summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-05-23 17:16:18 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-05-23 17:16:18 -0700
commitcaffb99b6929f41a69edbb5aef3a359bf45f3315 (patch)
tree5387820f7fbdffecd08481f070655e84f22034e9 /net
parent0cfc8a8d70dcd51db783e8e87917e02149c71458 (diff)
parent539d39ad0c61b35f69565a037d7586deaf6d6166 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from David Miller: 1) Fix RCU warnings in ipv6 multicast router code, from Madhuparna Bhowmik. 2) Nexthop attributes aren't being checked properly because of mis-initialized iterator, from David Ahern. 3) Revert iop_idents_reserve() change as it caused performance regressions and was just working around what is really a UBSAN bug in the compiler. From Yuqi Jin. 4) Read MAC address properly from ROM in bmac driver (double iteration proceeds past end of address array), from Jeremy Kerr. 5) Add Microsoft Surface device IDs to r8152, from Marc Payne. 6) Prevent reference to freed SKB in __netif_receive_skb_core(), from Boris Sukholitko. 7) Fix ACK discard behavior in rxrpc, from David Howells. 8) Preserve flow hash across packet scrubbing in wireguard, from Jason A. Donenfeld. 9) Cap option length properly for SO_BINDTODEVICE in AX25, from Eric Dumazet. 10) Fix encryption error checking in kTLS code, from Vadim Fedorenko. 11) Missing BPF prog ref release in flow dissector, from Jakub Sitnicki. 12) dst_cache must be used with BH disabled in tipc, from Eric Dumazet. 13) Fix use after free in mlxsw driver, from Jiri Pirko. 14) Order kTLS key destruction properly in mlx5 driver, from Tariq Toukan. 15) Check devm_platform_ioremap_resource() return value properly in several drivers, from Tiezhu Yang. * git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (71 commits) net: smsc911x: Fix runtime PM imbalance on error net/mlx4_core: fix a memory leak bug. net: ethernet: ti: cpsw: fix ASSERT_RTNL() warning during suspend net: phy: mscc: fix initialization of the MACsec protocol mode net: stmmac: don't attach interface until resume finishes net: Fix return value about devm_platform_ioremap_resource() net/mlx5: Fix error flow in case of function_setup failure net/mlx5e: CT: Correctly get flow rule net/mlx5e: Update netdev txq on completions during closure net/mlx5: Annotate mutex destroy for root ns net/mlx5: Don't maintain a case of del_sw_func being null net/mlx5: Fix cleaning unmanaged flow tables net/mlx5: Fix memory leak in mlx5_events_init net/mlx5e: Fix inner tirs handling net/mlx5e: kTLS, Destroy key object after destroying the TIS net/mlx5e: Fix allowed tc redirect merged eswitch offload cases net/mlx5: Avoid processing commands before cmdif is ready net/mlx5: Fix a race when moving command interface to events mode net/mlx5: Add command entry handling completion rxrpc: Fix a memory leak in rxkad_verify_response() ...
Diffstat (limited to 'net')
-rw-r--r--net/ax25/af_ax25.c6
-rw-r--r--net/core/dev.c20
-rw-r--r--net/core/flow_dissector.c26
-rw-r--r--net/dsa/tag_mtk.c15
-rw-r--r--net/ethtool/netlink.c4
-rw-r--r--net/ethtool/strset.c1
-rw-r--r--net/ipv4/fib_frontend.c3
-rw-r--r--net/ipv4/inet_connection_sock.c43
-rw-r--r--net/ipv4/ipip.c2
-rw-r--r--net/ipv4/ipmr.c2
-rw-r--r--net/ipv4/nexthop.c3
-rw-r--r--net/ipv4/route.c14
-rw-r--r--net/ipv6/ip6_fib.c2
-rw-r--r--net/ipv6/ip6mr.c5
-rw-r--r--net/mptcp/crypto.c24
-rw-r--r--net/mptcp/options.c9
-rw-r--r--net/mptcp/protocol.h1
-rw-r--r--net/mptcp/subflow.c15
-rw-r--r--net/qrtr/qrtr.c2
-rw-r--r--net/rxrpc/Makefile1
-rw-r--r--net/rxrpc/ar-internal.h25
-rw-r--r--net/rxrpc/call_accept.c2
-rw-r--r--net/rxrpc/call_event.c22
-rw-r--r--net/rxrpc/input.c44
-rw-r--r--net/rxrpc/misc.c5
-rw-r--r--net/rxrpc/output.c9
-rw-r--r--net/rxrpc/peer_event.c46
-rw-r--r--net/rxrpc/peer_object.c12
-rw-r--r--net/rxrpc/proc.c8
-rw-r--r--net/rxrpc/rtt.c195
-rw-r--r--net/rxrpc/rxkad.c3
-rw-r--r--net/rxrpc/sendmsg.c26
-rw-r--r--net/rxrpc/sysctl.c9
-rw-r--r--net/sctp/sm_sideeffect.c14
-rw-r--r--net/sctp/sm_statefuns.c9
-rw-r--r--net/tipc/udp_media.c6
-rw-r--r--net/tls/tls_sw.c17
37 files changed, 435 insertions, 215 deletions
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index ff57ea89c27e..fd91cd34f25e 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -635,8 +635,10 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
break;
case SO_BINDTODEVICE:
- if (optlen > IFNAMSIZ)
- optlen = IFNAMSIZ;
+ if (optlen > IFNAMSIZ - 1)
+ optlen = IFNAMSIZ - 1;
+
+ memset(devname, 0, sizeof(devname));
if (copy_from_user(devname, optval, optlen)) {
res = -EFAULT;
diff --git a/net/core/dev.c b/net/core/dev.c
index 6d327b7aa813..2d8aceee4284 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4988,11 +4988,12 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
return 0;
}
-static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
+static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
struct packet_type **ppt_prev)
{
struct packet_type *ptype, *pt_prev;
rx_handler_func_t *rx_handler;
+ struct sk_buff *skb = *pskb;
struct net_device *orig_dev;
bool deliver_exact = false;
int ret = NET_RX_DROP;
@@ -5023,8 +5024,10 @@ another_round:
ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
preempt_enable();
- if (ret2 != XDP_PASS)
- return NET_RX_DROP;
+ if (ret2 != XDP_PASS) {
+ ret = NET_RX_DROP;
+ goto out;
+ }
skb_reset_mac_len(skb);
}
@@ -5174,6 +5177,13 @@ drop:
}
out:
+ /* The invariant here is that if *ppt_prev is not NULL
+ * then skb should also be non-NULL.
+ *
+ * Apparently *ppt_prev assignment above holds this invariant due to
+ * skb dereferencing near it.
+ */
+ *pskb = skb;
return ret;
}
@@ -5183,7 +5193,7 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc)
struct packet_type *pt_prev = NULL;
int ret;
- ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+ ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
if (pt_prev)
ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb,
skb->dev, pt_prev, orig_dev);
@@ -5261,7 +5271,7 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo
struct packet_type *pt_prev = NULL;
skb_list_del_init(skb);
- __netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+ __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
if (!pt_prev)
continue;
if (pt_curr != pt_prev || od_curr != orig_dev) {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 3eff84824c8b..5dceed467f64 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -160,12 +160,10 @@ out:
return ret;
}
-int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
+static int flow_dissector_bpf_prog_detach(struct net *net)
{
struct bpf_prog *attached;
- struct net *net;
- net = current->nsproxy->net_ns;
mutex_lock(&flow_dissector_mutex);
attached = rcu_dereference_protected(net->flow_dissector_prog,
lockdep_is_held(&flow_dissector_mutex));
@@ -179,6 +177,24 @@ int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
return 0;
}
+int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
+{
+ return flow_dissector_bpf_prog_detach(current->nsproxy->net_ns);
+}
+
+static void __net_exit flow_dissector_pernet_pre_exit(struct net *net)
+{
+ /* We're not racing with attach/detach because there are no
+ * references to netns left when pre_exit gets called.
+ */
+ if (rcu_access_pointer(net->flow_dissector_prog))
+ flow_dissector_bpf_prog_detach(net);
+}
+
+static struct pernet_operations flow_dissector_pernet_ops __net_initdata = {
+ .pre_exit = flow_dissector_pernet_pre_exit,
+};
+
/**
* __skb_flow_get_ports - extract the upper layer ports and return them
* @skb: sk_buff to extract the ports from
@@ -1836,7 +1852,7 @@ static int __init init_default_flow_dissectors(void)
skb_flow_dissector_init(&flow_keys_basic_dissector,
flow_keys_basic_dissector_keys,
ARRAY_SIZE(flow_keys_basic_dissector_keys));
- return 0;
-}
+ return register_pernet_subsys(&flow_dissector_pernet_ops);
+}
core_initcall(init_default_flow_dissectors);
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index b5705cba8318..d6619edd53e5 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -15,6 +15,7 @@
#define MTK_HDR_XMIT_TAGGED_TPID_8100 1
#define MTK_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0)
#define MTK_HDR_XMIT_DP_BIT_MASK GENMASK(5, 0)
+#define MTK_HDR_XMIT_SA_DIS BIT(6)
static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
struct net_device *dev)
@@ -22,6 +23,9 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
struct dsa_port *dp = dsa_slave_to_port(dev);
u8 *mtk_tag;
bool is_vlan_skb = true;
+ unsigned char *dest = eth_hdr(skb)->h_dest;
+ bool is_multicast_skb = is_multicast_ether_addr(dest) &&
+ !is_broadcast_ether_addr(dest);
/* Build the special tag after the MAC Source Address. If VLAN header
* is present, it's required that VLAN header and special tag is
@@ -47,6 +51,10 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
MTK_HDR_XMIT_UNTAGGED;
mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
+ /* Disable SA learning for multicast frames */
+ if (unlikely(is_multicast_skb))
+ mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS;
+
/* Tag control information is kept for 802.1Q */
if (!is_vlan_skb) {
mtk_tag[2] = 0;
@@ -61,6 +69,9 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
{
int port;
__be16 *phdr, hdr;
+ unsigned char *dest = eth_hdr(skb)->h_dest;
+ bool is_multicast_skb = is_multicast_ether_addr(dest) &&
+ !is_broadcast_ether_addr(dest);
if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN)))
return NULL;
@@ -86,6 +97,10 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
if (!skb->dev)
return NULL;
+ /* Only unicast or broadcast frames are offloaded */
+ if (likely(!is_multicast_skb))
+ skb->offload_fwd_mark = 1;
+
return skb;
}
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 0c772318c023..ed5357210193 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -342,7 +342,7 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
ret = ops->reply_size(req_info, reply_data);
if (ret < 0)
goto err_cleanup;
- reply_len = ret;
+ reply_len = ret + ethnl_reply_header_size();
ret = -ENOMEM;
rskb = ethnl_reply_init(reply_len, req_info->dev, ops->reply_cmd,
ops->hdr_attr, info, &reply_payload);
@@ -588,7 +588,7 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd,
ret = ops->reply_size(req_info, reply_data);
if (ret < 0)
goto err_cleanup;
- reply_len = ret;
+ reply_len = ret + ethnl_reply_header_size();
ret = -ENOMEM;
skb = genlmsg_new(reply_len, GFP_KERNEL);
if (!skb)
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 95eae5c68a52..0eed4e4909ab 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -324,7 +324,6 @@ static int strset_reply_size(const struct ethnl_req_info *req_base,
int len = 0;
int ret;
- len += ethnl_reply_header_size();
for (i = 0; i < ETH_SS_COUNT; i++) {
const struct strset_info *set_info = &data->sets[i];
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 213be9c050ad..1bf9da3a75f9 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -918,7 +918,6 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
else
filter->dump_exceptions = false;
- filter->dump_all_families = (rtm->rtm_family == AF_UNSPEC);
filter->flags = rtm->rtm_flags;
filter->protocol = rtm->rtm_protocol;
filter->rt_type = rtm->rtm_type;
@@ -990,7 +989,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
if (filter.table_id) {
tb = fib_get_table(net, filter.table_id);
if (!tb) {
- if (filter.dump_all_families)
+ if (rtnl_msg_family(cb->nlh) != PF_INET)
return skb->len;
NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist");
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5f34eb951627..65c29f2bd89f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -24,17 +24,19 @@
#include <net/addrconf.h>
#if IS_ENABLED(CONFIG_IPV6)
-/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
- * only, and any IPv4 addresses if not IPv6 only
- * match_wildcard == false: addresses must be exactly the same, i.e.
- * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
- * and 0.0.0.0 equals to 0.0.0.0 only
+/* match_sk*_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses
+ * if IPv6 only, and any IPv4 addresses
+ * if not IPv6 only
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
+ * and 0.0.0.0 equals to 0.0.0.0 only
*/
static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
const struct in6_addr *sk2_rcv_saddr6,
__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
bool sk1_ipv6only, bool sk2_ipv6only,
- bool match_wildcard)
+ bool match_sk1_wildcard,
+ bool match_sk2_wildcard)
{
int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
@@ -44,8 +46,8 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
return true;
- if (!sk1_rcv_saddr || !sk2_rcv_saddr)
- return match_wildcard;
+ return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+ (match_sk2_wildcard && !sk2_rcv_saddr);
}
return false;
}
@@ -53,11 +55,11 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
return true;
- if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
+ if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard &&
!(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
return true;
- if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
+ if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard &&
!(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
return true;
@@ -69,18 +71,19 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
}
#endif
-/* match_wildcard == true: 0.0.0.0 equals to any IPv4 addresses
- * match_wildcard == false: addresses must be exactly the same, i.e.
- * 0.0.0.0 only equals to 0.0.0.0
+/* match_sk*_wildcard == true: 0.0.0.0 equals to any IPv4 addresses
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ * 0.0.0.0 only equals to 0.0.0.0
*/
static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
- bool sk2_ipv6only, bool match_wildcard)
+ bool sk2_ipv6only, bool match_sk1_wildcard,
+ bool match_sk2_wildcard)
{
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
return true;
- if (!sk1_rcv_saddr || !sk2_rcv_saddr)
- return match_wildcard;
+ return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+ (match_sk2_wildcard && !sk2_rcv_saddr);
}
return false;
}
@@ -96,10 +99,12 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
sk2->sk_rcv_saddr,
ipv6_only_sock(sk),
ipv6_only_sock(sk2),
+ match_wildcard,
match_wildcard);
#endif
return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr,
- ipv6_only_sock(sk2), match_wildcard);
+ ipv6_only_sock(sk2), match_wildcard,
+ match_wildcard);
}
EXPORT_SYMBOL(inet_rcv_saddr_equal);
@@ -285,10 +290,10 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
tb->fast_rcv_saddr,
sk->sk_rcv_saddr,
tb->fast_ipv6_only,
- ipv6_only_sock(sk), true);
+ ipv6_only_sock(sk), true, false);
#endif
return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr,
- ipv6_only_sock(sk), true);
+ ipv6_only_sock(sk), true, false);
}
/* Obtain a reference to a local port for the given sock,
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 2f01cf6fa0de..678575adaf3b 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -698,7 +698,7 @@ out:
rtnl_link_failed:
#if IS_ENABLED(CONFIG_MPLS)
- xfrm4_tunnel_deregister(&mplsip_handler, AF_INET);
+ xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
xfrm_tunnel_mplsip_failed:
#endif
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5c218db2dede..b2363b82b48d 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2613,7 +2613,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id);
if (!mrt) {
- if (filter.dump_all_families)
+ if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR)
return skb->len;
NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist");
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index fdfca534d094..715e14475220 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -276,6 +276,7 @@ out:
return 0;
nla_put_failure:
+ nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
@@ -433,7 +434,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
if (!valid_group_nh(nh, len, extack))
return -EINVAL;
}
- for (i = NHA_GROUP + 1; i < __NHA_MAX; ++i) {
+ for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) {
if (!tb[i])
continue;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index fa829f31a3f5..b73f540fa19b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -491,18 +491,16 @@ u32 ip_idents_reserve(u32 hash, int segs)
atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
u32 old = READ_ONCE(*p_tstamp);
u32 now = (u32)jiffies;
- u32 new, delta = 0;
+ u32 delta = 0;
if (old != now && cmpxchg(p_tstamp, old, now) == old)
delta = prandom_u32_max(now - old);
- /* Do not use atomic_add_return() as it makes UBSAN unhappy */
- do {
- old = (u32)atomic_read(p_id);
- new = old + delta + segs;
- } while (atomic_cmpxchg(p_id, old, new) != old);
-
- return new - segs;
+ /* If UBSAN reports an error there, please make sure your compiler
+ * supports -fno-strict-overflow before reporting it that was a bug
+ * in UBSAN, and it has been fixed in GCC-8.
+ */
+ return atomic_add_return(segs + delta, p_id) - segs;
}
EXPORT_SYMBOL(ip_idents_reserve);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 46ed56719476..20314895509c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -664,7 +664,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
if (arg.filter.table_id) {
tb = fib6_get_table(net, arg.filter.table_id);
if (!tb) {
- if (arg.filter.dump_all_families)
+ if (rtnl_msg_family(cb->nlh) != PF_INET6)
goto out;
NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist");
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 65a54d74acc1..1f4d20e97c07 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -98,7 +98,8 @@ static void ipmr_expire_process(struct timer_list *t);
#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
#define ip6mr_for_each_table(mrt, net) \
list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list, \
- lockdep_rtnl_is_held())
+ lockdep_rtnl_is_held() || \
+ list_empty(&net->ipv6.mr6_tables))
static struct mr_table *ip6mr_mr_table_iter(struct net *net,
struct mr_table *mrt)
@@ -2502,7 +2503,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
mrt = ip6mr_get_table(sock_net(skb->sk), filter.table_id);
if (!mrt) {
- if (filter.dump_all_families)
+ if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR)
return skb->len;
NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist");
diff --git a/net/mptcp/crypto.c b/net/mptcp/crypto.c
index c151628bd416..0f5a414a9366 100644
--- a/net/mptcp/crypto.c
+++ b/net/mptcp/crypto.c
@@ -47,8 +47,6 @@ void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn)
void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac)
{
u8 input[SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE];
- __be32 mptcp_hashed_key[SHA256_DIGEST_WORDS];
- __be32 *hash_out = (__force __be32 *)hmac;
struct sha256_state state;
u8 key1be[8];
u8 key2be[8];
@@ -86,11 +84,7 @@ void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac)
sha256_init(&state);
sha256_update(&state, input, SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE);
- sha256_final(&state, (u8 *)mptcp_hashed_key);
-
- /* takes only first 160 bits */
- for (i = 0; i < 5; i++)
- hash_out[i] = mptcp_hashed_key[i];
+ sha256_final(&state, (u8 *)hmac);
}
#ifdef CONFIG_MPTCP_HMAC_TEST
@@ -101,29 +95,29 @@ struct test_cast {
};
/* we can't reuse RFC 4231 test vectors, as we have constraint on the
- * input and key size, and we truncate the output.
+ * input and key size.
*/
static struct test_cast tests[] = {
{
.key = "0b0b0b0b0b0b0b0b",
.msg = "48692054",
- .result = "8385e24fb4235ac37556b6b886db106284a1da67",
+ .result = "8385e24fb4235ac37556b6b886db106284a1da671699f46db1f235ec622dcafa",
},
{
.key = "aaaaaaaaaaaaaaaa",
.msg = "dddddddd",
- .result = "2c5e219164ff1dca1c4a92318d847bb6b9d44492",
+ .result = "2c5e219164ff1dca1c4a92318d847bb6b9d44492984e1eb71aff9022f71046e9",
},
{
.key = "0102030405060708",
.msg = "cdcdcdcd",
- .result = "e73b9ba9969969cefb04aa0d6df18ec2fcc075b6",
+ .result = "e73b9ba9969969cefb04aa0d6df18ec2fcc075b6f23b4d8c4da736a5dbbc6e7d",
},
};
static int __init test_mptcp_crypto(void)
{
- char hmac[20], hmac_hex[41];
+ char hmac[32], hmac_hex[65];
u32 nonce1, nonce2;
u64 key1, key2;
u8 msg[8];
@@ -140,11 +134,11 @@ static int __init test_mptcp_crypto(void)
put_unaligned_be32(nonce2, &msg[4]);
mptcp_crypto_hmac_sha(key1, key2, msg, 8, hmac);
- for (j = 0; j < 20; ++j)
+ for (j = 0; j < 32; ++j)
sprintf(&hmac_hex[j << 1], "%02x", hmac[j] & 0xff);
- hmac_hex[40] = 0;
+ hmac_hex[64] = 0;
- if (memcmp(hmac_hex, tests[i].result, 40))
+ if (memcmp(hmac_hex, tests[i].result, 64))
pr_err("test %d failed, got %s expected %s", i,
hmac_hex, tests[i].result);
else
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 45497af23906..7793b6011fa7 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -7,6 +7,7 @@
#define pr_fmt(fmt) "MPTCP: " fmt
#include <linux/kernel.h>
+#include <crypto/sha.h>
#include <net/tcp.h>
#include <net/mptcp.h>
#include "protocol.h"
@@ -535,7 +536,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id,
struct in_addr *addr)
{
- u8 hmac[MPTCP_ADDR_HMAC_LEN];
+ u8 hmac[SHA256_DIGEST_SIZE];
u8 msg[7];
msg[0] = addr_id;
@@ -545,14 +546,14 @@ static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id,
mptcp_crypto_hmac_sha(key1, key2, msg, 7, hmac);
- return get_unaligned_be64(hmac);
+ return get_unaligned_be64(&hmac[SHA256_DIGEST_SIZE - sizeof(u64)]);
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
struct in6_addr *addr)
{
- u8 hmac[MPTCP_ADDR_HMAC_LEN];
+ u8 hmac[SHA256_DIGEST_SIZE];
u8 msg[19];
msg[0] = addr_id;
@@ -562,7 +563,7 @@ static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
mptcp_crypto_hmac_sha(key1, key2, msg, 19, hmac);
- return get_unaligned_be64(hmac);
+ return get_unaligned_be64(&hmac[SHA256_DIGEST_SIZE - sizeof(u64)]);
}
#endif
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index e4ca6320ce76..d0803dfb8108 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -81,7 +81,6 @@
/* MPTCP ADD_ADDR flags */
#define MPTCP_ADDR_ECHO BIT(0)
-#define MPTCP_ADDR_HMAC_LEN 20
#define MPTCP_ADDR_IPVERSION_4 4
#define MPTCP_ADDR_IPVERSION_6 6
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 4931a29a6f08..8968b2c065e7 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -10,6 +10,7 @@
#include <linux/module.h>
#include <linux/netdevice.h>
#include <crypto/algapi.h>
+#include <crypto/sha.h>
#include <net/sock.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
@@ -89,7 +90,7 @@ static bool subflow_token_join_request(struct request_sock *req,
const struct sk_buff *skb)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
- u8 hmac[MPTCPOPT_HMAC_LEN];
+ u8 hmac[SHA256_DIGEST_SIZE];
struct mptcp_sock *msk;
int local_id;
@@ -201,7 +202,7 @@ static void subflow_v6_init_req(struct request_sock *req,
/* validate received truncated hmac and create hmac for third ACK */
static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow)
{
- u8 hmac[MPTCPOPT_HMAC_LEN];
+ u8 hmac[SHA256_DIGEST_SIZE];
u64 thmac;
subflow_generate_hmac(subflow->remote_key, subflow->local_key,
@@ -267,6 +268,8 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
}
} else if (subflow->mp_join) {
+ u8 hmac[SHA256_DIGEST_SIZE];
+
pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u",
subflow, subflow->thmac,
subflow->remote_nonce);
@@ -279,7 +282,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow_generate_hmac(subflow->local_key, subflow->remote_key,
subflow->local_nonce,
subflow->remote_nonce,
- subflow->hmac);
+ hmac);
+
+ memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN);
if (skb)
subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
@@ -347,7 +352,7 @@ static bool subflow_hmac_valid(const struct request_sock *req,
const struct mptcp_options_received *mp_opt)
{
const struct mptcp_subflow_request_sock *subflow_req;
- u8 hmac[MPTCPOPT_HMAC_LEN];
+ u8 hmac[SHA256_DIGEST_SIZE];
struct mptcp_sock *msk;
bool ret;
@@ -361,7 +366,7 @@ static bool subflow_hmac_valid(const struct request_sock *req,
subflow_req->local_nonce, hmac);
ret = true;
- if (crypto_memneq(hmac, mp_opt->hmac, sizeof(hmac)))
+ if (crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN))
ret = false;
sock_put((struct sock *)msk);
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 7ed31b5e77e4..2d8d6131bc5f 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -854,7 +854,7 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
}
mutex_unlock(&qrtr_node_lock);
- qrtr_local_enqueue(node, skb, type, from, to);
+ qrtr_local_enqueue(NULL, skb, type, from, to);
return 0;
}
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile
index 6ffb7e9887ce..ddd0f95713a9 100644
--- a/net/rxrpc/Makefile
+++ b/net/rxrpc/Makefile
@@ -25,6 +25,7 @@ rxrpc-y := \
peer_event.o \
peer_object.o \
recvmsg.o \
+ rtt.o \
security.o \
sendmsg.o \
skbuff.o \
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 3eb1ab40ca5c..9fe264bec70c 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -7,6 +7,7 @@
#include <linux/atomic.h>
#include <linux/seqlock.h>
+#include <linux/win_minmax.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/sock.h>
@@ -311,11 +312,14 @@ struct rxrpc_peer {
#define RXRPC_RTT_CACHE_SIZE 32
spinlock_t rtt_input_lock; /* RTT lock for input routine */
ktime_t rtt_last_req; /* Time of last RTT request */
- u64 rtt; /* Current RTT estimate (in nS) */
- u64 rtt_sum; /* Sum of cache contents */
- u64 rtt_cache[RXRPC_RTT_CACHE_SIZE]; /* Determined RTT cache */
- u8 rtt_cursor; /* next entry at which to insert */
- u8 rtt_usage; /* amount of cache actually used */
+ unsigned int rtt_count; /* Number of samples we've got */
+
+ u32 srtt_us; /* smoothed round trip time << 3 in usecs */
+ u32 mdev_us; /* medium deviation */
+ u32 mdev_max_us; /* maximal mdev for the last rtt period */
+ u32 rttvar_us; /* smoothed mdev_max */
+ u32 rto_j; /* Retransmission timeout in jiffies */
+ u8 backoff; /* Backoff timeout */
u8 cong_cwnd; /* Congestion window size */
};
@@ -1041,7 +1045,6 @@ extern unsigned long rxrpc_idle_ack_delay;
extern unsigned int rxrpc_rx_window_size;
extern unsigned int rxrpc_rx_mtu;
extern unsigned int rxrpc_rx_jumbo_max;
-extern unsigned long rxrpc_resend_timeout;
extern const s8 rxrpc_ack_priority[];
@@ -1069,8 +1072,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
* peer_event.c
*/
void rxrpc_error_report(struct sock *);
-void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
- rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
void rxrpc_peer_keepalive_worker(struct work_struct *);
/*
@@ -1103,6 +1104,14 @@ void rxrpc_notify_socket(struct rxrpc_call *);
int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
/*
+ * rtt.c
+ */
+void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
+ rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
+unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool);
+void rxrpc_peer_init_rtt(struct rxrpc_peer *);
+
+/*
* rxkad.c
*/
#ifdef CONFIG_RXKAD
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 70e44abf106c..b7611cc159e5 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -248,7 +248,7 @@ static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb)
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
ktime_t now = skb->tstamp;
- if (call->peer->rtt_usage < 3 ||
+ if (call->peer->rtt_count < 3 ||
ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now))
rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
true, true,
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index cedbbb3a7c2e..2a65ac41055f 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -111,8 +111,8 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
} else {
unsigned long now = jiffies, ack_at;
- if (call->peer->rtt_usage > 0)
- ack_at = nsecs_to_jiffies(call->peer->rtt);
+ if (call->peer->srtt_us != 0)
+ ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3);
else
ack_at = expiry;
@@ -157,24 +157,18 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call)
static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
{
struct sk_buff *skb;
- unsigned long resend_at;
+ unsigned long resend_at, rto_j;
rxrpc_seq_t cursor, seq, top;
- ktime_t now, max_age, oldest, ack_ts, timeout, min_timeo;
+ ktime_t now, max_age, oldest, ack_ts;
int ix;
u8 annotation, anno_type, retrans = 0, unacked = 0;
_enter("{%d,%d}", call->tx_hard_ack, call->tx_top);
- if (call->peer->rtt_usage > 1)
- timeout = ns_to_ktime(call->peer->rtt * 3 / 2);
- else
- timeout = ms_to_ktime(rxrpc_resend_timeout);
- min_timeo = ns_to_ktime((1000000000 / HZ) * 4);
- if (ktime_before(timeout, min_timeo))
- timeout = min_timeo;
+ rto_j = call->peer->rto_j;
now = ktime_get_real();
- max_age = ktime_sub(now, timeout);
+ max_age = ktime_sub(now, jiffies_to_usecs(rto_j));
spin_lock_bh(&call->lock);
@@ -219,7 +213,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
}
resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest)));
- resend_at += jiffies + rxrpc_resend_timeout;
+ resend_at += jiffies + rto_j;
WRITE_ONCE(call->resend_at, resend_at);
if (unacked)
@@ -234,7 +228,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
rxrpc_timer_set_for_resend);
spin_unlock_bh(&call->lock);
ack_ts = ktime_sub(now, call->acks_latest_ts);
- if (ktime_to_ns(ack_ts) < call->peer->rtt)
+ if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3))
goto out;
rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
rxrpc_propose_ack_ping_for_lost_ack);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 69e09d69c896..3be4177baf70 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -91,11 +91,11 @@ static void rxrpc_congestion_management(struct rxrpc_call *call,
/* We analyse the number of packets that get ACK'd per RTT
* period and increase the window if we managed to fill it.
*/
- if (call->peer->rtt_usage == 0)
+ if (call->peer->rtt_count == 0)
goto out;
if (ktime_before(skb->tstamp,
- ktime_add_ns(call->cong_tstamp,
- call->peer->rtt)))
+ ktime_add_us(call->cong_tstamp,
+ call->peer->srtt_us >> 3)))
goto out_no_clear_ca;
change = rxrpc_cong_rtt_window_end;
call->cong_tstamp = skb->tstamp;
@@ -803,6 +803,30 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks,
}
/*
+ * Return true if the ACK is valid - ie. it doesn't appear to have regressed
+ * with respect to the ack state conveyed by preceding ACKs.
+ */
+static bool rxrpc_is_ack_valid(struct rxrpc_call *call,
+ rxrpc_seq_t first_pkt, rxrpc_seq_t prev_pkt)
+{
+ rxrpc_seq_t base = READ_ONCE(call->ackr_first_seq);
+
+ if (after(first_pkt, base))
+ return true; /* The window advanced */
+
+ if (before(first_pkt, base))
+ return false; /* firstPacket regressed */
+
+ if (after_eq(prev_pkt, call->ackr_prev_seq))
+ return true; /* previousPacket hasn't regressed. */
+
+ /* Some rx implementations put a serial number in previousPacket. */
+ if (after_eq(prev_pkt, base + call->tx_winsize))
+ return false;
+ return true;
+}
+
+/*
* Process an ACK packet.
*
* ack.firstPacket is the sequence number of the first soft-ACK'd/NAK'd packet
@@ -865,9 +889,12 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
}
/* Discard any out-of-order or duplicate ACKs (outside lock). */
- if (before(first_soft_ack, call->ackr_first_seq) ||
- before(prev_pkt, call->ackr_prev_seq))
+ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
+ trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial,
+ first_soft_ack, call->ackr_first_seq,
+ prev_pkt, call->ackr_prev_seq);
return;
+ }
buf.info.rxMTU = 0;
ioffset = offset + nr_acks + 3;
@@ -878,9 +905,12 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
spin_lock(&call->input_lock);
/* Discard any out-of-order or duplicate ACKs (inside lock). */
- if (before(first_soft_ack, call->ackr_first_seq) ||
- before(prev_pkt, call->ackr_prev_seq))
+ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
+ trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial,
+ first_soft_ack, call->ackr_first_seq,
+ prev_pkt, call->ackr_prev_seq);
goto out;
+ }
call->acks_latest_ts = skb->tstamp;
call->ackr_first_seq = first_soft_ack;
diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c
index 214405f75346..d4144fd86f84 100644
--- a/net/rxrpc/misc.c
+++ b/net/rxrpc/misc.c
@@ -63,11 +63,6 @@ unsigned int rxrpc_rx_mtu = 5692;
*/
unsigned int rxrpc_rx_jumbo_max = 4;
-/*
- * Time till packet resend (in milliseconds).
- */
-unsigned long rxrpc_resend_timeout = 4 * HZ;
-
const s8 rxrpc_ack_priority[] = {
[0] = 0,
[RXRPC_ACK_DELAY] = 1,
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 90e263c6aa69..f8b632a5c619 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -369,7 +369,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
(test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) ||
retrans ||
call->cong_mode == RXRPC_CALL_SLOW_START ||
- (call->peer->rtt_usage < 3 && sp->hdr.seq & 1) ||
+ (call->peer->rtt_count < 3 && sp->hdr.seq & 1) ||
ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000),
ktime_get_real())))
whdr.flags |= RXRPC_REQUEST_ACK;
@@ -423,13 +423,10 @@ done:
if (whdr.flags & RXRPC_REQUEST_ACK) {
call->peer->rtt_last_req = skb->tstamp;
trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
- if (call->peer->rtt_usage > 1) {
+ if (call->peer->rtt_count > 1) {
unsigned long nowj = jiffies, ack_lost_at;
- ack_lost_at = nsecs_to_jiffies(2 * call->peer->rtt);
- if (ack_lost_at < 1)
- ack_lost_at = 1;
-
+ ack_lost_at = rxrpc_get_rto_backoff(call->peer, retrans);
ack_lost_at += nowj;
WRITE_ONCE(call->ack_lost_at, ack_lost_at);
rxrpc_reduce_call_timer(call, ack_lost_at, nowj,
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 923b263c401b..b1449d971883 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -296,52 +296,6 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error,
}
/*
- * Add RTT information to cache. This is called in softirq mode and has
- * exclusive access to the peer RTT data.
- */
-void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
- rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
- ktime_t send_time, ktime_t resp_time)
-{
- struct rxrpc_peer *peer = call->peer;
- s64 rtt;
- u64 sum = peer->rtt_sum, avg;
- u8 cursor = peer->rtt_cursor, usage = peer->rtt_usage;
-
- rtt = ktime_to_ns(ktime_sub(resp_time, send_time));
- if (rtt < 0)
- return;
-
- spin_lock(&peer->rtt_input_lock);
-
- /* Replace the oldest datum in the RTT buffer */
- sum -= peer->rtt_cache[cursor];
- sum += rtt;
- peer->rtt_cache[cursor] = rtt;
- peer->rtt_cursor = (cursor + 1) & (RXRPC_RTT_CACHE_SIZE - 1);
- peer->rtt_sum = sum;
- if (usage < RXRPC_RTT_CACHE_SIZE) {
- usage++;
- peer->rtt_usage = usage;
- }
-
- spin_unlock(&peer->rtt_input_lock);
-
- /* Now recalculate the average */
- if (usage == RXRPC_RTT_CACHE_SIZE) {
- avg = sum / RXRPC_RTT_CACHE_SIZE;
- } else {
- avg = sum;
- do_div(avg, usage);
- }
-
- /* Don't need to update this under lock */
- peer->rtt = avg;
- trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt,
- usage, avg);
-}
-
-/*
* Perform keep-alive pings.
*/
static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 452163eadb98..ca29976bb193 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -225,6 +225,8 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
spin_lock_init(&peer->rtt_input_lock);
peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
+ rxrpc_peer_init_rtt(peer);
+
if (RXRPC_TX_SMSS > 2190)
peer->cong_cwnd = 2;
else if (RXRPC_TX_SMSS > 1095)
@@ -497,14 +499,14 @@ void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call,
EXPORT_SYMBOL(rxrpc_kernel_get_peer);
/**
- * rxrpc_kernel_get_rtt - Get a call's peer RTT
+ * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT
* @sock: The socket on which the call is in progress.
* @call: The call to query
*
- * Get the call's peer RTT.
+ * Get the call's peer smoothed RTT.
*/
-u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call)
+u32 rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call)
{
- return call->peer->rtt;
+ return call->peer->srtt_us >> 3;
}
-EXPORT_SYMBOL(rxrpc_kernel_get_rtt);
+EXPORT_SYMBOL(rxrpc_kernel_get_srtt);
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index b9d053e42821..8b179e3c802a 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -222,7 +222,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v)
seq_puts(seq,
"Proto Local "
" Remote "
- " Use CW MTU LastUse RTT Rc\n"
+ " Use CW MTU LastUse RTT RTO\n"
);
return 0;
}
@@ -236,15 +236,15 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v)
now = ktime_get_seconds();
seq_printf(seq,
"UDP %-47.47s %-47.47s %3u"
- " %3u %5u %6llus %12llu %2u\n",
+ " %3u %5u %6llus %8u %8u\n",
lbuff,
rbuff,
atomic_read(&peer->usage),
peer->cong_cwnd,
peer->mtu,
now - peer->last_tx_at,
- peer->rtt,
- peer->rtt_cursor);
+ peer->srtt_us >> 3,
+ jiffies_to_usecs(peer->rto_j));
return 0;
}
diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c
new file mode 100644
index 000000000000..928d8b34a3ee
--- /dev/null
+++ b/net/rxrpc/rtt.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/* RTT/RTO calculation.
+ *
+ * Adapted from TCP for AF_RXRPC by David Howells (dhowells@redhat.com)
+ *
+ * https://tools.ietf.org/html/rfc6298
+ * https://tools.ietf.org/html/rfc1122#section-4.2.3.1
+ * http://ccr.sigcomm.org/archive/1995/jan95/ccr-9501-partridge87.pdf
+ */
+
+#include <linux/net.h>
+#include "ar-internal.h"
+
+#define RXRPC_RTO_MAX ((unsigned)(120 * HZ))
+#define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */
+#define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */
+#define rxrpc_min_rtt_wlen 300 /* As sysctl_tcp_min_rtt_wlen */
+
+static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer)
+{
+ return 200;
+}
+
+static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer)
+{
+ return _usecs_to_jiffies((peer->srtt_us >> 3) + peer->rttvar_us);
+}
+
+static u32 rxrpc_bound_rto(u32 rto)
+{
+ return min(rto, RXRPC_RTO_MAX);
+}
+
+/*
+ * Called to compute a smoothed rtt estimate. The data fed to this
+ * routine either comes from timestamps, or from segments that were
+ * known _not_ to have been retransmitted [see Karn/Partridge
+ * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88
+ * piece by Van Jacobson.
+ * NOTE: the next three routines used to be one big routine.
+ * To save cycles in the RFC 1323 implementation it was better to break
+ * it up into three procedures. -- erics
+ */
+static void rxrpc_rtt_estimator(struct rxrpc_peer *peer, long sample_rtt_us)
+{
+ long m = sample_rtt_us; /* RTT */
+ u32 srtt = peer->srtt_us;
+
+ /* The following amusing code comes from Jacobson's
+ * article in SIGCOMM '88. Note that rtt and mdev
+ * are scaled versions of rtt and mean deviation.
+ * This is designed to be as fast as possible
+ * m stands for "measurement".
+ *
+ * On a 1990 paper the rto value is changed to:
+ * RTO = rtt + 4 * mdev
+ *
+ * Funny. This algorithm seems to be very broken.
+ * These formulae increase RTO, when it should be decreased, increase
+ * too slowly, when it should be increased quickly, decrease too quickly
+ * etc. I guess in BSD RTO takes ONE value, so that it is absolutely
+ * does not matter how to _calculate_ it. Seems, it was trap
+ * that VJ failed to avoid. 8)
+ */
+ if (srtt != 0) {
+ m -= (srtt >> 3); /* m is now error in rtt est */
+ srtt += m; /* rtt = 7/8 rtt + 1/8 new */
+ if (m < 0) {
+ m = -m; /* m is now abs(error) */
+ m -= (peer->mdev_us >> 2); /* similar update on mdev */
+ /* This is similar to one of Eifel findings.
+ * Eifel blocks mdev updates when rtt decreases.
+ * This solution is a bit different: we use finer gain
+ * for mdev in this case (alpha*beta).
+ * Like Eifel it also prevents growth of rto,
+ * but also it limits too fast rto decreases,
+ * happening in pure Eifel.
+ */
+ if (m > 0)
+ m >>= 3;
+ } else {
+ m -= (peer->mdev_us >> 2); /* similar update on mdev */
+ }
+
+ peer->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */
+ if (peer->mdev_us > peer->mdev_max_us) {
+ peer->mdev_max_us = peer->mdev_us;
+ if (peer->mdev_max_us > peer->rttvar_us)
+ peer->rttvar_us = peer->mdev_max_us;
+ }
+ } else {
+ /* no previous measure. */
+ srtt = m << 3; /* take the measured time to be rtt */
+ peer->mdev_us = m << 1; /* make sure rto = 3*rtt */
+ peer->rttvar_us = max(peer->mdev_us, rxrpc_rto_min_us(peer));
+ peer->mdev_max_us = peer->rttvar_us;
+ }
+
+ peer->srtt_us = max(1U, srtt);
+}
+
+/*
+ * Calculate rto without backoff. This is the second half of Van Jacobson's
+ * routine referred to above.
+ */
+static void rxrpc_set_rto(struct rxrpc_peer *peer)
+{
+ u32 rto;
+
+ /* 1. If rtt variance happened to be less 50msec, it is hallucination.
+ * It cannot be less due to utterly erratic ACK generation made
+ * at least by solaris and freebsd. "Erratic ACKs" has _nothing_
+ * to do with delayed acks, because at cwnd>2 true delack timeout
+ * is invisible. Actually, Linux-2.4 also generates erratic
+ * ACKs in some circumstances.
+ */
+ rto = __rxrpc_set_rto(peer);
+
+ /* 2. Fixups made earlier cannot be right.
+ * If we do not estimate RTO correctly without them,
+ * all the algo is pure shit and should be replaced
+ * with correct one. It is exactly, which we pretend to do.
+ */
+
+ /* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo
+ * guarantees that rto is higher.
+ */
+ peer->rto_j = rxrpc_bound_rto(rto);
+}
+
+static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us)
+{
+ if (rtt_us < 0)
+ return;
+
+ //rxrpc_update_rtt_min(peer, rtt_us);
+ rxrpc_rtt_estimator(peer, rtt_us);
+ rxrpc_set_rto(peer);
+
+ /* RFC6298: only reset backoff on valid RTT measurement. */
+ peer->backoff = 0;
+}
+
+/*
+ * Add RTT information to cache. This is called in softirq mode and has
+ * exclusive access to the peer RTT data.
+ */
+void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
+ rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
+ ktime_t send_time, ktime_t resp_time)
+{
+ struct rxrpc_peer *peer = call->peer;
+ s64 rtt_us;
+
+ rtt_us = ktime_to_us(ktime_sub(resp_time, send_time));
+ if (rtt_us < 0)
+ return;
+
+ spin_lock(&peer->rtt_input_lock);
+ rxrpc_ack_update_rtt(peer, rtt_us);
+ if (peer->rtt_count < 3)
+ peer->rtt_count++;
+ spin_unlock(&peer->rtt_input_lock);
+
+ trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial,
+ peer->srtt_us >> 3, peer->rto_j);
+}
+
+/*
+ * Get the retransmission timeout to set in jiffies, backing it off each time
+ * we retransmit.
+ */
+unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans)
+{
+ u64 timo_j;
+ u8 backoff = READ_ONCE(peer->backoff);
+
+ timo_j = peer->rto_j;
+ timo_j <<= backoff;
+ if (retrans && timo_j * 2 <= RXRPC_RTO_MAX)
+ WRITE_ONCE(peer->backoff, backoff + 1);
+
+ if (timo_j < 1)
+ timo_j = 1;
+
+ return timo_j;
+}
+
+void rxrpc_peer_init_rtt(struct rxrpc_peer *peer)
+{
+ peer->rto_j = RXRPC_TIMEOUT_INIT;
+ peer->mdev_us = jiffies_to_usecs(RXRPC_TIMEOUT_INIT);
+ peer->backoff = 0;
+ //minmax_reset(&peer->rtt_min, rxrpc_jiffies32, ~0U);
+}
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 098f1f9ec53b..52a24d4ef5d8 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -1148,7 +1148,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
ret = rxkad_decrypt_ticket(conn, skb, ticket, ticket_len, &session_key,
&expiry, _abort_code);
if (ret < 0)
- goto temporary_error_free_resp;
+ goto temporary_error_free_ticket;
/* use the session key from inside the ticket to decrypt the
* response */
@@ -1230,7 +1230,6 @@ protocol_error:
temporary_error_free_ticket:
kfree(ticket);
-temporary_error_free_resp:
kfree(response);
temporary_error:
/* Ignore the response packet if we got a temporary error such as
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 0fcf157aa09f..5e9c43d4a314 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -66,15 +66,14 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx,
struct rxrpc_call *call)
{
rxrpc_seq_t tx_start, tx_win;
- signed long rtt2, timeout;
- u64 rtt;
+ signed long rtt, timeout;
- rtt = READ_ONCE(call->peer->rtt);
- rtt2 = nsecs_to_jiffies64(rtt) * 2;
- if (rtt2 < 2)
- rtt2 = 2;
+ rtt = READ_ONCE(call->peer->srtt_us) >> 3;
+ rtt = usecs_to_jiffies(rtt) * 2;
+ if (rtt < 2)
+ rtt = 2;
- timeout = rtt2;
+ timeout = rtt;
tx_start = READ_ONCE(call->tx_hard_ack);
for (;;) {
@@ -92,7 +91,7 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx,
return -EINTR;
if (tx_win != tx_start) {
- timeout = rtt2;
+ timeout = rtt;
tx_start = tx_win;
}
@@ -271,16 +270,9 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
_debug("need instant resend %d", ret);
rxrpc_instant_resend(call, ix);
} else {
- unsigned long now = jiffies, resend_at;
+ unsigned long now = jiffies;
+ unsigned long resend_at = now + call->peer->rto_j;
- if (call->peer->rtt_usage > 1)
- resend_at = nsecs_to_jiffies(call->peer->rtt * 3 / 2);
- else
- resend_at = rxrpc_resend_timeout;
- if (resend_at < 1)
- resend_at = 1;
-
- resend_at += now;
WRITE_ONCE(call->resend_at, resend_at);
rxrpc_reduce_call_timer(call, resend_at, now,
rxrpc_timer_set_for_send);
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index 2bbb38161851..18dade4e6f9a 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -71,15 +71,6 @@ static struct ctl_table rxrpc_sysctl_table[] = {
.extra1 = (void *)&one_jiffy,
.extra2 = (void *)&max_jiffies,
},
- {
- .procname = "resend_timeout",
- .data = &rxrpc_resend_timeout,
- .maxlen = sizeof(unsigned long),
- .mode = 0644,
- .proc_handler = proc_doulongvec_ms_jiffies_minmax,
- .extra1 = (void *)&one_jiffy,
- .extra2 = (void *)&max_jiffies,
- },
/* Non-time values */
{
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 2bc29463e1dc..9f36fe911d08 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1523,9 +1523,17 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
timeout = asoc->timeouts[cmd->obj.to];
BUG_ON(!timeout);
- timer->expires = jiffies + timeout;
- sctp_association_hold(asoc);
- add_timer(timer);
+ /*
+ * SCTP has a hard time with timer starts. Because we process
+ * timer starts as side effects, it can be hard to tell if we
+ * have already started a timer or not, which leads to BUG
+ * halts when we call add_timer. So here, instead of just starting
+ * a timer, if the timer is already started, and just mod
+ * the timer with the shorter of the two expiration times
+ */
+ if (!timer_pending(timer))
+ sctp_association_hold(asoc);
+ timer_reduce(timer, jiffies + timeout);
break;
case SCTP_CMD_TIMER_RESTART:
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 26788f4a3b9e..e86620fbd90f 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1856,12 +1856,13 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
/* Update the content of current association. */
sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
- if (sctp_state(asoc, SHUTDOWN_PENDING) &&
+ if ((sctp_state(asoc, SHUTDOWN_PENDING) ||
+ sctp_state(asoc, SHUTDOWN_SENT)) &&
(sctp_sstate(asoc->base.sk, CLOSING) ||
sock_flag(asoc->base.sk, SOCK_DEAD))) {
- /* if were currently in SHUTDOWN_PENDING, but the socket
- * has been closed by user, don't transition to ESTABLISHED.
- * Instead trigger SHUTDOWN bundled with COOKIE_ACK.
+ /* If the socket has been closed by user, don't
+ * transition to ESTABLISHED. Instead trigger SHUTDOWN
+ * bundled with COOKIE_ACK.
*/
sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
return sctp_sf_do_9_2_start_shutdown(net, ep, asoc,
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index d6620ad53546..28a283f26a8d 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -161,9 +161,11 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
struct udp_bearer *ub, struct udp_media_addr *src,
struct udp_media_addr *dst, struct dst_cache *cache)
{
- struct dst_entry *ndst = dst_cache_get(cache);
+ struct dst_entry *ndst;
int ttl, err = 0;
+ local_bh_disable();
+ ndst = dst_cache_get(cache);
if (dst->proto == htons(ETH_P_IP)) {
struct rtable *rt = (struct rtable *)ndst;
@@ -210,9 +212,11 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
src->port, dst->port, false);
#endif
}
+ local_bh_enable();
return err;
tx_error:
+ local_bh_enable();
kfree_skb(skb);
return err;
}
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index e23f94a5549b..2d399b6c4075 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -780,7 +780,7 @@ static int tls_push_record(struct sock *sk, int flags,
static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
bool full_record, u8 record_type,
- size_t *copied, int flags)
+ ssize_t *copied, int flags)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
@@ -796,9 +796,10 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
psock = sk_psock_get(sk);
if (!psock || !policy) {
err = tls_push_record(sk, flags, record_type);
- if (err && err != -EINPROGRESS) {
+ if (err && sk->sk_err == EBADMSG) {
*copied -= sk_msg_free(sk, msg);
tls_free_open_rec(sk);
+ err = -sk->sk_err;
}
if (psock)
sk_psock_put(sk, psock);
@@ -824,9 +825,10 @@ more_data:
switch (psock->eval) {
case __SK_PASS:
err = tls_push_record(sk, flags, record_type);
- if (err && err != -EINPROGRESS) {
+ if (err && sk->sk_err == EBADMSG) {
*copied -= sk_msg_free(sk, msg);
tls_free_open_rec(sk);
+ err = -sk->sk_err;
goto out_err;
}
break;
@@ -916,7 +918,8 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
unsigned char record_type = TLS_RECORD_TYPE_DATA;
bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
bool eor = !(msg->msg_flags & MSG_MORE);
- size_t try_to_copy, copied = 0;
+ size_t try_to_copy;
+ ssize_t copied = 0;
struct sk_msg *msg_pl, *msg_en;
struct tls_rec *rec;
int required_size;
@@ -1118,7 +1121,7 @@ send_end:
release_sock(sk);
mutex_unlock(&tls_ctx->tx_lock);
- return copied ? copied : ret;
+ return copied > 0 ? copied : ret;
}
static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
@@ -1132,7 +1135,7 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
struct sk_msg *msg_pl;
struct tls_rec *rec;
int num_async = 0;
- size_t copied = 0;
+ ssize_t copied = 0;
bool full_record;
int record_room;
int ret = 0;
@@ -1234,7 +1237,7 @@ wait_for_memory:
}
sendpage_end:
ret = sk_stream_error(sk, flags, ret);
- return copied ? copied : ret;
+ return copied > 0 ? copied : ret;
}
int tls_sw_sendpage_locked(struct sock *sk, struct page *page,