summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/9p/trans_xen.c8
-rw-r--r--net/ax25/af_ax25.c13
-rw-r--r--net/can/isotp.c2
-rw-r--r--net/ceph/messenger_v2.c8
-rw-r--r--net/core/dev.c10
-rw-r--r--net/core/filter.c17
-rw-r--r--net/core/flow_dissector.c3
-rw-r--r--net/core/skbuff.c15
-rw-r--r--net/dsa/dsa2.c23
-rw-r--r--net/dsa/master.c25
-rw-r--r--net/ipv4/fib_semantics.c7
-rw-r--r--net/ipv6/ip6_output.c2
-rw-r--r--net/ipv6/ip6mr.c2
-rw-r--r--net/ipv6/route.c2
-rw-r--r--net/llc/af_llc.c59
-rw-r--r--net/mctp/af_mctp.c46
-rw-r--r--net/mctp/route.c16
-rw-r--r--net/netfilter/core.c2
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c17
-rw-r--r--net/netfilter/nf_tables_api.c48
-rw-r--r--net/netfilter/nft_bitwise.c4
-rw-r--r--net/netfilter/nft_connlimit.c2
-rw-r--r--net/netfilter/nft_counter.c2
-rw-r--r--net/netfilter/nft_last.c2
-rw-r--r--net/netfilter/nft_limit.c2
-rw-r--r--net/netfilter/nft_quota.c2
-rw-r--r--net/netfilter/nft_socket.c7
-rw-r--r--net/openvswitch/actions.c6
-rw-r--r--net/openvswitch/flow_netlink.c103
-rw-r--r--net/rxrpc/ar-internal.h15
-rw-r--r--net/rxrpc/call_event.c2
-rw-r--r--net/rxrpc/call_object.c40
-rw-r--r--net/rxrpc/net_ns.c2
-rw-r--r--net/rxrpc/server_key.c7
-rw-r--r--net/sched/act_ct.c15
-rw-r--r--net/sched/cls_api.c2
-rw-r--r--net/sched/cls_flower.c18
-rw-r--r--net/sched/sch_taprio.c3
-rw-r--r--net/sctp/outqueue.c6
-rw-r--r--net/sctp/sm_statefuns.c6
-rw-r--r--net/sctp/socket.c2
-rw-r--r--net/smc/af_smc.c14
-rw-r--r--net/smc/smc_clc.c6
-rw-r--r--net/smc/smc_close.c3
-rw-r--r--net/smc/smc_pnet.c5
-rw-r--r--net/smc/smc_sysctl.c5
-rw-r--r--net/sunrpc/auth.c8
-rw-r--r--net/sunrpc/auth_gss/auth_gss.c26
-rw-r--r--net/sunrpc/auth_gss/auth_gss_internal.h2
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_crypto.c10
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_seqnum.c4
-rw-r--r--net/sunrpc/auth_gss/gss_krb5_wrap.c4
-rw-r--r--net/sunrpc/auth_unix.c16
-rw-r--r--net/sunrpc/backchannel_rqst.c8
-rw-r--r--net/sunrpc/clnt.c13
-rw-r--r--net/sunrpc/rpcb_clnt.c4
-rw-r--r--net/sunrpc/sched.c56
-rw-r--r--net/sunrpc/socklib.c3
-rw-r--r--net/sunrpc/sysfs.c76
-rw-r--r--net/sunrpc/xprt.c23
-rw-r--r--net/sunrpc/xprtrdma/frwr_ops.c2
-rw-r--r--net/sunrpc/xprtrdma/transport.c10
-rw-r--r--net/sunrpc/xprtrdma/verbs.c4
-rw-r--r--net/sunrpc/xprtsock.c207
-rw-r--r--net/tls/tls_sw.c2
-rw-r--r--net/x25/af_x25.c11
-rw-r--r--net/xdp/xsk_buff_pool.c8
67 files changed, 718 insertions, 385 deletions
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index 01f8067994d6..77883b6788cd 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -279,13 +279,13 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv)
grant_ref_t ref;
ref = priv->rings[i].intf->ref[j];
- gnttab_end_foreign_access(ref, 0, 0);
+ gnttab_end_foreign_access(ref, 0);
}
free_pages_exact(priv->rings[i].data.in,
1UL << (priv->rings[i].intf->ring_order +
XEN_PAGE_SHIFT));
}
- gnttab_end_foreign_access(priv->rings[i].ref, 0, 0);
+ gnttab_end_foreign_access(priv->rings[i].ref, 0);
free_page((unsigned long)priv->rings[i].intf);
}
kfree(priv->rings);
@@ -353,10 +353,10 @@ static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev,
out:
if (bytes) {
for (i--; i >= 0; i--)
- gnttab_end_foreign_access(ring->intf->ref[i], 0, 0);
+ gnttab_end_foreign_access(ring->intf->ref[i], 0);
free_pages_exact(bytes, 1UL << (order + XEN_PAGE_SHIFT));
}
- gnttab_end_foreign_access(ring->ref, 0, 0);
+ gnttab_end_foreign_access(ring->ref, 0);
free_page((unsigned long)ring->intf);
return ret;
}
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 992b6e5d85d7..363d47f94532 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -991,10 +991,6 @@ static int ax25_release(struct socket *sock)
sock_orphan(sk);
ax25 = sk_to_ax25(sk);
ax25_dev = ax25->ax25_dev;
- if (ax25_dev) {
- dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker);
- ax25_dev_put(ax25_dev);
- }
if (sk->sk_type == SOCK_SEQPACKET) {
switch (ax25->state) {
@@ -1056,6 +1052,15 @@ static int ax25_release(struct socket *sock)
sk->sk_state_change(sk);
ax25_destroy_socket(ax25);
}
+ if (ax25_dev) {
+ del_timer_sync(&ax25->timer);
+ del_timer_sync(&ax25->t1timer);
+ del_timer_sync(&ax25->t2timer);
+ del_timer_sync(&ax25->t3timer);
+ del_timer_sync(&ax25->idletimer);
+ dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker);
+ ax25_dev_put(ax25_dev);
+ }
sock->sk = NULL;
release_sock(sk);
diff --git a/net/can/isotp.c b/net/can/isotp.c
index f6f8ba1f816d..bafb0fb5f0e0 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1050,7 +1050,7 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int noblock = flags & MSG_DONTWAIT;
int ret = 0;
- if (flags & ~(MSG_DONTWAIT | MSG_TRUNC))
+ if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK))
return -EINVAL;
if (!so->bound)
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index c81379f93ad5..c6e5bfc717d5 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -1773,10 +1773,8 @@ static int prepare_read_data(struct ceph_connection *con)
bv.bv_page = con->bounce_page;
bv.bv_offset = 0;
- set_in_bvec(con, &bv);
- } else {
- set_in_bvec(con, &bv);
}
+ set_in_bvec(con, &bv);
con->v2.in_state = IN_S_PREPARE_READ_DATA_CONT;
return 0;
}
@@ -1807,10 +1805,8 @@ static void prepare_read_data_cont(struct ceph_connection *con)
if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
bv.bv_page = con->bounce_page;
bv.bv_offset = 0;
- set_in_bvec(con, &bv);
- } else {
- set_in_bvec(con, &bv);
}
+ set_in_bvec(con, &bv);
WARN_ON(con->v2.in_state != IN_S_PREPARE_READ_DATA_CONT);
return;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 8a5109479dbe..8c6c08446556 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7193,6 +7193,16 @@ static int __netdev_update_upper_level(struct net_device *dev,
return 0;
}
+#ifdef CONFIG_LOCKDEP
+static LIST_HEAD(net_unlink_list);
+
+static void net_unlink_todo(struct net_device *dev)
+{
+ if (list_empty(&dev->unlink_list))
+ list_add_tail(&dev->unlink_list, &net_unlink_list);
+}
+#endif
+
static int __netdev_update_lower_level(struct net_device *dev,
struct netdev_nested_priv *priv)
{
diff --git a/net/core/filter.c b/net/core/filter.c
index a7044e98765e..64470a727ef7 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7016,24 +7016,33 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
if (!th->ack || th->rst || th->syn)
return -ENOENT;
+ if (unlikely(iph_len < sizeof(struct iphdr)))
+ return -EINVAL;
+
if (tcp_synq_no_recent_overflow(sk))
return -ENOENT;
cookie = ntohl(th->ack_seq) - 1;
- switch (sk->sk_family) {
- case AF_INET:
- if (unlikely(iph_len < sizeof(struct iphdr)))
+ /* Both struct iphdr and struct ipv6hdr have the version field at the
+ * same offset so we can cast to the shorter header (struct iphdr).
+ */
+ switch (((struct iphdr *)iph)->version) {
+ case 4:
+ if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk))
return -EINVAL;
ret = __cookie_v4_check((struct iphdr *)iph, th, cookie);
break;
#if IS_BUILTIN(CONFIG_IPV6)
- case AF_INET6:
+ case 6:
if (unlikely(iph_len < sizeof(struct ipv6hdr)))
return -EINVAL;
+ if (sk->sk_family != AF_INET6)
+ return -EINVAL;
+
ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie);
break;
#endif /* CONFIG_IPV6 */
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 03b6e649c428..6f7ec72016dc 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1032,7 +1032,7 @@ bool __skb_flow_dissect(const struct net *net,
key_eth_addrs = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_ETH_ADDRS,
target_container);
- memcpy(key_eth_addrs, &eth->h_dest, sizeof(*key_eth_addrs));
+ memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs));
}
proto_again:
@@ -1183,6 +1183,7 @@ proto_again:
VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
}
key_vlan->vlan_tpid = saved_vlan_tpid;
+ key_vlan->vlan_eth_type = proto;
}
fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 10bde7c6db44..30b523fa4ad2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5276,11 +5276,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
if (skb_cloned(to))
return false;
- /* The page pool signature of struct page will eventually figure out
- * which pages can be recycled or not but for now let's prohibit slab
- * allocated and page_pool allocated SKBs from being coalesced.
+ /* In general, avoid mixing slab allocated and page_pool allocated
+ * pages within the same SKB. However when @to is not pp_recycle and
+ * @from is cloned, we can transition frag pages from page_pool to
+ * reference counted.
+ *
+ * On the other hand, don't allow coalescing two pp_recycle SKBs if
+ * @from is cloned, in case the SKB is using page_pool fragment
+ * references (PP_FLAG_PAGE_FRAG). Since we only take full page
+ * references for cloned SKBs at the moment that would result in
+ * inconsistent reference counts.
*/
- if (to->pp_recycle != from->pp_recycle)
+ if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from)))
return false;
if (len <= skb_tailroom(to)) {
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index ca6af86964bc..cf933225df32 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -562,7 +562,6 @@ static void dsa_port_teardown(struct dsa_port *dp)
{
struct devlink_port *dlp = &dp->devlink_port;
struct dsa_switch *ds = dp->ds;
- struct net_device *slave;
if (!dp->setup)
return;
@@ -584,11 +583,9 @@ static void dsa_port_teardown(struct dsa_port *dp)
dsa_port_link_unregister_of(dp);
break;
case DSA_PORT_TYPE_USER:
- slave = dp->slave;
-
- if (slave) {
+ if (dp->slave) {
+ dsa_slave_destroy(dp->slave);
dp->slave = NULL;
- dsa_slave_destroy(slave);
}
break;
}
@@ -1147,17 +1144,17 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst)
if (err)
goto teardown_cpu_ports;
- err = dsa_tree_setup_master(dst);
+ err = dsa_tree_setup_ports(dst);
if (err)
goto teardown_switches;
- err = dsa_tree_setup_ports(dst);
+ err = dsa_tree_setup_master(dst);
if (err)
- goto teardown_master;
+ goto teardown_ports;
err = dsa_tree_setup_lags(dst);
if (err)
- goto teardown_ports;
+ goto teardown_master;
dst->setup = true;
@@ -1165,10 +1162,10 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst)
return 0;
-teardown_ports:
- dsa_tree_teardown_ports(dst);
teardown_master:
dsa_tree_teardown_master(dst);
+teardown_ports:
+ dsa_tree_teardown_ports(dst);
teardown_switches:
dsa_tree_teardown_switches(dst);
teardown_cpu_ports:
@@ -1186,10 +1183,10 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst)
dsa_tree_teardown_lags(dst);
- dsa_tree_teardown_ports(dst);
-
dsa_tree_teardown_master(dst);
+ dsa_tree_teardown_ports(dst);
+
dsa_tree_teardown_switches(dst);
dsa_tree_teardown_cpu_ports(dst);
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 991c2930d631..2851e44c4cf0 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -335,11 +335,24 @@ static const struct attribute_group dsa_group = {
.attrs = dsa_slave_attrs,
};
+static void dsa_master_reset_mtu(struct net_device *dev)
+{
+ int err;
+
+ err = dev_set_mtu(dev, ETH_DATA_LEN);
+ if (err)
+ netdev_dbg(dev,
+ "Unable to reset MTU to exclude DSA overheads\n");
+}
+
int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
{
+ const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops;
struct dsa_switch *ds = cpu_dp->ds;
struct device_link *consumer_link;
- int ret;
+ int mtu, ret;
+
+ mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops);
/* The DSA master must use SET_NETDEV_DEV for this to work. */
consumer_link = device_link_add(ds->dev, dev->dev.parent,
@@ -349,6 +362,15 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
"Failed to create a device link to DSA switch %s\n",
dev_name(ds->dev));
+ /* The switch driver may not implement ->port_change_mtu(), case in
+ * which dsa_slave_change_mtu() will not update the master MTU either,
+ * so we need to do that here.
+ */
+ ret = dev_set_mtu(dev, mtu);
+ if (ret)
+ netdev_warn(dev, "error %d setting MTU to %d to include DSA overhead\n",
+ ret, mtu);
+
/* If we use a tagging format that doesn't have an ethertype
* field, make sure that all packets from this point on get
* sent to the tag format's receive function.
@@ -384,6 +406,7 @@ void dsa_master_teardown(struct net_device *dev)
sysfs_remove_group(&dev->dev.kobj, &dsa_group);
dsa_netdev_ops_set(dev, NULL);
dsa_master_ethtool_teardown(dev);
+ dsa_master_reset_mtu(dev);
dsa_master_set_promiscuity(dev, -1);
dev->dsa_ptr = NULL;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index cc8e84ef2ae4..ccb62038f6a4 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -889,8 +889,13 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
}
if (cfg->fc_oif || cfg->fc_gw_family) {
- struct fib_nh *nh = fib_info_nh(fi, 0);
+ struct fib_nh *nh;
+
+ /* cannot match on nexthop object attributes */
+ if (fi->nh)
+ return 1;
+ nh = fib_info_nh(fi, 0);
if (cfg->fc_encap) {
if (fib_encap_match(net, cfg->fc_encap_type,
cfg->fc_encap, nh, cfg, extack))
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e23f058166af..fa63ef2bd99c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -485,7 +485,7 @@ int ip6_forward(struct sk_buff *skb)
goto drop;
if (!net->ipv6.devconf_all->disable_policy &&
- !idev->cnf.disable_policy &&
+ (!idev || !idev->cnf.disable_policy) &&
!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
goto drop;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index a9775c830194..4e74bc61a3db 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1653,7 +1653,6 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
mifi_t mifi;
struct net *net = sock_net(sk);
struct mr_table *mrt;
- bool do_wrmifwhole;
if (sk->sk_type != SOCK_RAW ||
inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
@@ -1761,6 +1760,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
#ifdef CONFIG_IPV6_PIMSM_V2
case MRT6_PIM:
{
+ bool do_wrmifwhole;
int v;
if (optlen != sizeof(v))
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2fa10e60cccd..169e9df6d172 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4484,7 +4484,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
struct inet6_dev *idev;
int type;
- if (netif_is_l3_master(skb->dev) &&
+ 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
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c86256064743..7f555d2e5357 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -275,6 +275,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
{
struct sock *sk = sock->sk;
struct llc_sock *llc = llc_sk(sk);
+ struct net_device *dev = NULL;
struct llc_sap *sap;
int rc = -EINVAL;
@@ -286,16 +287,15 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
goto out;
rc = -ENODEV;
if (sk->sk_bound_dev_if) {
- llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
- if (llc->dev && addr->sllc_arphrd != llc->dev->type) {
- dev_put(llc->dev);
- llc->dev = NULL;
+ dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
+ if (dev && addr->sllc_arphrd != dev->type) {
+ dev_put(dev);
+ dev = NULL;
}
} else
- llc->dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd);
- if (!llc->dev)
+ dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd);
+ if (!dev)
goto out;
- netdev_tracker_alloc(llc->dev, &llc->dev_tracker, GFP_KERNEL);
rc = -EUSERS;
llc->laddr.lsap = llc_ui_autoport();
if (!llc->laddr.lsap)
@@ -304,6 +304,12 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
sap = llc_sap_open(llc->laddr.lsap, NULL);
if (!sap)
goto out;
+
+ /* Note: We do not expect errors from this point. */
+ llc->dev = dev;
+ netdev_tracker_alloc(llc->dev, &llc->dev_tracker, GFP_KERNEL);
+ dev = NULL;
+
memcpy(llc->laddr.mac, llc->dev->dev_addr, IFHWADDRLEN);
memcpy(&llc->addr, addr, sizeof(llc->addr));
/* assign new connection to its SAP */
@@ -311,10 +317,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
sock_reset_flag(sk, SOCK_ZAPPED);
rc = 0;
out:
- if (rc) {
- dev_put_track(llc->dev, &llc->dev_tracker);
- llc->dev = NULL;
- }
+ dev_put(dev);
return rc;
}
@@ -337,6 +340,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
struct sockaddr_llc *addr = (struct sockaddr_llc *)uaddr;
struct sock *sk = sock->sk;
struct llc_sock *llc = llc_sk(sk);
+ struct net_device *dev = NULL;
struct llc_sap *sap;
int rc = -EINVAL;
@@ -352,25 +356,27 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
rc = -ENODEV;
rcu_read_lock();
if (sk->sk_bound_dev_if) {
- llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if);
- if (llc->dev) {
+ dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if);
+ if (dev) {
if (is_zero_ether_addr(addr->sllc_mac))
- memcpy(addr->sllc_mac, llc->dev->dev_addr,
+ memcpy(addr->sllc_mac, dev->dev_addr,
IFHWADDRLEN);
- if (addr->sllc_arphrd != llc->dev->type ||
+ if (addr->sllc_arphrd != dev->type ||
!ether_addr_equal(addr->sllc_mac,
- llc->dev->dev_addr)) {
+ dev->dev_addr)) {
rc = -EINVAL;
- llc->dev = NULL;
+ dev = NULL;
}
}
- } else
- llc->dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd,
+ } else {
+ dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd,
addr->sllc_mac);
- dev_hold_track(llc->dev, &llc->dev_tracker, GFP_ATOMIC);
+ }
+ dev_hold(dev);
rcu_read_unlock();
- if (!llc->dev)
+ if (!dev)
goto out;
+
if (!addr->sllc_sap) {
rc = -EUSERS;
addr->sllc_sap = llc_ui_autoport();
@@ -402,6 +408,12 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
goto out_put;
}
}
+
+ /* Note: We do not expect errors from this point. */
+ llc->dev = dev;
+ netdev_tracker_alloc(llc->dev, &llc->dev_tracker, GFP_KERNEL);
+ dev = NULL;
+
llc->laddr.lsap = addr->sllc_sap;
memcpy(llc->laddr.mac, addr->sllc_mac, IFHWADDRLEN);
memcpy(&llc->addr, addr, sizeof(llc->addr));
@@ -412,10 +424,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
out_put:
llc_sap_put(sap);
out:
- if (rc) {
- dev_put_track(llc->dev, &llc->dev_tracker);
- llc->dev = NULL;
- }
+ dev_put(dev);
release_sock(sk);
return rc;
}
diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index f0702d920d8d..e22b0cbb2f35 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -93,13 +93,13 @@ out_release:
static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
{
DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name);
- const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr);
int rc, addrlen = msg->msg_namelen;
struct sock *sk = sock->sk;
struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
struct mctp_skb_cb *cb;
struct mctp_route *rt;
- struct sk_buff *skb;
+ struct sk_buff *skb = NULL;
+ int hlen;
if (addr) {
const u8 tagbits = MCTP_TAG_MASK | MCTP_TAG_OWNER |
@@ -129,6 +129,34 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
if (addr->smctp_network == MCTP_NET_ANY)
addr->smctp_network = mctp_default_net(sock_net(sk));
+ /* direct addressing */
+ if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) {
+ DECLARE_SOCKADDR(struct sockaddr_mctp_ext *,
+ extaddr, msg->msg_name);
+ struct net_device *dev;
+
+ rc = -EINVAL;
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(sock_net(sk), extaddr->smctp_ifindex);
+ /* check for correct halen */
+ if (dev && extaddr->smctp_halen == dev->addr_len) {
+ hlen = LL_RESERVED_SPACE(dev) + sizeof(struct mctp_hdr);
+ rc = 0;
+ }
+ rcu_read_unlock();
+ if (rc)
+ goto err_free;
+ rt = NULL;
+ } else {
+ rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
+ addr->smctp_addr.s_addr);
+ if (!rt) {
+ rc = -EHOSTUNREACH;
+ goto err_free;
+ }
+ hlen = LL_RESERVED_SPACE(rt->dev->dev) + sizeof(struct mctp_hdr);
+ }
+
skb = sock_alloc_send_skb(sk, hlen + 1 + len,
msg->msg_flags & MSG_DONTWAIT, &rc);
if (!skb)
@@ -147,8 +175,8 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
cb = __mctp_cb(skb);
cb->net = addr->smctp_network;
- /* direct addressing */
- if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) {
+ if (!rt) {
+ /* fill extended address in cb */
DECLARE_SOCKADDR(struct sockaddr_mctp_ext *,
extaddr, msg->msg_name);
@@ -159,17 +187,9 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
}
cb->ifindex = extaddr->smctp_ifindex;
+ /* smctp_halen is checked above */
cb->halen = extaddr->smctp_halen;
memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen);
-
- rt = NULL;
- } else {
- rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
- addr->smctp_addr.s_addr);
- if (!rt) {
- rc = -EHOSTUNREACH;
- goto err_free;
- }
}
rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr,
diff --git a/net/mctp/route.c b/net/mctp/route.c
index d5e7db83fe9d..3b24b8d18b5b 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -503,6 +503,11 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb)
if (cb->ifindex) {
/* direct route; use the hwaddr we stashed in sendmsg */
+ if (cb->halen != skb->dev->addr_len) {
+ /* sanity check, sendmsg should have already caught this */
+ kfree_skb(skb);
+ return -EMSGSIZE;
+ }
daddr = cb->haddr;
} else {
/* If lookup fails let the device handle daddr==NULL */
@@ -512,7 +517,7 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb)
rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol),
daddr, skb->dev->dev_addr, skb->len);
- if (rc) {
+ if (rc < 0) {
kfree_skb(skb);
return -EHOSTUNREACH;
}
@@ -756,7 +761,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
{
const unsigned int hlen = sizeof(struct mctp_hdr);
struct mctp_hdr *hdr, *hdr2;
- unsigned int pos, size;
+ unsigned int pos, size, headroom;
struct sk_buff *skb2;
int rc;
u8 seq;
@@ -770,6 +775,9 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
return -EMSGSIZE;
}
+ /* keep same headroom as the original skb */
+ headroom = skb_headroom(skb);
+
/* we've got the header */
skb_pull(skb, hlen);
@@ -777,7 +785,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
/* size of message payload */
size = min(mtu - hlen, skb->len - pos);
- skb2 = alloc_skb(MCTP_HEADER_MAXLEN + hlen + size, GFP_KERNEL);
+ skb2 = alloc_skb(headroom + hlen + size, GFP_KERNEL);
if (!skb2) {
rc = -ENOMEM;
break;
@@ -793,7 +801,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
skb_set_owner_w(skb2, skb->sk);
/* establish packet */
- skb_reserve(skb2, MCTP_HEADER_MAXLEN);
+ skb_reserve(skb2, headroom);
skb_reset_network_header(skb2);
skb_put(skb2, hlen + size);
skb2->transport_header = skb2->network_header + hlen;
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 9a4feb922cf6..dcf752b55a52 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -58,7 +58,7 @@ static struct nf_hook_entries *allocate_hook_entries_size(u16 num)
if (num == 0)
return NULL;
- e = kvzalloc(alloc, GFP_KERNEL);
+ e = kvzalloc(alloc, GFP_KERNEL_ACCOUNT);
if (e)
e->num_hook_entries = num;
return e;
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index d1582b888c0d..8ec55cd72572 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -341,8 +341,8 @@ static void tcp_options(const struct sk_buff *skb,
if (!ptr)
return;
- state->td_scale =
- state->flags = 0;
+ state->td_scale = 0;
+ state->flags &= IP_CT_TCP_FLAG_BE_LIBERAL;
while (length > 0) {
int opcode=*ptr++;
@@ -862,6 +862,16 @@ static bool tcp_can_early_drop(const struct nf_conn *ct)
return false;
}
+static void nf_ct_tcp_state_reset(struct ip_ct_tcp_state *state)
+{
+ state->td_end = 0;
+ state->td_maxend = 0;
+ state->td_maxwin = 0;
+ state->td_maxack = 0;
+ state->td_scale = 0;
+ state->flags &= IP_CT_TCP_FLAG_BE_LIBERAL;
+}
+
/* Returns verdict for packet, or -1 for invalid. */
int nf_conntrack_tcp_packet(struct nf_conn *ct,
struct sk_buff *skb,
@@ -968,8 +978,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags =
ct->proto.tcp.last_flags;
- memset(&ct->proto.tcp.seen[dir], 0,
- sizeof(struct ip_ct_tcp_state));
+ nf_ct_tcp_state_reset(&ct->proto.tcp.seen[dir]);
break;
}
ct->proto.tcp.last_index = index;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c55ccd3cf2f8..16c3a39689f4 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1192,16 +1192,16 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info,
}
err = -ENOMEM;
- table = kzalloc(sizeof(*table), GFP_KERNEL);
+ table = kzalloc(sizeof(*table), GFP_KERNEL_ACCOUNT);
if (table == NULL)
goto err_kzalloc;
- table->name = nla_strdup(attr, GFP_KERNEL);
+ table->name = nla_strdup(attr, GFP_KERNEL_ACCOUNT);
if (table->name == NULL)
goto err_strdup;
if (nla[NFTA_TABLE_USERDATA]) {
- table->udata = nla_memdup(nla[NFTA_TABLE_USERDATA], GFP_KERNEL);
+ table->udata = nla_memdup(nla[NFTA_TABLE_USERDATA], GFP_KERNEL_ACCOUNT);
if (table->udata == NULL)
goto err_table_udata;
@@ -1882,7 +1882,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net,
struct nft_hook *hook;
int err;
- hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL);
+ hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT);
if (!hook) {
err = -ENOMEM;
goto err_hook_alloc;
@@ -2105,7 +2105,7 @@ static struct nft_rule_blob *nf_tables_chain_alloc_rules(unsigned int size)
if (size > INT_MAX)
return NULL;
- blob = kvmalloc(size, GFP_KERNEL);
+ blob = kvmalloc(size, GFP_KERNEL_ACCOUNT);
if (!blob)
return NULL;
@@ -2205,7 +2205,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
if (err < 0)
return err;
- basechain = kzalloc(sizeof(*basechain), GFP_KERNEL);
+ basechain = kzalloc(sizeof(*basechain), GFP_KERNEL_ACCOUNT);
if (basechain == NULL) {
nft_chain_release_hook(&hook);
return -ENOMEM;
@@ -2235,7 +2235,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
if (flags & NFT_CHAIN_HW_OFFLOAD)
return -EOPNOTSUPP;
- chain = kzalloc(sizeof(*chain), GFP_KERNEL);
+ chain = kzalloc(sizeof(*chain), GFP_KERNEL_ACCOUNT);
if (chain == NULL)
return -ENOMEM;
@@ -2248,7 +2248,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
chain->table = table;
if (nla[NFTA_CHAIN_NAME]) {
- chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL);
+ chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL_ACCOUNT);
} else {
if (!(flags & NFT_CHAIN_BINDING)) {
err = -EINVAL;
@@ -2256,7 +2256,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
}
snprintf(name, sizeof(name), "__chain%llu", ++chain_id);
- chain->name = kstrdup(name, GFP_KERNEL);
+ chain->name = kstrdup(name, GFP_KERNEL_ACCOUNT);
}
if (!chain->name) {
@@ -2265,7 +2265,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
}
if (nla[NFTA_CHAIN_USERDATA]) {
- chain->udata = nla_memdup(nla[NFTA_CHAIN_USERDATA], GFP_KERNEL);
+ chain->udata = nla_memdup(nla[NFTA_CHAIN_USERDATA], GFP_KERNEL_ACCOUNT);
if (chain->udata == NULL) {
err = -ENOMEM;
goto err_destroy_chain;
@@ -2428,7 +2428,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
char *name;
err = -ENOMEM;
- name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL);
+ name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL_ACCOUNT);
if (!name)
goto err;
@@ -2876,7 +2876,7 @@ static struct nft_expr *nft_expr_init(const struct nft_ctx *ctx,
goto err1;
err = -ENOMEM;
- expr = kzalloc(expr_info.ops->size, GFP_KERNEL);
+ expr = kzalloc(expr_info.ops->size, GFP_KERNEL_ACCOUNT);
if (expr == NULL)
goto err2;
@@ -3484,7 +3484,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info,
}
err = -ENOMEM;
- rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL);
+ rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL_ACCOUNT);
if (rule == NULL)
goto err_release_expr;
@@ -3897,7 +3897,7 @@ cont:
free_page((unsigned long)inuse);
}
- set->name = kasprintf(GFP_KERNEL, name, min + n);
+ set->name = kasprintf(GFP_KERNEL_ACCOUNT, name, min + n);
if (!set->name)
return -ENOMEM;
@@ -4461,11 +4461,11 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
alloc_size = sizeof(*set) + size + udlen;
if (alloc_size < size || alloc_size > INT_MAX)
return -ENOMEM;
- set = kvzalloc(alloc_size, GFP_KERNEL);
+ set = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT);
if (!set)
return -ENOMEM;
- name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL);
+ name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL_ACCOUNT);
if (!name) {
err = -ENOMEM;
goto err_set_name;
@@ -5526,7 +5526,7 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set,
int err, i, k;
for (i = 0; i < set->num_exprs; i++) {
- expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL);
+ expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL_ACCOUNT);
if (!expr)
goto err_expr;
@@ -6000,7 +6000,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
err = -ENOMEM;
elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data,
elem.key_end.val.data, elem.data.val.data,
- timeout, expiration, GFP_KERNEL);
+ timeout, expiration, GFP_KERNEL_ACCOUNT);
if (elem.priv == NULL)
goto err_parse_data;
@@ -6244,7 +6244,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
err = -ENOMEM;
elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data,
elem.key_end.val.data, NULL, 0, 0,
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
if (elem.priv == NULL)
goto fail_elem;
@@ -6556,7 +6556,7 @@ static struct nft_object *nft_obj_init(const struct nft_ctx *ctx,
}
err = -ENOMEM;
- obj = kzalloc(sizeof(*obj) + ops->size, GFP_KERNEL);
+ obj = kzalloc(sizeof(*obj) + ops->size, GFP_KERNEL_ACCOUNT);
if (!obj)
goto err2;
@@ -6722,7 +6722,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info,
obj->key.table = table;
obj->handle = nf_tables_alloc_handle(table);
- obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL);
+ obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL_ACCOUNT);
if (!obj->key.name) {
err = -ENOMEM;
goto err_strdup;
@@ -7483,7 +7483,7 @@ static int nf_tables_newflowtable(struct sk_buff *skb,
nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);
- flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL);
+ flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL_ACCOUNT);
if (!flowtable)
return -ENOMEM;
@@ -7491,7 +7491,7 @@ static int nf_tables_newflowtable(struct sk_buff *skb,
flowtable->handle = nf_tables_alloc_handle(table);
INIT_LIST_HEAD(&flowtable->hook_list);
- flowtable->name = nla_strdup(nla[NFTA_FLOWTABLE_NAME], GFP_KERNEL);
+ flowtable->name = nla_strdup(nla[NFTA_FLOWTABLE_NAME], GFP_KERNEL_ACCOUNT);
if (!flowtable->name) {
err = -ENOMEM;
goto err1;
@@ -9363,7 +9363,7 @@ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest)
}
EXPORT_SYMBOL_GPL(nft_parse_u32_check);
-static unsigned int nft_parse_register(const struct nlattr *attr, u32 *preg)
+static int nft_parse_register(const struct nlattr *attr, u32 *preg)
{
unsigned int reg;
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index 38caa66632b4..f590ee1c8a1b 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -290,7 +290,7 @@ static bool nft_bitwise_reduce(struct nft_regs_track *track,
if (!track->regs[priv->sreg].selector)
return false;
- bitwise = nft_expr_priv(expr);
+ bitwise = nft_expr_priv(track->regs[priv->dreg].selector);
if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector &&
track->regs[priv->sreg].num_reg == 0 &&
track->regs[priv->dreg].bitwise &&
@@ -442,7 +442,7 @@ static bool nft_bitwise_fast_reduce(struct nft_regs_track *track,
if (!track->regs[priv->sreg].selector)
return false;
- bitwise = nft_expr_priv(expr);
+ bitwise = nft_expr_priv(track->regs[priv->dreg].selector);
if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector &&
track->regs[priv->dreg].bitwise &&
track->regs[priv->dreg].bitwise->ops == expr->ops &&
diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c
index 9de1462e4ac4..d657f999a11b 100644
--- a/net/netfilter/nft_connlimit.c
+++ b/net/netfilter/nft_connlimit.c
@@ -77,7 +77,7 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx,
invert = true;
}
- priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL);
+ priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL_ACCOUNT);
if (!priv->list)
return -ENOMEM;
diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index da9083605a61..f4d3573e8782 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -62,7 +62,7 @@ static int nft_counter_do_init(const struct nlattr * const tb[],
struct nft_counter __percpu *cpu_stats;
struct nft_counter *this_cpu;
- cpu_stats = alloc_percpu(struct nft_counter);
+ cpu_stats = alloc_percpu_gfp(struct nft_counter, GFP_KERNEL_ACCOUNT);
if (cpu_stats == NULL)
return -ENOMEM;
diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c
index 43d0d4aadb1f..bb15a55dad5c 100644
--- a/net/netfilter/nft_last.c
+++ b/net/netfilter/nft_last.c
@@ -30,7 +30,7 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
u64 last_jiffies;
int err;
- last = kzalloc(sizeof(*last), GFP_KERNEL);
+ last = kzalloc(sizeof(*last), GFP_KERNEL_ACCOUNT);
if (!last)
return -ENOMEM;
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index d4a6cf3cd697..04ea8b9bf202 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -90,7 +90,7 @@ static int nft_limit_init(struct nft_limit_priv *priv,
priv->rate);
}
- priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL);
+ priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT);
if (!priv->limit)
return -ENOMEM;
diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c
index d7db57ed3bc1..e6b0df68feea 100644
--- a/net/netfilter/nft_quota.c
+++ b/net/netfilter/nft_quota.c
@@ -90,7 +90,7 @@ static int nft_quota_do_init(const struct nlattr * const tb[],
return -EOPNOTSUPP;
}
- priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL);
+ priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL_ACCOUNT);
if (!priv->consumed)
return -ENOMEM;
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index bd3792f080ed..6d9e8e0a3a7d 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -37,12 +37,11 @@ static void nft_socket_wildcard(const struct nft_pktinfo *pkt,
#ifdef CONFIG_SOCK_CGROUP_DATA
static noinline bool
-nft_sock_get_eval_cgroupv2(u32 *dest, const struct nft_pktinfo *pkt, u32 level)
+nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo *pkt, u32 level)
{
- struct sock *sk = skb_to_full_sk(pkt->skb);
struct cgroup *cgrp;
- if (!sk || !sk_fullsock(sk) || !net_eq(nft_net(pkt), sock_net(sk)))
+ if (!sk_fullsock(sk))
return false;
cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
@@ -109,7 +108,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
break;
#ifdef CONFIG_SOCK_CGROUP_DATA
case NFT_SOCKET_CGROUPV2:
- if (!nft_sock_get_eval_cgroupv2(dest, pkt, priv->level)) {
+ if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) {
regs->verdict.code = NFT_BREAK;
return;
}
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 780d9e2246f3..1b5d73079dc9 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1051,7 +1051,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb,
int rem = nla_len(attr);
bool dont_clone_flow_key;
- /* The first action is always 'OVS_CLONE_ATTR_ARG'. */
+ /* The first action is always 'OVS_CLONE_ATTR_EXEC'. */
clone_arg = nla_data(attr);
dont_clone_flow_key = nla_get_u32(clone_arg);
actions = nla_next(clone_arg, &rem);
@@ -1539,8 +1539,8 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
pr_warn("%s: deferred action limit reached, drop sample action\n",
ovs_dp_name(dp));
} else { /* Recirc action */
- pr_warn("%s: deferred action limit reached, drop recirc action\n",
- ovs_dp_name(dp));
+ pr_warn("%s: deferred action limit reached, drop recirc action (recirc_id=%#x)\n",
+ ovs_dp_name(dp), recirc_id);
}
}
}
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 5176f6ccac8e..7176156d3844 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2230,8 +2230,8 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
icmpv6_key->icmpv6_type = ntohs(output->tp.src);
icmpv6_key->icmpv6_code = ntohs(output->tp.dst);
- if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION ||
- icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) {
+ if (swkey->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) ||
+ swkey->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
struct ovs_key_nd *nd_key;
nla = nla_reserve(skb, OVS_KEY_ATTR_ND, sizeof(*nd_key));
@@ -2317,6 +2317,62 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size)
return sfa;
}
+static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len);
+
+static void ovs_nla_free_check_pkt_len_action(const struct nlattr *action)
+{
+ const struct nlattr *a;
+ int rem;
+
+ nla_for_each_nested(a, action, rem) {
+ switch (nla_type(a)) {
+ case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL:
+ case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER:
+ ovs_nla_free_nested_actions(nla_data(a), nla_len(a));
+ break;
+ }
+ }
+}
+
+static void ovs_nla_free_clone_action(const struct nlattr *action)
+{
+ const struct nlattr *a = nla_data(action);
+ int rem = nla_len(action);
+
+ switch (nla_type(a)) {
+ case OVS_CLONE_ATTR_EXEC:
+ /* The real list of actions follows this attribute. */
+ a = nla_next(a, &rem);
+ ovs_nla_free_nested_actions(a, rem);
+ break;
+ }
+}
+
+static void ovs_nla_free_dec_ttl_action(const struct nlattr *action)
+{
+ const struct nlattr *a = nla_data(action);
+
+ switch (nla_type(a)) {
+ case OVS_DEC_TTL_ATTR_ACTION:
+ ovs_nla_free_nested_actions(nla_data(a), nla_len(a));
+ break;
+ }
+}
+
+static void ovs_nla_free_sample_action(const struct nlattr *action)
+{
+ const struct nlattr *a = nla_data(action);
+ int rem = nla_len(action);
+
+ switch (nla_type(a)) {
+ case OVS_SAMPLE_ATTR_ARG:
+ /* The real list of actions follows this attribute. */
+ a = nla_next(a, &rem);
+ ovs_nla_free_nested_actions(a, rem);
+ break;
+ }
+}
+
static void ovs_nla_free_set_action(const struct nlattr *a)
{
const struct nlattr *ovs_key = nla_data(a);
@@ -2330,25 +2386,54 @@ static void ovs_nla_free_set_action(const struct nlattr *a)
}
}
-void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len)
{
const struct nlattr *a;
int rem;
- if (!sf_acts)
+ /* Whenever new actions are added, the need to update this
+ * function should be considered.
+ */
+ BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23);
+
+ if (!actions)
return;
- nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) {
+ nla_for_each_attr(a, actions, len, rem) {
switch (nla_type(a)) {
- case OVS_ACTION_ATTR_SET:
- ovs_nla_free_set_action(a);
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+ ovs_nla_free_check_pkt_len_action(a);
+ break;
+
+ case OVS_ACTION_ATTR_CLONE:
+ ovs_nla_free_clone_action(a);
break;
+
case OVS_ACTION_ATTR_CT:
ovs_ct_free_action(a);
break;
+
+ case OVS_ACTION_ATTR_DEC_TTL:
+ ovs_nla_free_dec_ttl_action(a);
+ break;
+
+ case OVS_ACTION_ATTR_SAMPLE:
+ ovs_nla_free_sample_action(a);
+ break;
+
+ case OVS_ACTION_ATTR_SET:
+ ovs_nla_free_set_action(a);
+ break;
}
}
+}
+
+void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+{
+ if (!sf_acts)
+ return;
+ ovs_nla_free_nested_actions(sf_acts->actions, sf_acts->actions_len);
kfree(sf_acts);
}
@@ -3458,7 +3543,9 @@ static int clone_action_to_attr(const struct nlattr *attr,
if (!start)
return -EMSGSIZE;
- err = ovs_nla_put_actions(nla_data(attr), rem, skb);
+ /* Skipping the OVS_CLONE_ATTR_EXEC that is always the first attribute. */
+ attr = nla_next(nla_data(attr), &rem);
+ err = ovs_nla_put_actions(attr, rem, skb);
if (err)
nla_nest_cancel(skb, start);
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 7bd6f8a66a3e..969e532f77a9 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -777,14 +777,12 @@ void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool,
enum rxrpc_propose_ack_trace);
void rxrpc_process_call(struct work_struct *);
-static inline void rxrpc_reduce_call_timer(struct rxrpc_call *call,
- unsigned long expire_at,
- unsigned long now,
- enum rxrpc_timer_trace why)
-{
- trace_rxrpc_timer(call, why, now);
- timer_reduce(&call->timer, expire_at);
-}
+void rxrpc_reduce_call_timer(struct rxrpc_call *call,
+ unsigned long expire_at,
+ unsigned long now,
+ enum rxrpc_timer_trace why);
+
+void rxrpc_delete_call_timer(struct rxrpc_call *call);
/*
* call_object.c
@@ -808,6 +806,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *);
bool __rxrpc_queue_call(struct rxrpc_call *);
bool rxrpc_queue_call(struct rxrpc_call *);
void rxrpc_see_call(struct rxrpc_call *);
+bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op);
void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace);
void rxrpc_put_call(struct rxrpc_call *, enum rxrpc_call_trace);
void rxrpc_cleanup_call(struct rxrpc_call *);
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index df864e692267..22e05de5d1ca 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -310,7 +310,7 @@ recheck_state:
}
if (call->state == RXRPC_CALL_COMPLETE) {
- del_timer_sync(&call->timer);
+ rxrpc_delete_call_timer(call);
goto out_put;
}
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 4eb91d958a48..043508fd8d8a 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -53,10 +53,30 @@ static void rxrpc_call_timer_expired(struct timer_list *t)
if (call->state < RXRPC_CALL_COMPLETE) {
trace_rxrpc_timer(call, rxrpc_timer_expired, jiffies);
- rxrpc_queue_call(call);
+ __rxrpc_queue_call(call);
+ } else {
+ rxrpc_put_call(call, rxrpc_call_put);
+ }
+}
+
+void rxrpc_reduce_call_timer(struct rxrpc_call *call,
+ unsigned long expire_at,
+ unsigned long now,
+ enum rxrpc_timer_trace why)
+{
+ if (rxrpc_try_get_call(call, rxrpc_call_got_timer)) {
+ trace_rxrpc_timer(call, why, now);
+ if (timer_reduce(&call->timer, expire_at))
+ rxrpc_put_call(call, rxrpc_call_put_notimer);
}
}
+void rxrpc_delete_call_timer(struct rxrpc_call *call)
+{
+ if (del_timer_sync(&call->timer))
+ rxrpc_put_call(call, rxrpc_call_put_timer);
+}
+
static struct lock_class_key rxrpc_call_user_mutex_lock_class_key;
/*
@@ -463,6 +483,17 @@ void rxrpc_see_call(struct rxrpc_call *call)
}
}
+bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
+{
+ const void *here = __builtin_return_address(0);
+ int n = atomic_fetch_add_unless(&call->usage, 1, 0);
+
+ if (n == 0)
+ return false;
+ trace_rxrpc_call(call->debug_id, op, n, here, NULL);
+ return true;
+}
+
/*
* Note the addition of a ref on a call.
*/
@@ -510,8 +541,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
spin_unlock_bh(&call->lock);
rxrpc_put_call_slot(call);
-
- del_timer_sync(&call->timer);
+ rxrpc_delete_call_timer(call);
/* Make sure we don't get any more notifications */
write_lock_bh(&rx->recvmsg_lock);
@@ -618,6 +648,8 @@ static void rxrpc_destroy_call(struct work_struct *work)
struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor);
struct rxrpc_net *rxnet = call->rxnet;
+ rxrpc_delete_call_timer(call);
+
rxrpc_put_connection(call->conn);
rxrpc_put_peer(call->peer);
kfree(call->rxtx_buffer);
@@ -652,8 +684,6 @@ void rxrpc_cleanup_call(struct rxrpc_call *call)
memset(&call->sock_node, 0xcd, sizeof(call->sock_node));
- del_timer_sync(&call->timer);
-
ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index 25bbc4cc8b13..f15d6942da45 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -113,8 +113,8 @@ static __net_exit void rxrpc_exit_net(struct net *net)
struct rxrpc_net *rxnet = rxrpc_net(net);
rxnet->live = false;
- del_timer_sync(&rxnet->peer_keepalive_timer);
cancel_work_sync(&rxnet->peer_keepalive_work);
+ del_timer_sync(&rxnet->peer_keepalive_timer);
rxrpc_destroy_all_calls(rxnet);
rxrpc_destroy_all_connections(rxnet);
rxrpc_destroy_all_peers(rxnet);
diff --git a/net/rxrpc/server_key.c b/net/rxrpc/server_key.c
index ead3471307ee..ee269e0e6ee8 100644
--- a/net/rxrpc/server_key.c
+++ b/net/rxrpc/server_key.c
@@ -84,6 +84,9 @@ static int rxrpc_preparse_s(struct key_preparsed_payload *prep)
prep->payload.data[1] = (struct rxrpc_security *)sec;
+ if (!sec->preparse_server_key)
+ return -EINVAL;
+
return sec->preparse_server_key(prep);
}
@@ -91,7 +94,7 @@ static void rxrpc_free_preparse_s(struct key_preparsed_payload *prep)
{
const struct rxrpc_security *sec = prep->payload.data[1];
- if (sec)
+ if (sec && sec->free_preparse_server_key)
sec->free_preparse_server_key(prep);
}
@@ -99,7 +102,7 @@ static void rxrpc_destroy_s(struct key *key)
{
const struct rxrpc_security *sec = key->payload.data[1];
- if (sec)
+ if (sec && sec->destroy_server_key)
sec->destroy_server_key(key);
}
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 6a34f7b80a6d..b1f502fce595 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -666,22 +666,25 @@ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
if (!ct)
return false;
if (!net_eq(net, read_pnet(&ct->ct_net)))
- return false;
+ goto drop_ct;
if (nf_ct_zone(ct)->id != zone_id)
- return false;
+ goto drop_ct;
/* Force conntrack entry direction. */
if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
if (nf_ct_is_confirmed(ct))
nf_ct_kill(ct);
- nf_ct_put(ct);
- nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
-
- return false;
+ goto drop_ct;
}
return true;
+
+drop_ct:
+ nf_ct_put(ct);
+ nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
+
+ return false;
}
/* Trim the skb to the length specified by the IP/IPv6 header,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2957f8f5cea7..f0699f39afdb 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1672,10 +1672,10 @@ static int tcf_chain_tp_insert(struct tcf_chain *chain,
if (chain->flushing)
return -EAGAIN;
+ RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info));
if (*chain_info->pprev == chain->filter_chain)
tcf_chain0_head_change(chain, tp);
tcf_proto_get(tp);
- RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info));
rcu_assign_pointer(*chain_info->pprev, tp);
return 0;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index c80fc49c0da1..ed5e6f08e74a 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1013,6 +1013,7 @@ static int fl_set_key_mpls(struct nlattr **tb,
static void fl_set_key_vlan(struct nlattr **tb,
__be16 ethertype,
int vlan_id_key, int vlan_prio_key,
+ int vlan_next_eth_type_key,
struct flow_dissector_key_vlan *key_val,
struct flow_dissector_key_vlan *key_mask)
{
@@ -1031,6 +1032,11 @@ static void fl_set_key_vlan(struct nlattr **tb,
}
key_val->vlan_tpid = ethertype;
key_mask->vlan_tpid = cpu_to_be16(~0);
+ if (tb[vlan_next_eth_type_key]) {
+ key_val->vlan_eth_type =
+ nla_get_be16(tb[vlan_next_eth_type_key]);
+ key_mask->vlan_eth_type = cpu_to_be16(~0);
+ }
}
static void fl_set_key_flag(u32 flower_key, u32 flower_mask,
@@ -1602,8 +1608,9 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
if (eth_type_vlan(ethertype)) {
fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID,
- TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan,
- &mask->vlan);
+ TCA_FLOWER_KEY_VLAN_PRIO,
+ TCA_FLOWER_KEY_VLAN_ETH_TYPE,
+ &key->vlan, &mask->vlan);
if (tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]) {
ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]);
@@ -1611,6 +1618,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
fl_set_key_vlan(tb, ethertype,
TCA_FLOWER_KEY_CVLAN_ID,
TCA_FLOWER_KEY_CVLAN_PRIO,
+ TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
&key->cvlan, &mask->cvlan);
fl_set_key_val(tb, &key->basic.n_proto,
TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
@@ -3002,13 +3010,13 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
goto nla_put_failure;
if (mask->basic.n_proto) {
- if (mask->cvlan.vlan_tpid) {
+ if (mask->cvlan.vlan_eth_type) {
if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
key->basic.n_proto))
goto nla_put_failure;
- } else if (mask->vlan.vlan_tpid) {
+ } else if (mask->vlan.vlan_eth_type) {
if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE,
- key->basic.n_proto))
+ key->vlan.vlan_eth_type))
goto nla_put_failure;
}
}
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 377f896bdedc..b9c71a304d39 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -417,7 +417,8 @@ static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch,
{
struct taprio_sched *q = qdisc_priv(sch);
- if (skb->sk && sock_flag(skb->sk, SOCK_TXTIME)) {
+ /* sk_flags are only safe to use on full sockets. */
+ if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) {
if (!is_valid_interval(skb, sch))
return qdisc_drop(skb, sch, to_free);
} else if (TXTIME_ASSIST_IS_ENABLED(q->flags)) {
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index a18609f608fb..e213aaf45d67 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -914,6 +914,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
ctx->asoc->base.sk->sk_err = -error;
return;
}
+ ctx->asoc->stats.octrlchunks++;
break;
case SCTP_CID_ABORT:
@@ -938,7 +939,10 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
case SCTP_CID_HEARTBEAT:
if (chunk->pmtu_probe) {
- sctp_packet_singleton(ctx->transport, chunk, ctx->gfp);
+ error = sctp_packet_singleton(ctx->transport,
+ chunk, ctx->gfp);
+ if (!error)
+ ctx->asoc->stats.octrlchunks++;
break;
}
fallthrough;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 7f342bc12735..52edee1322fc 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -781,7 +781,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
}
}
- if (security_sctp_assoc_request(new_asoc, chunk->skb)) {
+ if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) {
sctp_association_free(new_asoc);
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
}
@@ -932,7 +932,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net,
/* Set peer label for connection. */
if (security_sctp_assoc_established((struct sctp_association *)asoc,
- chunk->skb))
+ chunk->head_skb ?: chunk->skb))
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
/* Verify that the chunk length for the COOKIE-ACK is OK.
@@ -2262,7 +2262,7 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook(
}
/* Update socket peer label if first association. */
- if (security_sctp_assoc_request(new_asoc, chunk->skb)) {
+ if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) {
sctp_association_free(new_asoc);
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3e1a9600be5e..7b0427658056 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5636,7 +5636,7 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp)
* Set the daddr and initialize id to something more random and also
* copy over any ip options.
*/
- sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sk);
+ sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sock->sk);
sp->pf->copy_ip_options(sk, sock->sk);
/* Populate the fields of the newsk from the oldsk and migrate the
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index f0d118e9f155..14ddc40149e8 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -121,6 +121,7 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk,
bool *own_req)
{
struct smc_sock *smc;
+ struct sock *child;
smc = smc_clcsock_user_data(sk);
@@ -134,8 +135,17 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk,
}
/* passthrough to original syn recv sock fct */
- return smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash,
- own_req);
+ child = smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash,
+ own_req);
+ /* child must not inherit smc or its ops */
+ if (child) {
+ rcu_assign_sk_user_data(child, NULL);
+
+ /* v4-mapped sockets don't inherit parent ops. Don't restore. */
+ if (inet_csk(child)->icsk_af_ops == inet_csk(sk)->icsk_af_ops)
+ inet_csk(child)->icsk_af_ops = smc->ori_af_ops;
+ }
+ return child;
drop:
dst_release(dst);
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index ce27399b38b1..f9f3f59c79de 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -191,7 +191,8 @@ static int smc_nl_ueid_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq,
flags, SMC_NETLINK_DUMP_UEID);
if (!hdr)
return -ENOMEM;
- snprintf(ueid_str, sizeof(ueid_str), "%s", ueid);
+ memcpy(ueid_str, ueid, SMC_MAX_EID_LEN);
+ ueid_str[SMC_MAX_EID_LEN] = 0;
if (nla_put_string(skb, SMC_NLA_EID_TABLE_ENTRY, ueid_str)) {
genlmsg_cancel(skb, hdr);
return -EMSGSIZE;
@@ -252,7 +253,8 @@ int smc_nl_dump_seid(struct sk_buff *skb, struct netlink_callback *cb)
goto end;
smc_ism_get_system_eid(&seid);
- snprintf(seid_str, sizeof(seid_str), "%s", seid);
+ memcpy(seid_str, seid, SMC_MAX_EID_LEN);
+ seid_str[SMC_MAX_EID_LEN] = 0;
if (nla_put_string(skb, SMC_NLA_SEID_ENTRY, seid_str))
goto err;
read_lock(&smc_clc_eid_table.lock);
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 292e4d904ab6..676cb2333d3c 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -57,6 +57,9 @@ static void smc_close_stream_wait(struct smc_sock *smc, long timeout)
if (!smc_tx_prepared_sends(&smc->conn))
return;
+ /* Send out corked data remaining in sndbuf */
+ smc_tx_pending(&smc->conn);
+
smc->wait_close_tx_prepared = 1;
add_wait_queue(sk_sleep(sk), &wait);
while (!signal_pending(current) && timeout) {
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 7984f8883472..7055ed10e316 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -311,8 +311,9 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name)
list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
if (!strncmp(ibdev->ibdev->name, ib_name,
sizeof(ibdev->ibdev->name)) ||
- !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name,
- IB_DEVICE_NAME_MAX - 1)) {
+ (ibdev->ibdev->dev.parent &&
+ !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name,
+ IB_DEVICE_NAME_MAX - 1))) {
goto out;
}
}
diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c
index bae19419e755..cf3ab1334c00 100644
--- a/net/smc/smc_sysctl.c
+++ b/net/smc/smc_sysctl.c
@@ -61,5 +61,10 @@ err_alloc:
void __net_exit smc_sysctl_net_exit(struct net *net)
{
+ struct ctl_table *table;
+
+ table = net->smc.smc_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->smc.smc_hdr);
+ if (!net_eq(net, &init_net))
+ kfree(table);
}
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index a9f0d17fdb0d..682fcd24bf43 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -615,6 +615,8 @@ rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags)
};
struct rpc_cred *ret;
+ if (RPC_IS_ASYNC(task))
+ lookupflags |= RPCAUTH_LOOKUP_ASYNC;
ret = auth->au_ops->lookup_cred(auth, &acred, lookupflags);
put_cred(acred.cred);
return ret;
@@ -631,6 +633,8 @@ rpcauth_bind_machine_cred(struct rpc_task *task, int lookupflags)
if (!acred.principal)
return NULL;
+ if (RPC_IS_ASYNC(task))
+ lookupflags |= RPCAUTH_LOOKUP_ASYNC;
return auth->au_ops->lookup_cred(auth, &acred, lookupflags);
}
@@ -654,7 +658,7 @@ rpcauth_bindcred(struct rpc_task *task, const struct cred *cred, int flags)
};
if (flags & RPC_TASK_ASYNC)
- lookupflags |= RPCAUTH_LOOKUP_NEW;
+ lookupflags |= RPCAUTH_LOOKUP_NEW | RPCAUTH_LOOKUP_ASYNC;
if (task->tk_op_cred)
/* Task must use exactly this rpc_cred */
new = get_rpccred(task->tk_op_cred);
@@ -666,7 +670,7 @@ rpcauth_bindcred(struct rpc_task *task, const struct cred *cred, int flags)
/* If machine cred couldn't be bound, try a root cred */
if (new)
;
- else if (cred == &machine_cred || (flags & RPC_TASK_ROOTCREDS))
+ else if (cred == &machine_cred)
new = rpcauth_bind_root_cred(task, lookupflags);
else if (flags & RPC_TASK_NULLCREDS)
new = authnull_ops.lookup_cred(NULL, NULL, 0);
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 8eb7e8544815..de7e5b41ab8f 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -146,7 +146,7 @@ gss_alloc_context(void)
{
struct gss_cl_ctx *ctx;
- ctx = kzalloc(sizeof(*ctx), GFP_NOFS);
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (ctx != NULL) {
ctx->gc_proc = RPC_GSS_PROC_DATA;
ctx->gc_seq = 1; /* NetApp 6.4R1 doesn't accept seq. no. 0 */
@@ -209,7 +209,7 @@ gss_fill_context(const void *p, const void *end, struct gss_cl_ctx *ctx, struct
p = ERR_PTR(-EFAULT);
goto err;
}
- ret = gss_import_sec_context(p, seclen, gm, &ctx->gc_gss_ctx, NULL, GFP_NOFS);
+ ret = gss_import_sec_context(p, seclen, gm, &ctx->gc_gss_ctx, NULL, GFP_KERNEL);
if (ret < 0) {
trace_rpcgss_import_ctx(ret);
p = ERR_PTR(ret);
@@ -511,7 +511,7 @@ gss_alloc_msg(struct gss_auth *gss_auth,
int vers;
int err = -ENOMEM;
- gss_msg = kzalloc(sizeof(*gss_msg), GFP_NOFS);
+ gss_msg = kzalloc(sizeof(*gss_msg), GFP_KERNEL);
if (gss_msg == NULL)
goto err;
vers = get_pipe_version(gss_auth->net);
@@ -527,7 +527,7 @@ gss_alloc_msg(struct gss_auth *gss_auth,
gss_msg->auth = gss_auth;
kref_get(&gss_auth->kref);
if (service_name) {
- gss_msg->service_name = kstrdup_const(service_name, GFP_NOFS);
+ gss_msg->service_name = kstrdup_const(service_name, GFP_KERNEL);
if (!gss_msg->service_name) {
err = -ENOMEM;
goto err_put_pipe_version;
@@ -703,7 +703,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
if (mlen > MSG_BUF_MAXSIZE)
goto out;
err = -ENOMEM;
- buf = kmalloc(mlen, GFP_NOFS);
+ buf = kmalloc(mlen, GFP_KERNEL);
if (!buf)
goto out;
@@ -1220,7 +1220,7 @@ gss_dup_cred(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
struct gss_cred *new;
/* Make a copy of the cred so that we can reference count it */
- new = kzalloc(sizeof(*gss_cred), GFP_NOFS);
+ new = kzalloc(sizeof(*gss_cred), GFP_KERNEL);
if (new) {
struct auth_cred acred = {
.cred = gss_cred->gc_base.cr_cred,
@@ -1343,7 +1343,11 @@ gss_hash_cred(struct auth_cred *acred, unsigned int hashbits)
static struct rpc_cred *
gss_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
{
- return rpcauth_lookup_credcache(auth, acred, flags, GFP_NOFS);
+ gfp_t gfp = GFP_KERNEL;
+
+ if (flags & RPCAUTH_LOOKUP_ASYNC)
+ gfp = GFP_NOWAIT | __GFP_NOWARN;
+ return rpcauth_lookup_credcache(auth, acred, flags, gfp);
}
static struct rpc_cred *
@@ -1669,7 +1673,7 @@ gss_validate(struct rpc_task *task, struct xdr_stream *xdr)
if (!p)
goto validate_failed;
- seq = kmalloc(4, GFP_NOFS);
+ seq = kmalloc(4, GFP_KERNEL);
if (!seq)
goto validate_failed;
*seq = cpu_to_be32(task->tk_rqstp->rq_seqno);
@@ -1779,11 +1783,11 @@ alloc_enc_pages(struct rpc_rqst *rqstp)
rqstp->rq_enc_pages
= kmalloc_array(rqstp->rq_enc_pages_num,
sizeof(struct page *),
- GFP_NOFS);
+ GFP_KERNEL);
if (!rqstp->rq_enc_pages)
goto out;
for (i=0; i < rqstp->rq_enc_pages_num; i++) {
- rqstp->rq_enc_pages[i] = alloc_page(GFP_NOFS);
+ rqstp->rq_enc_pages[i] = alloc_page(GFP_KERNEL);
if (rqstp->rq_enc_pages[i] == NULL)
goto out_free;
}
@@ -1987,7 +1991,7 @@ gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred,
if (offset + len > rcv_buf->len)
goto unwrap_failed;
mic.len = len;
- mic.data = kmalloc(len, GFP_NOFS);
+ mic.data = kmalloc(len, GFP_KERNEL);
if (!mic.data)
goto unwrap_failed;
if (read_bytes_from_xdr_buf(rcv_buf, offset, mic.data, mic.len))
diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h
index f6d9631bd9d0..c53b329092d4 100644
--- a/net/sunrpc/auth_gss/auth_gss_internal.h
+++ b/net/sunrpc/auth_gss/auth_gss_internal.h
@@ -35,7 +35,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest)
if (unlikely(q > end || q < p))
return ERR_PTR(-EFAULT);
if (len) {
- dest->data = kmemdup(p, len, GFP_NOFS);
+ dest->data = kmemdup(p, len, GFP_KERNEL);
if (unlikely(dest->data == NULL))
return ERR_PTR(-ENOMEM);
} else
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 634b6c6e0dcb..3ea58175e159 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -161,7 +161,7 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
return GSS_S_FAILURE;
}
- checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS);
+ checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_KERNEL);
if (checksumdata == NULL)
return GSS_S_FAILURE;
@@ -169,7 +169,7 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
if (IS_ERR(tfm))
goto out_free_cksum;
- req = ahash_request_alloc(tfm, GFP_NOFS);
+ req = ahash_request_alloc(tfm, GFP_KERNEL);
if (!req)
goto out_free_ahash;
@@ -257,7 +257,7 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen,
return GSS_S_FAILURE;
}
- checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS);
+ checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_KERNEL);
if (!checksumdata)
return GSS_S_FAILURE;
@@ -265,7 +265,7 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen,
if (IS_ERR(tfm))
goto out_free_cksum;
- req = ahash_request_alloc(tfm, GFP_NOFS);
+ req = ahash_request_alloc(tfm, GFP_KERNEL);
if (!req)
goto out_free_ahash;
@@ -554,7 +554,7 @@ gss_krb5_cts_crypt(struct crypto_sync_skcipher *cipher, struct xdr_buf *buf,
WARN_ON(0);
return -ENOMEM;
}
- data = kmalloc(GSS_KRB5_MAX_BLOCKSIZE * 2, GFP_NOFS);
+ data = kmalloc(GSS_KRB5_MAX_BLOCKSIZE * 2, GFP_KERNEL);
if (!data)
return -ENOMEM;
diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
index fb117817ff5d..3200b971a814 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
@@ -49,7 +49,7 @@ krb5_make_seq_num(struct krb5_ctx *kctx,
unsigned char *plain;
s32 code;
- plain = kmalloc(8, GFP_NOFS);
+ plain = kmalloc(8, GFP_KERNEL);
if (!plain)
return -ENOMEM;
@@ -80,7 +80,7 @@ krb5_get_seq_num(struct krb5_ctx *kctx,
dprintk("RPC: krb5_get_seq_num:\n");
- plain = kmalloc(8, GFP_NOFS);
+ plain = kmalloc(8, GFP_KERNEL);
if (!plain)
return -ENOMEM;
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index e95c009bb869..5f96e75f9eec 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -409,7 +409,7 @@ static u32
gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset,
struct xdr_buf *buf, struct page **pages)
{
- u8 *ptr, *plainhdr;
+ u8 *ptr;
time64_t now;
u8 flags = 0x00;
__be16 *be16ptr;
@@ -426,7 +426,7 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset,
return GSS_S_FAILURE;
/* construct gss token header */
- ptr = plainhdr = buf->head[0].iov_base + offset;
+ ptr = buf->head[0].iov_base + offset;
*ptr++ = (unsigned char) ((KG2_TOK_WRAP>>8) & 0xff);
*ptr++ = (unsigned char) (KG2_TOK_WRAP & 0xff);
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index e7df1f782b2e..1e091d3fa607 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -40,11 +40,19 @@ unx_destroy(struct rpc_auth *auth)
/*
* Lookup AUTH_UNIX creds for current process
*/
-static struct rpc_cred *
-unx_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
+static struct rpc_cred *unx_lookup_cred(struct rpc_auth *auth,
+ struct auth_cred *acred, int flags)
{
- struct rpc_cred *ret = mempool_alloc(unix_pool, GFP_NOFS);
-
+ struct rpc_cred *ret;
+
+ ret = kmalloc(sizeof(*ret), rpc_task_gfp_mask());
+ if (!ret) {
+ if (!(flags & RPCAUTH_LOOKUP_ASYNC))
+ return ERR_PTR(-ENOMEM);
+ ret = mempool_alloc(unix_pool, GFP_NOWAIT);
+ if (!ret)
+ return ERR_PTR(-ENOMEM);
+ }
rpcauth_init_cred(ret, acred, auth, &unix_credops);
ret->cr_flags = 1UL << RPCAUTH_CRED_UPTODATE;
return ret;
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 22a2c235abf1..5a6b61dcdf2d 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -75,9 +75,9 @@ static int xprt_alloc_xdr_buf(struct xdr_buf *buf, gfp_t gfp_flags)
return 0;
}
-static
-struct rpc_rqst *xprt_alloc_bc_req(struct rpc_xprt *xprt, gfp_t gfp_flags)
+static struct rpc_rqst *xprt_alloc_bc_req(struct rpc_xprt *xprt)
{
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
struct rpc_rqst *req;
/* Pre-allocate one backchannel rpc_rqst */
@@ -154,7 +154,7 @@ int xprt_setup_bc(struct rpc_xprt *xprt, unsigned int min_reqs)
INIT_LIST_HEAD(&tmp_list);
for (i = 0; i < min_reqs; i++) {
/* Pre-allocate one backchannel rpc_rqst */
- req = xprt_alloc_bc_req(xprt, GFP_KERNEL);
+ req = xprt_alloc_bc_req(xprt);
if (req == NULL) {
printk(KERN_ERR "Failed to create bc rpc_rqst\n");
goto out_free;
@@ -343,7 +343,7 @@ found:
break;
} else if (req)
break;
- new = xprt_alloc_bc_req(xprt, GFP_KERNEL);
+ new = xprt_alloc_bc_req(xprt);
} while (new);
return req;
}
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index c83fe618767c..8bf2af8546d2 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1065,7 +1065,9 @@ rpc_task_get_next_xprt(struct rpc_clnt *clnt)
static
void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt)
{
- if (task->tk_xprt)
+ if (task->tk_xprt &&
+ !(test_bit(XPRT_OFFLINE, &task->tk_xprt->state) &&
+ (task->tk_flags & RPC_TASK_MOVEABLE)))
return;
if (task->tk_flags & RPC_TASK_NO_ROUND_ROBIN)
task->tk_xprt = rpc_task_get_first_xprt(clnt);
@@ -1085,8 +1087,6 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt)
task->tk_flags |= RPC_TASK_TIMEOUT;
if (clnt->cl_noretranstimeo)
task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT;
- if (atomic_read(&clnt->cl_swapper))
- task->tk_flags |= RPC_TASK_SWAPPER;
/* Add to the client's list of all tasks */
spin_lock(&clnt->cl_lock);
list_add_tail(&task->tk_task, &clnt->cl_tasks);
@@ -1745,6 +1745,9 @@ call_refreshresult(struct rpc_task *task)
task->tk_cred_retry--;
trace_rpc_retry_refresh_status(task);
return;
+ case -ENOMEM:
+ rpc_delay(task, HZ >> 4);
+ return;
}
trace_rpc_refresh_status(task);
rpc_call_rpcerror(task, status);
@@ -2793,7 +2796,7 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt,
return -EINVAL;
}
- data = kmalloc(sizeof(*data), GFP_NOFS);
+ data = kmalloc(sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
data->xps = xprt_switch_get(xps);
@@ -3068,6 +3071,8 @@ rpc_clnt_swap_activate_callback(struct rpc_clnt *clnt,
int
rpc_clnt_swap_activate(struct rpc_clnt *clnt)
{
+ while (clnt != clnt->cl_parent)
+ clnt = clnt->cl_parent;
if (atomic_inc_return(&clnt->cl_swapper) == 1)
return rpc_clnt_iterate_for_each_xprt(clnt,
rpc_clnt_swap_activate_callback, NULL);
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 647b323cc1d5..5a8e6d46809a 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -714,7 +714,7 @@ void rpcb_getport_async(struct rpc_task *task)
goto bailout_nofree;
}
- map = kzalloc(sizeof(struct rpcbind_args), GFP_NOFS);
+ map = kzalloc(sizeof(struct rpcbind_args), rpc_task_gfp_mask());
if (!map) {
status = -ENOMEM;
goto bailout_release_client;
@@ -730,7 +730,7 @@ void rpcb_getport_async(struct rpc_task *task)
case RPCBVERS_4:
case RPCBVERS_3:
map->r_netid = xprt->address_strings[RPC_DISPLAY_NETID];
- map->r_addr = rpc_sockaddr2uaddr(sap, GFP_NOFS);
+ map->r_addr = rpc_sockaddr2uaddr(sap, rpc_task_gfp_mask());
if (!map->r_addr) {
status = -ENOMEM;
goto bailout_free_args;
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index e2c835482791..b258b87a3ec2 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -57,6 +57,13 @@ struct workqueue_struct *rpciod_workqueue __read_mostly;
struct workqueue_struct *xprtiod_workqueue __read_mostly;
EXPORT_SYMBOL_GPL(xprtiod_workqueue);
+gfp_t rpc_task_gfp_mask(void)
+{
+ if (current->flags & PF_WQ_WORKER)
+ return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
+ return GFP_KERNEL;
+}
+
unsigned long
rpc_task_timeout(const struct rpc_task *task)
{
@@ -186,11 +193,6 @@ static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue,
/*
* Add new request to wait queue.
- *
- * Swapper tasks always get inserted at the head of the queue.
- * This should avoid many nasty memory deadlocks and hopefully
- * improve overall performance.
- * Everyone else gets appended to the queue to ensure proper FIFO behavior.
*/
static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
struct rpc_task *task,
@@ -199,8 +201,6 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
INIT_LIST_HEAD(&task->u.tk_wait.timer_list);
if (RPC_IS_PRIORITY(queue))
__rpc_add_wait_queue_priority(queue, task, queue_priority);
- else if (RPC_IS_SWAPPER(task))
- list_add(&task->u.tk_wait.list, &queue->tasks[0]);
else
list_add_tail(&task->u.tk_wait.list, &queue->tasks[0]);
task->tk_waitqueue = queue;
@@ -876,6 +876,15 @@ void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata)
ops->rpc_release(calldata);
}
+static bool xprt_needs_memalloc(struct rpc_xprt *xprt, struct rpc_task *tk)
+{
+ if (!xprt)
+ return false;
+ if (!atomic_read(&xprt->swapper))
+ return false;
+ return test_bit(XPRT_LOCKED, &xprt->state) && xprt->snd_task == tk;
+}
+
/*
* This is the RPC `scheduler' (or rather, the finite state machine).
*/
@@ -884,6 +893,7 @@ static void __rpc_execute(struct rpc_task *task)
struct rpc_wait_queue *queue;
int task_is_async = RPC_IS_ASYNC(task);
int status = 0;
+ unsigned long pflags = current->flags;
WARN_ON_ONCE(RPC_IS_QUEUED(task));
if (RPC_IS_QUEUED(task))
@@ -906,6 +916,10 @@ static void __rpc_execute(struct rpc_task *task)
}
if (!do_action)
break;
+ if (RPC_IS_SWAPPER(task) ||
+ xprt_needs_memalloc(task->tk_xprt, task))
+ current->flags |= PF_MEMALLOC;
+
trace_rpc_task_run_action(task, do_action);
do_action(task);
@@ -943,7 +957,7 @@ static void __rpc_execute(struct rpc_task *task)
rpc_clear_running(task);
spin_unlock(&queue->lock);
if (task_is_async)
- return;
+ goto out;
/* sync task: sleep here */
trace_rpc_task_sync_sleep(task, task->tk_action);
@@ -967,6 +981,8 @@ static void __rpc_execute(struct rpc_task *task)
/* Release all resources associated with the task */
rpc_release_task(task);
+out:
+ current_restore_flags(pflags, PF_MEMALLOC);
}
/*
@@ -1021,15 +1037,15 @@ int rpc_malloc(struct rpc_task *task)
struct rpc_rqst *rqst = task->tk_rqstp;
size_t size = rqst->rq_callsize + rqst->rq_rcvsize;
struct rpc_buffer *buf;
- gfp_t gfp = GFP_NOFS;
-
- if (RPC_IS_SWAPPER(task))
- gfp = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN;
+ gfp_t gfp = rpc_task_gfp_mask();
size += sizeof(struct rpc_buffer);
- if (size <= RPC_BUFFER_MAXSIZE)
- buf = mempool_alloc(rpc_buffer_mempool, gfp);
- else
+ if (size <= RPC_BUFFER_MAXSIZE) {
+ buf = kmem_cache_alloc(rpc_buffer_slabp, gfp);
+ /* Reach for the mempool if dynamic allocation fails */
+ if (!buf && RPC_IS_ASYNC(task))
+ buf = mempool_alloc(rpc_buffer_mempool, GFP_NOWAIT);
+ } else
buf = kmalloc(size, gfp);
if (!buf)
@@ -1092,10 +1108,14 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
rpc_init_task_statistics(task);
}
-static struct rpc_task *
-rpc_alloc_task(void)
+static struct rpc_task *rpc_alloc_task(void)
{
- return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOFS);
+ struct rpc_task *task;
+
+ task = kmem_cache_alloc(rpc_task_slabp, rpc_task_gfp_mask());
+ if (task)
+ return task;
+ return mempool_alloc(rpc_task_mempool, GFP_NOWAIT);
}
/*
diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c
index d52313af82bc..05b38bf68316 100644
--- a/net/sunrpc/socklib.c
+++ b/net/sunrpc/socklib.c
@@ -15,6 +15,7 @@
#include <linux/pagemap.h>
#include <linux/udp.h>
#include <linux/sunrpc/msg_prot.h>
+#include <linux/sunrpc/sched.h>
#include <linux/sunrpc/xdr.h>
#include <linux/export.h>
@@ -222,7 +223,7 @@ static int xprt_send_pagedata(struct socket *sock, struct msghdr *msg,
{
int err;
- err = xdr_alloc_bvec(xdr, GFP_KERNEL);
+ err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask());
if (err < 0)
return err;
diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c
index 05c758da6a92..a3a2f8aeb80e 100644
--- a/net/sunrpc/sysfs.c
+++ b/net/sunrpc/sysfs.c
@@ -93,11 +93,14 @@ static ssize_t rpc_sysfs_xprt_dstaddr_show(struct kobject *kobj,
struct rpc_xprt *xprt = rpc_sysfs_xprt_kobj_get_xprt(kobj);
ssize_t ret;
- if (!xprt)
- return 0;
+ if (!xprt) {
+ ret = sprintf(buf, "<closed>\n");
+ goto out;
+ }
ret = sprintf(buf, "%s\n", xprt->address_strings[RPC_DISPLAY_ADDR]);
xprt_put(xprt);
- return ret + 1;
+out:
+ return ret;
}
static ssize_t rpc_sysfs_xprt_srcaddr_show(struct kobject *kobj,
@@ -105,41 +108,45 @@ static ssize_t rpc_sysfs_xprt_srcaddr_show(struct kobject *kobj,
char *buf)
{
struct rpc_xprt *xprt = rpc_sysfs_xprt_kobj_get_xprt(kobj);
- struct sockaddr_storage saddr;
- struct sock_xprt *sock;
- ssize_t ret = -1;
+ size_t buflen = PAGE_SIZE;
+ ssize_t ret;
if (!xprt || !xprt_connected(xprt)) {
- xprt_put(xprt);
- return -ENOTCONN;
- }
-
- sock = container_of(xprt, struct sock_xprt, xprt);
- mutex_lock(&sock->recv_mutex);
- if (sock->sock == NULL ||
- kernel_getsockname(sock->sock, (struct sockaddr *)&saddr) < 0)
- goto out;
-
- ret = sprintf(buf, "%pISc\n", &saddr);
-out:
- mutex_unlock(&sock->recv_mutex);
+ ret = sprintf(buf, "<closed>\n");
+ } else if (xprt->ops->get_srcaddr) {
+ ret = xprt->ops->get_srcaddr(xprt, buf, buflen);
+ if (ret > 0) {
+ if (ret < buflen - 1) {
+ buf[ret] = '\n';
+ ret++;
+ buf[ret] = '\0';
+ }
+ } else
+ ret = sprintf(buf, "<closed>\n");
+ } else
+ ret = sprintf(buf, "<not a socket>\n");
xprt_put(xprt);
- return ret + 1;
+ return ret;
}
static ssize_t rpc_sysfs_xprt_info_show(struct kobject *kobj,
- struct kobj_attribute *attr,
- char *buf)
+ struct kobj_attribute *attr, char *buf)
{
struct rpc_xprt *xprt = rpc_sysfs_xprt_kobj_get_xprt(kobj);
+ unsigned short srcport = 0;
+ size_t buflen = PAGE_SIZE;
ssize_t ret;
if (!xprt || !xprt_connected(xprt)) {
- xprt_put(xprt);
- return -ENOTCONN;
+ ret = sprintf(buf, "<closed>\n");
+ goto out;
}
- ret = sprintf(buf, "last_used=%lu\ncur_cong=%lu\ncong_win=%lu\n"
+ if (xprt->ops->get_srcport)
+ srcport = xprt->ops->get_srcport(xprt);
+
+ ret = snprintf(buf, buflen,
+ "last_used=%lu\ncur_cong=%lu\ncong_win=%lu\n"
"max_num_slots=%u\nmin_num_slots=%u\nnum_reqs=%u\n"
"binding_q_len=%u\nsending_q_len=%u\npending_q_len=%u\n"
"backlog_q_len=%u\nmain_xprt=%d\nsrc_port=%u\n"
@@ -147,14 +154,12 @@ static ssize_t rpc_sysfs_xprt_info_show(struct kobject *kobj,
xprt->last_used, xprt->cong, xprt->cwnd, xprt->max_reqs,
xprt->min_reqs, xprt->num_reqs, xprt->binding.qlen,
xprt->sending.qlen, xprt->pending.qlen,
- xprt->backlog.qlen, xprt->main,
- (xprt->xprt_class->ident == XPRT_TRANSPORT_TCP) ?
- get_srcport(xprt) : 0,
+ xprt->backlog.qlen, xprt->main, srcport,
atomic_long_read(&xprt->queuelen),
- (xprt->xprt_class->ident == XPRT_TRANSPORT_TCP) ?
- xprt->address_strings[RPC_DISPLAY_PORT] : "0");
+ xprt->address_strings[RPC_DISPLAY_PORT]);
+out:
xprt_put(xprt);
- return ret + 1;
+ return ret;
}
static ssize_t rpc_sysfs_xprt_state_show(struct kobject *kobj,
@@ -166,10 +171,7 @@ static ssize_t rpc_sysfs_xprt_state_show(struct kobject *kobj,
int locked, connected, connecting, close_wait, bound, binding,
closing, congested, cwnd_wait, write_space, offline, remove;
- if (!xprt)
- return 0;
-
- if (!xprt->state) {
+ if (!(xprt && xprt->state)) {
ret = sprintf(buf, "state=CLOSED\n");
} else {
locked = test_bit(XPRT_LOCKED, &xprt->state);
@@ -201,7 +203,7 @@ static ssize_t rpc_sysfs_xprt_state_show(struct kobject *kobj,
}
xprt_put(xprt);
- return ret + 1;
+ return ret;
}
static ssize_t rpc_sysfs_xprt_switch_info_show(struct kobject *kobj,
@@ -220,7 +222,7 @@ static ssize_t rpc_sysfs_xprt_switch_info_show(struct kobject *kobj,
xprt_switch->xps_nunique_destaddr_xprts,
atomic_long_read(&xprt_switch->xps_queuelen));
xprt_switch_put(xprt_switch);
- return ret + 1;
+ return ret;
}
static ssize_t rpc_sysfs_xprt_dstaddr_store(struct kobject *kobj,
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 5af484d6ba5e..515501f79290 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1354,17 +1354,6 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
INIT_LIST_HEAD(&req->rq_xmit2);
goto out;
}
- } else if (RPC_IS_SWAPPER(task)) {
- list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) {
- if (pos->rq_cong || pos->rq_bytes_sent)
- continue;
- if (RPC_IS_SWAPPER(pos->rq_task))
- continue;
- /* Note: req is added _before_ pos */
- list_add_tail(&req->rq_xmit, &pos->rq_xmit);
- INIT_LIST_HEAD(&req->rq_xmit2);
- goto out;
- }
} else if (!req->rq_seqno) {
list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) {
if (pos->rq_task->tk_owner != task->tk_owner)
@@ -1503,6 +1492,9 @@ bool xprt_prepare_transmit(struct rpc_task *task)
return false;
}
+ if (atomic_read(&xprt->swapper))
+ /* This will be clear in __rpc_execute */
+ current->flags |= PF_MEMALLOC;
return true;
}
@@ -1692,7 +1684,7 @@ static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt)
goto out;
++xprt->num_reqs;
spin_unlock(&xprt->reserve_lock);
- req = kzalloc(sizeof(struct rpc_rqst), GFP_NOFS);
+ req = kzalloc(sizeof(*req), rpc_task_gfp_mask());
spin_lock(&xprt->reserve_lock);
if (req != NULL)
goto out;
@@ -2112,7 +2104,14 @@ static void xprt_destroy(struct rpc_xprt *xprt)
*/
wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_UNINTERRUPTIBLE);
+ /*
+ * xprt_schedule_autodisconnect() can run after XPRT_LOCKED
+ * is cleared. We use ->transport_lock to ensure the mod_timer()
+ * can only run *before* del_time_sync(), never after.
+ */
+ spin_lock(&xprt->transport_lock);
del_timer_sync(&xprt->timer);
+ spin_unlock(&xprt->transport_lock);
/*
* Destroy sockets etc from the system workqueue so they can
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 515dd7a66a04..3fcd8e1b2550 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -130,7 +130,7 @@ int frwr_mr_init(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr)
if (IS_ERR(frmr))
goto out_mr_err;
- sg = kmalloc_array(depth, sizeof(*sg), GFP_NOFS);
+ sg = kmalloc_array(depth, sizeof(*sg), GFP_KERNEL);
if (!sg)
goto out_list_err;
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 42e375dbdadb..6b7e10e5a141 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -235,8 +235,11 @@ xprt_rdma_connect_worker(struct work_struct *work)
struct rpcrdma_xprt *r_xprt = container_of(work, struct rpcrdma_xprt,
rx_connect_worker.work);
struct rpc_xprt *xprt = &r_xprt->rx_xprt;
+ unsigned int pflags = current->flags;
int rc;
+ if (atomic_read(&xprt->swapper))
+ current->flags |= PF_MEMALLOC;
rc = rpcrdma_xprt_connect(r_xprt);
xprt_clear_connecting(xprt);
if (!rc) {
@@ -250,6 +253,7 @@ xprt_rdma_connect_worker(struct work_struct *work)
rpcrdma_xprt_disconnect(r_xprt);
xprt_unlock_connect(xprt, r_xprt);
xprt_wake_pending_tasks(xprt, rc);
+ current_restore_flags(pflags, PF_MEMALLOC);
}
/**
@@ -517,7 +521,7 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
return;
out_sleep:
- task->tk_status = -EAGAIN;
+ task->tk_status = -ENOMEM;
xprt_add_backlog(xprt, task);
}
@@ -570,8 +574,8 @@ xprt_rdma_allocate(struct rpc_task *task)
gfp_t flags;
flags = RPCRDMA_DEF_GFP;
- if (RPC_IS_SWAPPER(task))
- flags = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN;
+ if (RPC_IS_ASYNC(task))
+ flags = GFP_NOWAIT | __GFP_NOWARN;
if (!rpcrdma_check_regbuf(r_xprt, req->rl_sendbuf, rqst->rq_callsize,
flags))
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 7b5fce2faa10..2fbe9aaeec34 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -373,7 +373,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt)
struct rpcrdma_ep *ep;
int rc;
- ep = kzalloc(sizeof(*ep), GFP_NOFS);
+ ep = kzalloc(sizeof(*ep), GFP_KERNEL);
if (!ep)
return -ENOTCONN;
ep->re_xprt = &r_xprt->rx_xprt;
@@ -746,7 +746,7 @@ rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt)
struct rpcrdma_mr *mr;
int rc;
- mr = kzalloc(sizeof(*mr), GFP_NOFS);
+ mr = kzalloc(sizeof(*mr), GFP_KERNEL);
if (!mr)
break;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 0f39e08ee580..78af7518f263 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -58,6 +58,7 @@
#include "sunrpc.h"
static void xs_close(struct rpc_xprt *xprt);
+static void xs_set_srcport(struct sock_xprt *transport, struct socket *sock);
static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
struct socket *sock);
@@ -427,9 +428,9 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags,
offset += want;
}
- want = xs_alloc_sparse_pages(buf,
- min_t(size_t, count - offset, buf->page_len),
- GFP_KERNEL);
+ want = xs_alloc_sparse_pages(
+ buf, min_t(size_t, count - offset, buf->page_len),
+ GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
if (seek < want) {
ret = xs_read_bvec(sock, msg, flags, buf->bvec,
xdr_buf_pagecount(buf),
@@ -763,12 +764,12 @@ xs_stream_start_connect(struct sock_xprt *transport)
/**
* xs_nospace - handle transmit was incomplete
* @req: pointer to RPC request
+ * @transport: pointer to struct sock_xprt
*
*/
-static int xs_nospace(struct rpc_rqst *req)
+static int xs_nospace(struct rpc_rqst *req, struct sock_xprt *transport)
{
- struct rpc_xprt *xprt = req->rq_xprt;
- struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ struct rpc_xprt *xprt = &transport->xprt;
struct sock *sk = transport->inet;
int ret = -EAGAIN;
@@ -780,24 +781,44 @@ static int xs_nospace(struct rpc_rqst *req)
/* Don't race with disconnect */
if (xprt_connected(xprt)) {
/* wait for more buffer space */
+ set_bit(XPRT_SOCK_NOSPACE, &transport->sock_state);
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk->sk_write_pending++;
xprt_wait_for_buffer_space(xprt);
} else
ret = -ENOTCONN;
spin_unlock(&xprt->transport_lock);
+ return ret;
+}
- /* Race breaker in case memory is freed before above code is called */
- if (ret == -EAGAIN) {
- struct socket_wq *wq;
+static int xs_sock_nospace(struct rpc_rqst *req)
+{
+ struct sock_xprt *transport =
+ container_of(req->rq_xprt, struct sock_xprt, xprt);
+ struct sock *sk = transport->inet;
+ int ret = -EAGAIN;
- rcu_read_lock();
- wq = rcu_dereference(sk->sk_wq);
- set_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags);
- rcu_read_unlock();
+ lock_sock(sk);
+ if (!sock_writeable(sk))
+ ret = xs_nospace(req, transport);
+ release_sock(sk);
+ return ret;
+}
- sk->sk_write_space(sk);
- }
+static int xs_stream_nospace(struct rpc_rqst *req, bool vm_wait)
+{
+ struct sock_xprt *transport =
+ container_of(req->rq_xprt, struct sock_xprt, xprt);
+ struct sock *sk = transport->inet;
+ int ret = -EAGAIN;
+
+ if (vm_wait)
+ return -ENOBUFS;
+ lock_sock(sk);
+ if (!sk_stream_memory_free(sk))
+ ret = xs_nospace(req, transport);
+ release_sock(sk);
return ret;
}
@@ -805,7 +826,8 @@ static void
xs_stream_prepare_request(struct rpc_rqst *req)
{
xdr_free_bvec(&req->rq_rcv_buf);
- req->rq_task->tk_status = xdr_alloc_bvec(&req->rq_rcv_buf, GFP_KERNEL);
+ req->rq_task->tk_status = xdr_alloc_bvec(
+ &req->rq_rcv_buf, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
}
/*
@@ -851,6 +873,7 @@ static int xs_local_send_request(struct rpc_rqst *req)
struct msghdr msg = {
.msg_flags = XS_SENDMSG_FLAGS,
};
+ bool vm_wait;
unsigned int sent;
int status;
@@ -863,15 +886,14 @@ static int xs_local_send_request(struct rpc_rqst *req)
xs_pktdump("packet data:",
req->rq_svec->iov_base, req->rq_svec->iov_len);
+ vm_wait = sk_stream_is_writeable(transport->inet) ? true : false;
+
req->rq_xtime = ktime_get();
status = xprt_sock_sendmsg(transport->sock, &msg, xdr,
transport->xmit.offset, rm, &sent);
dprintk("RPC: %s(%u) = %d\n",
__func__, xdr->len - transport->xmit.offset, status);
- if (status == -EAGAIN && sock_writeable(transport->inet))
- status = -ENOBUFS;
-
if (likely(sent > 0) || status == 0) {
transport->xmit.offset += sent;
req->rq_bytes_sent = transport->xmit.offset;
@@ -881,13 +903,12 @@ static int xs_local_send_request(struct rpc_rqst *req)
return 0;
}
status = -EAGAIN;
+ vm_wait = false;
}
switch (status) {
- case -ENOBUFS:
- break;
case -EAGAIN:
- status = xs_nospace(req);
+ status = xs_stream_nospace(req, vm_wait);
break;
default:
dprintk("RPC: sendmsg returned unrecognized error %d\n",
@@ -963,7 +984,7 @@ process_status:
/* Should we call xs_close() here? */
break;
case -EAGAIN:
- status = xs_nospace(req);
+ status = xs_sock_nospace(req);
break;
case -ENETUNREACH:
case -ENOBUFS:
@@ -1005,7 +1026,7 @@ static int xs_tcp_send_request(struct rpc_rqst *req)
struct msghdr msg = {
.msg_flags = XS_SENDMSG_FLAGS,
};
- bool vm_wait = false;
+ bool vm_wait;
unsigned int sent;
int status;
@@ -1025,12 +1046,17 @@ static int xs_tcp_send_request(struct rpc_rqst *req)
if (test_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state))
xs_tcp_set_socket_timeouts(xprt, transport->sock);
+ xs_set_srcport(transport, transport->sock);
+
/* Continue transmitting the packet/record. We must be careful
* to cope with writespace callbacks arriving _after_ we have
* called sendmsg(). */
req->rq_xtime = ktime_get();
tcp_sock_set_cork(transport->inet, true);
- while (1) {
+
+ vm_wait = sk_stream_is_writeable(transport->inet) ? true : false;
+
+ do {
status = xprt_sock_sendmsg(transport->sock, &msg, xdr,
transport->xmit.offset, rm, &sent);
@@ -1051,31 +1077,10 @@ static int xs_tcp_send_request(struct rpc_rqst *req)
WARN_ON_ONCE(sent == 0 && status == 0);
- if (status == -EAGAIN ) {
- /*
- * Return EAGAIN if we're sure we're hitting the
- * socket send buffer limits.
- */
- if (test_bit(SOCK_NOSPACE, &transport->sock->flags))
- break;
- /*
- * Did we hit a memory allocation failure?
- */
- if (sent == 0) {
- status = -ENOBUFS;
- if (vm_wait)
- break;
- /* Retry, knowing now that we're below the
- * socket send buffer limit
- */
- vm_wait = true;
- }
- continue;
- }
- if (status < 0)
- break;
- vm_wait = false;
- }
+ if (sent > 0)
+ vm_wait = false;
+
+ } while (status == 0);
switch (status) {
case -ENOTSOCK:
@@ -1083,7 +1088,7 @@ static int xs_tcp_send_request(struct rpc_rqst *req)
/* Should we call xs_close() here? */
break;
case -EAGAIN:
- status = xs_nospace(req);
+ status = xs_stream_nospace(req, vm_wait);
break;
case -ECONNRESET:
case -ECONNREFUSED:
@@ -1124,6 +1129,7 @@ static void xs_sock_reset_state_flags(struct rpc_xprt *xprt)
clear_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state);
clear_bit(XPRT_SOCK_WAKE_WRITE, &transport->sock_state);
clear_bit(XPRT_SOCK_WAKE_DISCONNECT, &transport->sock_state);
+ clear_bit(XPRT_SOCK_NOSPACE, &transport->sock_state);
}
static void xs_run_error_worker(struct sock_xprt *transport, unsigned int nr)
@@ -1470,7 +1476,6 @@ static void xs_tcp_state_change(struct sock *sk)
static void xs_write_space(struct sock *sk)
{
- struct socket_wq *wq;
struct sock_xprt *transport;
struct rpc_xprt *xprt;
@@ -1481,15 +1486,10 @@ static void xs_write_space(struct sock *sk)
if (unlikely(!(xprt = xprt_from_sock(sk))))
return;
transport = container_of(xprt, struct sock_xprt, xprt);
- rcu_read_lock();
- wq = rcu_dereference(sk->sk_wq);
- if (!wq || test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags) == 0)
- goto out;
-
+ if (!test_and_clear_bit(XPRT_SOCK_NOSPACE, &transport->sock_state))
+ return;
xs_run_error_worker(transport, XPRT_SOCK_WAKE_WRITE);
sk->sk_write_pending--;
-out:
- rcu_read_unlock();
}
/**
@@ -1638,7 +1638,7 @@ static int xs_get_srcport(struct sock_xprt *transport)
return port;
}
-unsigned short get_srcport(struct rpc_xprt *xprt)
+static unsigned short xs_sock_srcport(struct rpc_xprt *xprt)
{
struct sock_xprt *sock = container_of(xprt, struct sock_xprt, xprt);
unsigned short ret = 0;
@@ -1648,7 +1648,25 @@ unsigned short get_srcport(struct rpc_xprt *xprt)
mutex_unlock(&sock->recv_mutex);
return ret;
}
-EXPORT_SYMBOL(get_srcport);
+
+static int xs_sock_srcaddr(struct rpc_xprt *xprt, char *buf, size_t buflen)
+{
+ struct sock_xprt *sock = container_of(xprt, struct sock_xprt, xprt);
+ union {
+ struct sockaddr sa;
+ struct sockaddr_storage st;
+ } saddr;
+ int ret = -ENOTCONN;
+
+ mutex_lock(&sock->recv_mutex);
+ if (sock->sock) {
+ ret = kernel_getsockname(sock->sock, &saddr.sa);
+ if (ret >= 0)
+ ret = snprintf(buf, buflen, "%pISc", &saddr.sa);
+ }
+ mutex_unlock(&sock->recv_mutex);
+ return ret;
+}
static unsigned short xs_next_srcport(struct sock_xprt *transport, unsigned short port)
{
@@ -1830,7 +1848,6 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt,
sk->sk_user_data = xprt;
sk->sk_data_ready = xs_data_ready;
sk->sk_write_space = xs_udp_write_space;
- sock_set_flag(sk, SOCK_FASYNC);
sk->sk_error_report = xs_error_report;
xprt_clear_connected(xprt);
@@ -1936,9 +1953,9 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task)
#if IS_ENABLED(CONFIG_SUNRPC_SWAP)
/*
- * Note that this should be called with XPRT_LOCKED held (or when we otherwise
- * know that we have exclusive access to the socket), to guard against
- * races with xs_reset_transport.
+ * Note that this should be called with XPRT_LOCKED held, or recv_mutex
+ * held, or when we otherwise know that we have exclusive access to the
+ * socket, to guard against races with xs_reset_transport.
*/
static void xs_set_memalloc(struct rpc_xprt *xprt)
{
@@ -1967,13 +1984,11 @@ xs_enable_swap(struct rpc_xprt *xprt)
{
struct sock_xprt *xs = container_of(xprt, struct sock_xprt, xprt);
- if (atomic_inc_return(&xprt->swapper) != 1)
- return 0;
- if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE))
- return -ERESTARTSYS;
- if (xs->inet)
+ mutex_lock(&xs->recv_mutex);
+ if (atomic_inc_return(&xprt->swapper) == 1 &&
+ xs->inet)
sk_set_memalloc(xs->inet);
- xprt_release_xprt(xprt, NULL);
+ mutex_unlock(&xs->recv_mutex);
return 0;
}
@@ -1989,13 +2004,11 @@ xs_disable_swap(struct rpc_xprt *xprt)
{
struct sock_xprt *xs = container_of(xprt, struct sock_xprt, xprt);
- if (!atomic_dec_and_test(&xprt->swapper))
- return;
- if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE))
- return;
- if (xs->inet)
+ mutex_lock(&xs->recv_mutex);
+ if (atomic_dec_and_test(&xprt->swapper) &&
+ xs->inet)
sk_clear_memalloc(xs->inet);
- xprt_release_xprt(xprt, NULL);
+ mutex_unlock(&xs->recv_mutex);
}
#else
static void xs_set_memalloc(struct rpc_xprt *xprt)
@@ -2028,7 +2041,6 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
sk->sk_user_data = xprt;
sk->sk_data_ready = xs_data_ready;
sk->sk_write_space = xs_udp_write_space;
- sock_set_flag(sk, SOCK_FASYNC);
xprt_set_connected(xprt);
@@ -2052,7 +2064,10 @@ static void xs_udp_setup_socket(struct work_struct *work)
struct rpc_xprt *xprt = &transport->xprt;
struct socket *sock;
int status = -EIO;
+ unsigned int pflags = current->flags;
+ if (atomic_read(&xprt->swapper))
+ current->flags |= PF_MEMALLOC;
sock = xs_create_sock(xprt, transport,
xs_addr(xprt)->sa_family, SOCK_DGRAM,
IPPROTO_UDP, false);
@@ -2072,6 +2087,7 @@ out:
xprt_clear_connecting(xprt);
xprt_unlock_connect(xprt, transport);
xprt_wake_pending_tasks(xprt, status);
+ current_restore_flags(pflags, PF_MEMALLOC);
}
/**
@@ -2191,7 +2207,6 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
sk->sk_data_ready = xs_data_ready;
sk->sk_state_change = xs_tcp_state_change;
sk->sk_write_space = xs_tcp_write_space;
- sock_set_flag(sk, SOCK_FASYNC);
sk->sk_error_report = xs_error_report;
/* socket options */
@@ -2231,11 +2246,19 @@ static void xs_tcp_setup_socket(struct work_struct *work)
struct socket *sock = transport->sock;
struct rpc_xprt *xprt = &transport->xprt;
int status;
+ unsigned int pflags = current->flags;
- if (!sock) {
- sock = xs_create_sock(xprt, transport,
- xs_addr(xprt)->sa_family, SOCK_STREAM,
- IPPROTO_TCP, true);
+ if (atomic_read(&xprt->swapper))
+ current->flags |= PF_MEMALLOC;
+
+ if (xprt_connected(xprt))
+ goto out;
+ if (test_and_clear_bit(XPRT_SOCK_CONNECT_SENT,
+ &transport->sock_state) ||
+ !sock) {
+ xs_reset_transport(transport);
+ sock = xs_create_sock(xprt, transport, xs_addr(xprt)->sa_family,
+ SOCK_STREAM, IPPROTO_TCP, true);
if (IS_ERR(sock)) {
xprt_wake_pending_tasks(xprt, PTR_ERR(sock));
goto out;
@@ -2255,10 +2278,9 @@ static void xs_tcp_setup_socket(struct work_struct *work)
sock->sk->sk_state);
switch (status) {
case 0:
- xs_set_srcport(transport, sock);
- fallthrough;
case -EINPROGRESS:
/* SYN_SENT! */
+ set_bit(XPRT_SOCK_CONNECT_SENT, &transport->sock_state);
if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
fallthrough;
@@ -2296,6 +2318,7 @@ out:
xprt_clear_connecting(xprt);
out_unlock:
xprt_unlock_connect(xprt, transport);
+ current_restore_flags(pflags, PF_MEMALLOC);
}
/**
@@ -2319,13 +2342,9 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport));
- if (transport->sock != NULL && !xprt_connecting(xprt)) {
+ if (transport->sock != NULL) {
dprintk("RPC: xs_connect delayed xprt %p for %lu "
- "seconds\n",
- xprt, xprt->reestablish_timeout / HZ);
-
- /* Start by resetting any existing state */
- xs_reset_transport(transport);
+ "seconds\n", xprt, xprt->reestablish_timeout / HZ);
delay = xprt_reconnect_delay(xprt);
xprt_reconnect_backoff(xprt, XS_TCP_INIT_REEST_TO);
@@ -2487,7 +2506,7 @@ static int bc_malloc(struct rpc_task *task)
return -EINVAL;
}
- page = alloc_page(GFP_KERNEL);
+ page = alloc_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
if (!page)
return -ENOMEM;
@@ -2621,6 +2640,8 @@ static const struct rpc_xprt_ops xs_udp_ops = {
.rpcbind = rpcb_getport_async,
.set_port = xs_set_port,
.connect = xs_connect,
+ .get_srcaddr = xs_sock_srcaddr,
+ .get_srcport = xs_sock_srcport,
.buf_alloc = rpc_malloc,
.buf_free = rpc_free,
.send_request = xs_udp_send_request,
@@ -2643,6 +2664,8 @@ static const struct rpc_xprt_ops xs_tcp_ops = {
.rpcbind = rpcb_getport_async,
.set_port = xs_set_port,
.connect = xs_connect,
+ .get_srcaddr = xs_sock_srcaddr,
+ .get_srcport = xs_sock_srcport,
.buf_alloc = rpc_malloc,
.buf_free = rpc_free,
.prepare_request = xs_stream_prepare_request,
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 0024a692f0f8..a8976ef95528 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1496,7 +1496,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
if (prot->version == TLS_1_3_VERSION ||
prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305)
memcpy(iv + iv_offset, tls_ctx->rx.iv,
- crypto_aead_ivsize(ctx->aead_recv));
+ prot->iv_size + prot->salt_size);
else
memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size);
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 3583354a7d7f..3a171828638b 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1765,10 +1765,15 @@ void x25_kill_by_neigh(struct x25_neigh *nb)
write_lock_bh(&x25_list_lock);
- sk_for_each(s, &x25_list)
- if (x25_sk(s)->neighbour == nb)
+ sk_for_each(s, &x25_list) {
+ if (x25_sk(s)->neighbour == nb) {
+ write_unlock_bh(&x25_list_lock);
+ lock_sock(s);
x25_disconnect(s, ENETUNREACH, 0, 0);
-
+ release_sock(s);
+ write_lock_bh(&x25_list_lock);
+ }
+ }
write_unlock_bh(&x25_list_lock);
/* Remove any related forwards */
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index b34fca6ada86..af040ffa14ff 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -591,9 +591,13 @@ u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
u32 nb_entries1 = 0, nb_entries2;
if (unlikely(pool->dma_need_sync)) {
+ struct xdp_buff *buff;
+
/* Slow path */
- *xdp = xp_alloc(pool);
- return !!*xdp;
+ buff = xp_alloc(pool);
+ if (buff)
+ *xdp = buff;
+ return !!buff;
}
if (unlikely(pool->free_list_cnt)) {