);
struct rxrpc_connection *conn;
struct rxrpc_channel *chan;
struct rxrpc_call *call = NULL;
struct rxrpc_skb_priv *sp;
- struct rxrpc_local *local = udp_sk->sk_user_data;
struct rxrpc_peer *peer = NULL;
struct rxrpc_sock *rx = NULL;
unsigned int channel;
@@ -1181,6 +1181,10 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
_enter("%p", udp_sk);
+ if (unlikely(!local)) {
+ kfree_skb(skb);
+ return 0;
+ }
if (skb->tstamp == 0)
skb->tstamp = ktime_get_real();
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 15cf42d5b53a..01959db51445 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -304,7 +304,8 @@ nomem:
ret = -ENOMEM;
sock_error:
mutex_unlock(&rxnet->local_mutex);
- kfree(local);
+ if (local)
+ call_rcu(&local->rcu, rxrpc_local_rcu);
_leave(" = %d", ret);
return ERR_PTR(ret);
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 1d143bc3f73d..4aa03588f87b 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1112,32 +1112,6 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc,
}
-/* Sent the next ASCONF packet currently stored in the association.
- * This happens after the ASCONF_ACK was succeffully processed.
- */
-static void sctp_cmd_send_asconf(struct sctp_association *asoc)
-{
- struct net *net = sock_net(asoc->base.sk);
-
- /* Send the next asconf chunk from the addip chunk
- * queue.
- */
- if (!list_empty(&asoc->addip_chunk_list)) {
- struct list_head *entry = asoc->addip_chunk_list.next;
- struct sctp_chunk *asconf = list_entry(entry,
- struct sctp_chunk, list);
- list_del_init(entry);
-
- /* Hold the chunk until an ASCONF_ACK is received. */
- sctp_chunk_hold(asconf);
- if (sctp_primitive_ASCONF(net, asoc, asconf))
- sctp_chunk_free(asconf);
- else
- asoc->addip_last_asconf = asconf;
- }
-}
-
-
/* These three macros allow us to pull the debugging code out of the
* main flow of sctp_do_sm() to keep attention focused on the real
* functionality there.
@@ -1783,9 +1757,6 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
}
sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp);
break;
- case SCTP_CMD_SEND_NEXT_ASCONF:
- sctp_cmd_send_asconf(asoc);
- break;
case SCTP_CMD_PURGE_ASCONF_QUEUE:
sctp_asconf_queue_teardown(asoc);
break;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index c9ae3404b1bb..713a669d2058 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3824,6 +3824,29 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net,
return SCTP_DISPOSITION_CONSUME;
}
+static enum sctp_disposition sctp_send_next_asconf(
+ struct net *net,
+ const struct sctp_endpoint *ep,
+ struct sctp_association *asoc,
+ const union sctp_subtype type,
+ struct sctp_cmd_seq *commands)
+{
+ struct sctp_chunk *asconf;
+ struct list_head *entry;
+
+ if (list_empty(&asoc->addip_chunk_list))
+ return SCTP_DISPOSITION_CONSUME;
+
+ entry = asoc->addip_chunk_list.next;
+ asconf = list_entry(entry, struct sctp_chunk, list);
+
+ list_del_init(entry);
+ sctp_chunk_hold(asconf);
+ asoc->addip_last_asconf = asconf;
+
+ return sctp_sf_do_prm_asconf(net, ep, asoc, type, asconf, commands);
+}
+
/*
* ADDIP Section 4.3 General rules for address manipulation
* When building TLV parameters for the ASCONF Chunk that will add or
@@ -3915,14 +3938,10 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net,
SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
if (!sctp_process_asconf_ack((struct sctp_association *)asoc,
- asconf_ack)) {
- /* Successfully processed ASCONF_ACK. We can
- * release the next asconf if we have one.
- */
- sctp_add_cmd_sf(commands, SCTP_CMD_SEND_NEXT_ASCONF,
- SCTP_NULL());
- return SCTP_DISPOSITION_CONSUME;
- }
+ asconf_ack))
+ return sctp_send_next_asconf(net, ep,
+ (struct sctp_association *)asoc,
+ type, commands);
abort = sctp_make_abort(asoc, asconf_ack,
sizeof(struct sctp_errhdr));
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 12bb23b8e0c5..261131dfa1f1 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -54,6 +54,7 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail)
h->last_refresh = now;
}
+static inline int cache_is_valid(struct cache_head *h);
static void cache_fresh_locked(struct cache_head *head, time_t expiry,
struct cache_detail *detail);
static void cache_fresh_unlocked(struct cache_head *head,
@@ -105,6 +106,8 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail,
if (cache_is_expired(detail, tmp)) {
hlist_del_init_rcu(&tmp->cache_list);
detail->entries --;
+ if (cache_is_valid(tmp) == -EAGAIN)
+ set_bit(CACHE_NEGATIVE, &tmp->flags);
cache_fresh_locked(tmp, 0, detail);
freeme = tmp;
break;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 1d0395ef62c9..8ff11dc98d7f 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2081,8 +2081,8 @@ call_transmit_status(struct rpc_task *task)
* test first.
*/
if (rpc_task_transmitted(task)) {
- if (task->tk_status == 0)
- xprt_request_wait_receive(task);
+ task->tk_status = 0;
+ xprt_request_wait_receive(task);
return;
}
@@ -2167,6 +2167,9 @@ call_bc_transmit_status(struct rpc_task *task)
{
struct rpc_rqst *req = task->tk_rqstp;
+ if (rpc_task_transmitted(task))
+ task->tk_status = 0;
+
dprint_status(task);
switch (task->tk_status) {
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 9f3bdbc1e593..14dedb24fa7b 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -597,7 +597,7 @@ void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
{
struct strp_msg *rxm = strp_msg(skb);
- int err = 0, offset = rxm->offset, copy, nsg;
+ int err = 0, offset = rxm->offset, copy, nsg, data_len, pos;
struct sk_buff *skb_iter, *unused;
struct scatterlist sg[1];
char *orig_buf, *buf;
@@ -628,25 +628,42 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
else
err = 0;
- copy = min_t(int, skb_pagelen(skb) - offset,
- rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+ data_len = rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE;
- if (skb->decrypted)
- skb_store_bits(skb, offset, buf, copy);
+ if (skb_pagelen(skb) > offset) {
+ copy = min_t(int, skb_pagelen(skb) - offset, data_len);
- offset += copy;
- buf += copy;
+ if (skb->decrypted)
+ skb_store_bits(skb, offset, buf, copy);
+ offset += copy;
+ buf += copy;
+ }
+
+ pos = skb_pagelen(skb);
skb_walk_frags(skb, skb_iter) {
- copy = min_t(int, skb_iter->len,
- rxm->full_len - offset + rxm->offset -
- TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+ int frag_pos;
+
+ /* Practically all frags must belong to msg if reencrypt
+ * is needed with current strparser and coalescing logic,
+ * but strparser may "get optimized", so let's be safe.
+ */
+ if (pos + skb_iter->len <= offset)
+ goto done_with_frag;
+ if (pos >= data_len + rxm->offset)
+ break;
+
+ frag_pos = offset - pos;
+ copy = min_t(int, skb_iter->len - frag_pos,
+ data_len + rxm->offset - offset);
if (skb_iter->decrypted)
- skb_store_bits(skb_iter, offset, buf, copy);
+ skb_store_bits(skb_iter, frag_pos, buf, copy);
offset += copy;
buf += copy;
+done_with_frag:
+ pos += skb_iter->len;
}
free_buf:
@@ -904,7 +921,9 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
goto release_netdev;
free_sw_resources:
+ up_read(&device_offload_lock);
tls_sw_free_resources_rx(sk);
+ down_read(&device_offload_lock);
release_ctx:
ctx->priv_ctx_rx = NULL;
release_netdev:
@@ -939,8 +958,6 @@ void tls_device_offload_cleanup_rx(struct sock *sk)
}
out:
up_read(&device_offload_lock);
- kfree(tls_ctx->rx.rec_seq);
- kfree(tls_ctx->rx.iv);
tls_sw_release_resources_rx(sk);
}
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 54c3a758f2a7..c3a5fe624b4e 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -194,18 +194,26 @@ static void update_chksum(struct sk_buff *skb, int headln)
static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
{
+ struct sock *sk = skb->sk;
+ int delta;
+
skb_copy_header(nskb, skb);
skb_put(nskb, skb->len);
memcpy(nskb->data, skb->data, headln);
- update_chksum(nskb, headln);
nskb->destructor = skb->destructor;
- nskb->sk = skb->sk;
+ nskb->sk = sk;
skb->destructor = NULL;
skb->sk = NULL;
- refcount_add(nskb->truesize - skb->truesize,
- &nskb->sk->sk_wmem_alloc);
+
+ update_chksum(nskb, headln);
+
+ delta = nskb->truesize - skb->truesize;
+ if (likely(delta < 0))
+ WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
+ else if (delta)
+ refcount_add(delta, &sk->sk_wmem_alloc);
}
/* This function may be called after the user socket is already
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 9547cea0ce3b..478603f43964 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -293,11 +293,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
#endif
}
- if (ctx->rx_conf == TLS_SW) {
- kfree(ctx->rx.rec_seq);
- kfree(ctx->rx.iv);
+ if (ctx->rx_conf == TLS_SW)
tls_sw_free_resources_rx(sk);
- }
#ifdef CONFIG_TLS_DEVICE
if (ctx->rx_conf == TLS_HW)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index b50ced862f6f..29d6af43dd24 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2078,6 +2078,9 @@ void tls_sw_release_resources_rx(struct sock *sk)
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+ kfree(tls_ctx->rx.rec_seq);
+ kfree(tls_ctx->rx.iv);
+
if (ctx->aead_recv) {
kfree_skb(ctx->recv_pkt);
ctx->recv_pkt = NULL;
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 0ba778f371cb..a6fd5ce199da 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -3778,10 +3778,9 @@ void wiphy_regulatory_register(struct wiphy *wiphy)
/*
* The last request may have been received before this
* registration call. Call the driver notifier if
- * initiator is USER and user type is CELL_BASE.
+ * initiator is USER.
*/
- if (lr->initiator == NL80211_REGDOM_SET_BY_USER &&
- lr->user_reg_hint_type == NL80211_USER_REG_HINT_CELL_BASE)
+ if (lr->initiator == NL80211_REGDOM_SET_BY_USER)
reg_call_notifier(wiphy, lr);
}
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index dbb3c1945b5c..85fec98676d3 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -70,17 +70,28 @@ static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x)
return NULL;
}
-static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb)
+static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb,
+ unsigned short family)
{
struct xfrmi_net *xfrmn;
- int ifindex;
struct xfrm_if *xi;
+ int ifindex = 0;
if (!secpath_exists(skb) || !skb->dev)
return NULL;
+ switch (family) {
+ case AF_INET6:
+ ifindex = inet6_sdif(skb);
+ break;
+ case AF_INET:
+ ifindex = inet_sdif(skb);
+ break;
+ }
+ if (!ifindex)
+ ifindex = skb->dev->ifindex;
+
xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id);
- ifindex = skb->dev->ifindex;
for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
if (ifindex == xi->dev->ifindex &&
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 8d1a898d0ba5..a6b58df7a70f 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3313,7 +3313,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
ifcb = xfrm_if_get_cb();
if (ifcb) {
- xi = ifcb->decode_session(skb);
+ xi = ifcb->decode_session(skb, family);
if (xi) {
if_id = xi->p.if_id;
net = xi->net;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 1bb971f46fc6..178baaa037e5 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2384,7 +2384,7 @@ void xfrm_state_fini(struct net *net)
flush_work(&net->xfrm.state_hash_work);
flush_work(&xfrm_state_gc_work);
- xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
+ xfrm_state_flush(net, 0, false, true);
WARN_ON(!list_empty(&net->xfrm.state_all));
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index a131f9ff979e..6916931b1de1 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1424,7 +1424,7 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
ret = verify_policy_dir(p->dir);
if (ret)
return ret;
- if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir))
+ if (p->index && (xfrm_policy_id2dir(p->index) != p->dir))
return -EINVAL;
return 0;
@@ -1513,20 +1513,8 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
return -EINVAL;
}
- switch (ut[i].id.proto) {
- case IPPROTO_AH:
- case IPPROTO_ESP:
- case IPPROTO_COMP:
-#if IS_ENABLED(CONFIG_IPV6)
- case IPPROTO_ROUTING:
- case IPPROTO_DSTOPTS:
-#endif
- case IPSEC_PROTO_ANY:
- break;
- default:
+ if (!xfrm_id_proto_valid(ut[i].id.proto))
return -EINVAL;
- }
-
}
return 0;
generated by cgit (git 2.34.1) at 2024-05-22 00:42:06 +0000