summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2019-02-09 02:00:17 +0300
committerDavid S. Miller <davem@davemloft.net>2019-02-09 02:00:17 +0300
commita655fe9f194842693258f43b5382855db1c2f654 (patch)
treea6e523c42378f43881c421530941dcbb529461ab /net
parent7499a288bf1a4a49be9d72beb0a5c7b9aa6ffec9 (diff)
parent27b4ad621e887ce8e5eb508a0103f13d30f6b38a (diff)
downloadlinux-a655fe9f194842693258f43b5382855db1c2f654.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
An ipvlan bug fix in 'net' conflicted with the abstraction away of the IPV6 specific support in 'net-next'. Similarly, a bug fix for mlx5 in 'net' conflicted with the flow action conversion in 'net-next'. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/batman-adv/bat_v_elp.c3
-rw-r--r--net/batman-adv/hard-interface.c5
-rw-r--r--net/batman-adv/soft-interface.c2
-rw-r--r--net/core/filter.c2
-rw-r--r--net/core/skmsg.c3
-rw-r--r--net/dccp/ccid.h4
-rw-r--r--net/dsa/master.c4
-rw-r--r--net/dsa/slave.c17
-rw-r--r--net/ipv4/ip_gre.c7
-rw-r--r--net/ipv6/ip6_gre.c7
-rw-r--r--net/ipv6/netfilter.c4
-rw-r--r--net/ipv6/seg6_iptunnel.c2
-rw-r--r--net/ipv6/sit.c3
-rw-r--r--net/l2tp/l2tp_core.c9
-rw-r--r--net/l2tp/l2tp_core.h20
-rw-r--r--net/l2tp/l2tp_ip.c3
-rw-r--r--net/l2tp/l2tp_ip6.c3
-rw-r--r--net/mac80211/tx.c12
-rw-r--r--net/netfilter/nf_conntrack_core.c16
-rw-r--r--net/netfilter/nf_tables_api.c85
-rw-r--r--net/netfilter/nft_compat.c62
-rw-r--r--net/netfilter/nft_dynset.c18
-rw-r--r--net/netfilter/nft_immediate.c6
-rw-r--r--net/netfilter/nft_lookup.c18
-rw-r--r--net/netfilter/nft_objref.c18
-rw-r--r--net/rds/bind.c6
-rw-r--r--net/rxrpc/recvmsg.c3
-rw-r--r--net/sched/cls_flower.c6
-rw-r--r--net/sctp/socket.c4
-rw-r--r--net/sctp/stream.c20
-rw-r--r--net/smc/af_smc.c11
-rw-r--r--net/smc/smc_cdc.c21
-rw-r--r--net/smc/smc_cdc.h34
-rw-r--r--net/smc/smc_clc.c2
-rw-r--r--net/smc/smc_close.c9
-rw-r--r--net/smc/smc_core.c6
-rw-r--r--net/smc/smc_core.h20
-rw-r--r--net/smc/smc_ib.c6
-rw-r--r--net/smc/smc_llc.c3
-rw-r--r--net/smc/smc_pnet.c2
-rw-r--r--net/smc/smc_tx.c64
-rw-r--r--net/smc/smc_wr.c46
-rw-r--r--net/smc/smc_wr.h1
-rw-r--r--net/socket.c82
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_sendto.c105
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c9
-rw-r--r--net/vmw_vsock/virtio_transport.c29
-rw-r--r--net/wireless/ap.c2
-rw-r--r--net/wireless/core.h2
-rw-r--r--net/wireless/sme.c2
50 files changed, 576 insertions, 252 deletions
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index 7b80f6f8d4dc..a9b7919c9de5 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -104,6 +104,9 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh)
ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo);
+ /* free the TID stats immediately */
+ cfg80211_sinfo_release_content(&sinfo);
+
dev_put(real_netdev);
if (ret == -ENOENT) {
/* Node is not associated anymore! It would be
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 28c1fb8d1af0..96ef7c70b4d9 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -20,7 +20,6 @@
#include "main.h"
#include <linux/atomic.h>
-#include <linux/bug.h>
#include <linux/byteorder/generic.h>
#include <linux/errno.h>
#include <linux/gfp.h>
@@ -179,8 +178,10 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
parent_dev = __dev_get_by_index((struct net *)parent_net,
dev_get_iflink(net_dev));
/* if we got a NULL parent_dev there is something broken.. */
- if (WARN(!parent_dev, "Cannot find parent device"))
+ if (!parent_dev) {
+ pr_err("Cannot find parent device\n");
return false;
+ }
if (batadv_mutual_parents(net_dev, net, parent_dev, parent_net))
return false;
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index b14fb3462af7..93a5975c21a4 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -222,6 +222,8 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
netif_trans_update(soft_iface);
vid = batadv_get_vid(skb, 0);
+
+ skb_reset_mac_header(skb);
ethhdr = eth_hdr(skb);
proto = ethhdr->h_proto;
diff --git a/net/core/filter.c b/net/core/filter.c
index 3a49f68eda10..b5a002d7b263 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4112,10 +4112,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
/* Only some socketops are supported */
switch (optname) {
case SO_RCVBUF:
+ val = min_t(u32, val, sysctl_rmem_max);
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
break;
case SO_SNDBUF:
+ val = min_t(u32, val, sysctl_wmem_max);
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
break;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index e76ed8df9f13..ae6f06e45737 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -554,8 +554,7 @@ static void sk_psock_destroy_deferred(struct work_struct *gc)
struct sk_psock *psock = container_of(gc, struct sk_psock, gc);
/* No sk_callback_lock since already detached. */
- if (psock->parser.enabled)
- strp_done(&psock->parser.strp);
+ strp_done(&psock->parser.strp);
cancel_work_sync(&psock->work);
diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h
index 6eb837a47b5c..baaaeb2b2c42 100644
--- a/net/dccp/ccid.h
+++ b/net/dccp/ccid.h
@@ -202,7 +202,7 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk,
static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk,
u8 pkt, u8 opt, u8 *val, u8 len)
{
- if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL)
+ if (!ccid || !ccid->ccid_ops->ccid_hc_tx_parse_options)
return 0;
return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len);
}
@@ -214,7 +214,7 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk,
static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk,
u8 pkt, u8 opt, u8 *val, u8 len)
{
- if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL)
+ if (!ccid || !ccid->ccid_ops->ccid_hc_rx_parse_options)
return 0;
return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len);
}
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 79e97d2f2d9b..c58f33931be1 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -248,6 +248,8 @@ static void dsa_master_reset_mtu(struct net_device *dev)
rtnl_unlock();
}
+static struct lock_class_key dsa_master_addr_list_lock_key;
+
int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
{
int ret;
@@ -261,6 +263,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
wmb();
dev->dsa_ptr = cpu_dp;
+ lockdep_set_class(&dev->addr_list_lock,
+ &dsa_master_addr_list_lock_key);
ret = dsa_master_ethtool_setup(dev);
if (ret)
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 70395a0ae52e..2e5e7c04821b 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -140,11 +140,14 @@ static int dsa_slave_close(struct net_device *dev)
static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
{
struct net_device *master = dsa_slave_to_master(dev);
-
- if (change & IFF_ALLMULTI)
- dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1);
- if (change & IFF_PROMISC)
- dev_set_promiscuity(master, dev->flags & IFF_PROMISC ? 1 : -1);
+ if (dev->flags & IFF_UP) {
+ if (change & IFF_ALLMULTI)
+ dev_set_allmulti(master,
+ dev->flags & IFF_ALLMULTI ? 1 : -1);
+ if (change & IFF_PROMISC)
+ dev_set_promiscuity(master,
+ dev->flags & IFF_PROMISC ? 1 : -1);
+ }
}
static void dsa_slave_set_rx_mode(struct net_device *dev)
@@ -644,7 +647,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e)
int ret;
/* Port's PHY and MAC both need to be EEE capable */
- if (!dev->phydev && !dp->pl)
+ if (!dev->phydev || !dp->pl)
return -ENODEV;
if (!ds->ops->set_mac_eee)
@@ -664,7 +667,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
int ret;
/* Port's PHY and MAC both need to be EEE capable */
- if (!dev->phydev && !dp->pl)
+ if (!dev->phydev || !dp->pl)
return -ENODEV;
if (!ds->ops->get_mac_eee)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index d1cef66820d3..ccee9411dae1 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1381,12 +1381,17 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
struct ip_tunnel_parm *p = &t->parms;
+ __be16 o_flags = p->o_flags;
+
+ if ((t->erspan_ver == 1 || t->erspan_ver == 2) &&
+ !t->collect_md)
+ o_flags |= TUNNEL_KEY;
if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
nla_put_be16(skb, IFLA_GRE_IFLAGS,
gre_tnl_flags_to_gre_flags(p->i_flags)) ||
nla_put_be16(skb, IFLA_GRE_OFLAGS,
- gre_tnl_flags_to_gre_flags(p->o_flags)) ||
+ gre_tnl_flags_to_gre_flags(o_flags)) ||
nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) ||
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index e081e69d534e..65a4f96dc462 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -2098,12 +2098,17 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct __ip6_tnl_parm *p = &t->parms;
+ __be16 o_flags = p->o_flags;
+
+ if ((p->erspan_ver == 1 || p->erspan_ver == 2) &&
+ !p->collect_md)
+ o_flags |= TUNNEL_KEY;
if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
nla_put_be16(skb, IFLA_GRE_IFLAGS,
gre_tnl_flags_to_gre_flags(p->i_flags)) ||
nla_put_be16(skb, IFLA_GRE_OFLAGS,
- gre_tnl_flags_to_gre_flags(p->o_flags)) ||
+ gre_tnl_flags_to_gre_flags(o_flags)) ||
nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) ||
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 8b075f0bc351..6d0b1f3e927b 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -23,9 +23,11 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
struct sock *sk = sk_to_full_sk(skb->sk);
unsigned int hh_len;
struct dst_entry *dst;
+ int strict = (ipv6_addr_type(&iph->daddr) &
+ (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
struct flowi6 fl6 = {
.flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if :
- rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0,
+ strict ? skb_dst(skb)->dev->ifindex : 0,
.flowi6_mark = skb->mark,
.flowi6_uid = sock_net_uid(net, sk),
.daddr = iph->daddr,
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 8181ee7e1e27..ee5403cbe655 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -146,6 +146,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
} else {
ip6_flow_hdr(hdr, 0, flowlabel);
hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb));
+
+ memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
}
hdr->nexthdr = NEXTHDR_ROUTING;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 1e03305c0549..e8a1dabef803 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -546,7 +546,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
}
err = 0;
- if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
+ if (__in6_dev_get(skb->dev) &&
+ !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
goto out;
if (t->parms.iph.daddr == 0)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 26f1d435696a..fed6becc5daf 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -83,8 +83,7 @@
#define L2TP_SLFLAG_S 0x40000000
#define L2TP_SL_SEQ_MASK 0x00ffffff
-#define L2TP_HDR_SIZE_SEQ 10
-#define L2TP_HDR_SIZE_NOSEQ 6
+#define L2TP_HDR_SIZE_MAX 14
/* Default trace flags */
#define L2TP_DEFAULT_DEBUG_FLAGS 0
@@ -808,7 +807,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
__skb_pull(skb, sizeof(struct udphdr));
/* Short packet? */
- if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) {
+ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) {
l2tp_info(tunnel, L2TP_MSG_DATA,
"%s: recv short packet (len=%d)\n",
tunnel->name, skb->len);
@@ -884,6 +883,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
goto error;
}
+ if (tunnel->version == L2TP_HDR_VER_3 &&
+ l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+ goto error;
+
l2tp_recv_common(session, skb, ptr, optr, hdrflags, length);
l2tp_session_dec_refcount(session);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 9c9afe94d389..b2ce90260c35 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -301,6 +301,26 @@ static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel)
}
#endif
+static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb,
+ unsigned char **ptr, unsigned char **optr)
+{
+ int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session);
+
+ if (opt_len > 0) {
+ int off = *ptr - *optr;
+
+ if (!pskb_may_pull(skb, off + opt_len))
+ return -1;
+
+ if (skb->data != *optr) {
+ *optr = skb->data;
+ *ptr = skb->data + off;
+ }
+ }
+
+ return 0;
+}
+
#define l2tp_printk(ptr, type, func, fmt, ...) \
do { \
if (((ptr)->debug) & (type)) \
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 35f6f86d4dcc..d4c60523c549 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -165,6 +165,9 @@ static int l2tp_ip_recv(struct sk_buff *skb)
print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
}
+ if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+ goto discard_sess;
+
l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
l2tp_session_dec_refcount(session);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 237f1a4a0b0c..0ae6899edac0 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -178,6 +178,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
}
+ if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+ goto discard_sess;
+
l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
l2tp_session_dec_refcount(session);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 61c7ea9de2cc..8a49a74c0a37 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1945,9 +1945,16 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
int head_need, bool may_encrypt)
{
struct ieee80211_local *local = sdata->local;
+ struct ieee80211_hdr *hdr;
+ bool enc_tailroom;
int tail_need = 0;
- if (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt) {
+ hdr = (struct ieee80211_hdr *) skb->data;
+ enc_tailroom = may_encrypt &&
+ (sdata->crypto_tx_tailroom_needed_cnt ||
+ ieee80211_is_mgmt(hdr->frame_control));
+
+ if (enc_tailroom) {
tail_need = IEEE80211_ENCRYPT_TAILROOM;
tail_need -= skb_tailroom(skb);
tail_need = max_t(int, tail_need, 0);
@@ -1955,8 +1962,7 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
if (skb_cloned(skb) &&
(!ieee80211_hw_check(&local->hw, SUPPORTS_CLONED_SKBS) ||
- !skb_clone_writable(skb, ETH_HLEN) ||
- (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt)))
+ !skb_clone_writable(skb, ETH_HLEN) || enc_tailroom))
I802_DEBUG_INC(local->tx_expand_skb_head_cloned);
else if (head_need || tail_need)
I802_DEBUG_INC(local->tx_expand_skb_head);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 815956ac5a76..08ee03407ace 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1042,6 +1042,22 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
}
if (nf_ct_key_equal(h, tuple, zone, net)) {
+ /* Tuple is taken already, so caller will need to find
+ * a new source port to use.
+ *
+ * Only exception:
+ * If the *original tuples* are identical, then both
+ * conntracks refer to the same flow.
+ * This is a rare situation, it can occur e.g. when
+ * more than one UDP packet is sent from same socket
+ * in different threads.
+ *
+ * Let nf_ct_resolve_clash() deal with this later.
+ */
+ if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple))
+ continue;
+
NF_CT_STAT_INC_ATOMIC(net, found);
rcu_read_unlock();
return 1;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index e92bedd09cde..5ca5ec8f3cf0 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -131,6 +131,23 @@ static void nft_trans_destroy(struct nft_trans *trans)
kfree(trans);
}
+static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
+{
+ struct net *net = ctx->net;
+ struct nft_trans *trans;
+
+ if (!nft_set_is_anonymous(set))
+ return;
+
+ list_for_each_entry_reverse(trans, &net->nft.commit_list, list) {
+ if (trans->msg_type == NFT_MSG_NEWSET &&
+ nft_trans_set(trans) == set) {
+ nft_trans_set_bound(trans) = true;
+ break;
+ }
+ }
+}
+
static int nf_tables_register_hook(struct net *net,
const struct nft_table *table,
struct nft_chain *chain)
@@ -226,18 +243,6 @@ static int nft_delchain(struct nft_ctx *ctx)
return err;
}
-/* either expr ops provide both activate/deactivate, or neither */
-static bool nft_expr_check_ops(const struct nft_expr_ops *ops)
-{
- if (!ops)
- return true;
-
- if (WARN_ON_ONCE((!ops->activate ^ !ops->deactivate)))
- return false;
-
- return true;
-}
-
static void nft_rule_expr_activate(const struct nft_ctx *ctx,
struct nft_rule *rule)
{
@@ -253,14 +258,15 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx,
}
static void nft_rule_expr_deactivate(const struct nft_ctx *ctx,
- struct nft_rule *rule)
+ struct nft_rule *rule,
+ enum nft_trans_phase phase)
{
struct nft_expr *expr;
expr = nft_expr_first(rule);
while (expr != nft_expr_last(rule) && expr->ops) {
if (expr->ops->deactivate)
- expr->ops->deactivate(ctx, expr);
+ expr->ops->deactivate(ctx, expr, phase);
expr = nft_expr_next(expr);
}
@@ -311,7 +317,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule)
nft_trans_destroy(trans);
return err;
}
- nft_rule_expr_deactivate(ctx, rule);
+ nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE);
return 0;
}
@@ -1972,9 +1978,6 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk,
*/
int nft_register_expr(struct nft_expr_type *type)
{
- if (!nft_expr_check_ops(type->ops))
- return -EINVAL;
-
nfnl_lock(NFNL_SUBSYS_NFTABLES);
if (type->family == NFPROTO_UNSPEC)
list_add_tail_rcu(&type->list, &nf_tables_expressions);
@@ -2122,10 +2125,6 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
err = PTR_ERR(ops);
goto err1;
}
- if (!nft_expr_check_ops(ops)) {
- err = -EINVAL;
- goto err1;
- }
} else
ops = type->ops;
@@ -2554,7 +2553,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
static void nf_tables_rule_release(const struct nft_ctx *ctx,
struct nft_rule *rule)
{
- nft_rule_expr_deactivate(ctx, rule);
+ nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE);
nf_tables_rule_destroy(ctx, rule);
}
@@ -3760,39 +3759,30 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
bind:
binding->chain = ctx->chain;
list_add_tail_rcu(&binding->list, &set->bindings);
+ nft_set_trans_bind(ctx, set);
+
return 0;
}
EXPORT_SYMBOL_GPL(nf_tables_bind_set);
-void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding)
-{
- if (list_empty(&set->bindings) && nft_set_is_anonymous(set) &&
- nft_is_active(ctx->net, set))
- list_add_tail_rcu(&set->list, &ctx->table->sets);
-
- list_add_tail_rcu(&binding->list, &set->bindings);
-}
-EXPORT_SYMBOL_GPL(nf_tables_rebind_set);
-
void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding)
+ struct nft_set_binding *binding, bool event)
{
list_del_rcu(&binding->list);
- if (list_empty(&set->bindings) && nft_set_is_anonymous(set) &&
- nft_is_active(ctx->net, set))
+ if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) {
list_del_rcu(&set->list);
+ if (event)
+ nf_tables_set_notify(ctx, set, NFT_MSG_DELSET,
+ GFP_KERNEL);
+ }
}
EXPORT_SYMBOL_GPL(nf_tables_unbind_set);
void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set)
{
- if (list_empty(&set->bindings) && nft_set_is_anonymous(set) &&
- nft_is_active(ctx->net, set)) {
- nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC);
+ if (list_empty(&set->bindings) && nft_set_is_anonymous(set))
nft_set_destroy(set);
- }
}
EXPORT_SYMBOL_GPL(nf_tables_destroy_set);
@@ -6621,6 +6611,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
nf_tables_rule_notify(&trans->ctx,
nft_trans_rule(trans),
NFT_MSG_DELRULE);
+ nft_rule_expr_deactivate(&trans->ctx,
+ nft_trans_rule(trans),
+ NFT_TRANS_COMMIT);
break;
case NFT_MSG_NEWSET:
nft_clear(net, nft_trans_set(trans));
@@ -6707,7 +6700,8 @@ static void nf_tables_abort_release(struct nft_trans *trans)
nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));
break;
case NFT_MSG_NEWSET:
- nft_set_destroy(nft_trans_set(trans));
+ if (!nft_trans_set_bound(trans))
+ nft_set_destroy(nft_trans_set(trans));
break;
case NFT_MSG_NEWSETELEM:
nft_set_elem_destroy(nft_trans_elem_set(trans),
@@ -6768,7 +6762,9 @@ static int __nf_tables_abort(struct net *net)
case NFT_MSG_NEWRULE:
trans->ctx.chain->use--;
list_del_rcu(&nft_trans_rule(trans)->list);
- nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans));
+ nft_rule_expr_deactivate(&trans->ctx,
+ nft_trans_rule(trans),
+ NFT_TRANS_ABORT);
break;
case NFT_MSG_DELRULE:
trans->ctx.chain->use++;
@@ -6778,7 +6774,8 @@ static int __nf_tables_abort(struct net *net)
break;
case NFT_MSG_NEWSET:
trans->ctx.table->use--;
- list_del_rcu(&nft_trans_set(trans)->list);
+ if (!nft_trans_set_bound(trans))
+ list_del_rcu(&nft_trans_set(trans)->list);
break;
case NFT_MSG_DELSET:
trans->ctx.table->use++;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 5eb269428832..fe64df848365 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -61,6 +61,21 @@ static struct nft_compat_net *nft_compat_pernet(struct net *net)
return net_generic(net, nft_compat_net_id);
}
+static void nft_xt_get(struct nft_xt *xt)
+{
+ /* refcount_inc() warns on 0 -> 1 transition, but we can't
+ * init the reference count to 1 in .select_ops -- we can't
+ * undo such an increase when another expression inside the same
+ * rule fails afterwards.
+ */
+ if (xt->listcnt == 0)
+ refcount_set(&xt->refcnt, 1);
+ else
+ refcount_inc(&xt->refcnt);
+
+ xt->listcnt++;
+}
+
static bool nft_xt_put(struct nft_xt *xt)
{
if (refcount_dec_and_test(&xt->refcnt)) {
@@ -291,7 +306,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
return -EINVAL;
nft_xt = container_of(expr->ops, struct nft_xt, ops);
- refcount_inc(&nft_xt->refcnt);
+ nft_xt_get(nft_xt);
return 0;
}
@@ -504,7 +519,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
return ret;
nft_xt = container_of(expr->ops, struct nft_xt, ops);
- refcount_inc(&nft_xt->refcnt);
+ nft_xt_get(nft_xt);
return 0;
}
@@ -558,41 +573,16 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
__nft_match_destroy(ctx, expr, nft_expr_priv(expr));
}
-static void nft_compat_activate(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- struct list_head *h)
-{
- struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops);
-
- if (xt->listcnt == 0)
- list_add(&xt->head, h);
-
- xt->listcnt++;
-}
-
-static void nft_compat_activate_mt(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
-{
- struct nft_compat_net *cn = nft_compat_pernet(ctx->net);
-
- nft_compat_activate(ctx, expr, &cn->nft_match_list);
-}
-
-static void nft_compat_activate_tg(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
-{
- struct nft_compat_net *cn = nft_compat_pernet(ctx->net);
-
- nft_compat_activate(ctx, expr, &cn->nft_target_list);
-}
-
static void nft_compat_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops);
- if (--xt->listcnt == 0)
- list_del_init(&xt->head);
+ if (phase == NFT_TRANS_ABORT || phase == NFT_TRANS_COMMIT) {
+ if (--xt->listcnt == 0)
+ list_del_init(&xt->head);
+ }
}
static void
@@ -848,7 +838,6 @@ nft_match_select_ops(const struct nft_ctx *ctx,
nft_match->ops.eval = nft_match_eval;
nft_match->ops.init = nft_match_init;
nft_match->ops.destroy = nft_match_destroy;
- nft_match->ops.activate = nft_compat_activate_mt;
nft_match->ops.deactivate = nft_compat_deactivate;
nft_match->ops.dump = nft_match_dump;
nft_match->ops.validate = nft_match_validate;
@@ -866,7 +855,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
nft_match->ops.size = matchsize;
- nft_match->listcnt = 1;
+ nft_match->listcnt = 0;
list_add(&nft_match->head, &cn->nft_match_list);
return &nft_match->ops;
@@ -953,7 +942,6 @@ nft_target_select_ops(const struct nft_ctx *ctx,
nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
nft_target->ops.init = nft_target_init;
nft_target->ops.destroy = nft_target_destroy;
- nft_target->ops.activate = nft_compat_activate_tg;
nft_target->ops.deactivate = nft_compat_deactivate;
nft_target->ops.dump = nft_target_dump;
nft_target->ops.validate = nft_target_validate;
@@ -964,7 +952,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
else
nft_target->ops.eval = nft_target_eval_xt;
- nft_target->listcnt = 1;
+ nft_target->listcnt = 0;
list_add(&nft_target->head, &cn->nft_target_list);
return &nft_target->ops;
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 9658493d37d4..a8a74a16f9c4 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -234,20 +234,17 @@ err1:
return err;
}
-static void nft_dynset_activate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
-{
- struct nft_dynset *priv = nft_expr_priv(expr);
-
- nf_tables_rebind_set(ctx, priv->set, &priv->binding);
-}
-
static void nft_dynset_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_dynset *priv = nft_expr_priv(expr);
- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+ if (phase == NFT_TRANS_PREPARE)
+ return;
+
+ nf_tables_unbind_set(ctx, priv->set, &priv->binding,
+ phase == NFT_TRANS_COMMIT);
}
static void nft_dynset_destroy(const struct nft_ctx *ctx,
@@ -295,7 +292,6 @@ static const struct nft_expr_ops nft_dynset_ops = {
.eval = nft_dynset_eval,
.init = nft_dynset_init,
.destroy = nft_dynset_destroy,
- .activate = nft_dynset_activate,
.deactivate = nft_dynset_deactivate,
.dump = nft_dynset_dump,
};
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 3e5ed787b1d4..5ec43124cbca 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -72,10 +72,14 @@ static void nft_immediate_activate(const struct nft_ctx *ctx,
}
static void nft_immediate_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+ if (phase == NFT_TRANS_COMMIT)
+ return;
+
return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg));
}
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 227b2b15a19c..14496da5141d 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -121,20 +121,17 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
return 0;
}
-static void nft_lookup_activate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
-{
- struct nft_lookup *priv = nft_expr_priv(expr);
-
- nf_tables_rebind_set(ctx, priv->set, &priv->binding);
-}
-
static void nft_lookup_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_lookup *priv = nft_expr_priv(expr);
- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+ if (phase == NFT_TRANS_PREPARE)
+ return;
+
+ nf_tables_unbind_set(ctx, priv->set, &priv->binding,
+ phase == NFT_TRANS_COMMIT);
}
static void nft_lookup_destroy(const struct nft_ctx *ctx,
@@ -225,7 +222,6 @@ static const struct nft_expr_ops nft_lookup_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)),
.eval = nft_lookup_eval,
.init = nft_lookup_init,
- .activate = nft_lookup_activate,
.deactivate = nft_lookup_deactivate,
.destroy = nft_lookup_destroy,
.dump = nft_lookup_dump,
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index c1f2adf198a0..79ef074c18ca 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -156,20 +156,17 @@ nla_put_failure:
return -1;
}
-static void nft_objref_map_activate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
-{
- struct nft_objref_map *priv = nft_expr_priv(expr);
-
- nf_tables_rebind_set(ctx, priv->set, &priv->binding);
-}
-
static void nft_objref_map_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_objref_map *priv = nft_expr_priv(expr);
- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+ if (phase == NFT_TRANS_PREPARE)
+ return;
+
+ nf_tables_unbind_set(ctx, priv->set, &priv->binding,
+ phase == NFT_TRANS_COMMIT);
}
static void nft_objref_map_destroy(const struct nft_ctx *ctx,
@@ -186,7 +183,6 @@ static const struct nft_expr_ops nft_objref_map_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)),
.eval = nft_objref_map_eval,
.init = nft_objref_map_init,
- .activate = nft_objref_map_activate,
.deactivate = nft_objref_map_deactivate,
.destroy = nft_objref_map_destroy,
.dump = nft_objref_map_dump,
diff --git a/net/rds/bind.c b/net/rds/bind.c
index 762d2c6788a3..17c9d9f0c848 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -78,10 +78,10 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port,
__rds_create_bind_key(key, addr, port, scope_id);
rcu_read_lock();
rs = rhashtable_lookup(&bind_hash_table, key, ht_parms);
- if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD))
- rds_sock_addref(rs);
- else
+ if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) ||
+ !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt)))
rs = NULL;
+
rcu_read_unlock();
rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr,
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index eaf19ebaa964..3f7bb11f3290 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -596,6 +596,7 @@ error_requeue_call:
}
error_no_call:
release_sock(&rx->sk);
+error_trace:
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret);
return ret;
@@ -604,7 +605,7 @@ wait_interrupted:
wait_error:
finish_wait(sk_sleep(&rx->sk), &wait);
call = NULL;
- goto error_no_call;
+ goto error_trace;
}
/**
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index c5d1db3a3db7..6a341287a527 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1385,7 +1385,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
if (!tc_skip_hw(fnew->flags)) {
err = fl_hw_replace_filter(tp, fnew, extack);
if (err)
- goto errout_mask;
+ goto errout_mask_ht;
}
if (!tc_in_hw(fnew->flags))
@@ -1415,6 +1415,10 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
kfree(mask);
return 0;
+errout_mask_ht:
+ rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node,
+ fnew->mask->filter_ht_params);
+
errout_mask:
fl_mask_put(head, fnew->mask, false);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9644bdc8e85c..a78e55a1bb9c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2027,7 +2027,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_transport *transport = NULL;
struct sctp_sndrcvinfo _sinfo, *sinfo;
- struct sctp_association *asoc;
+ struct sctp_association *asoc, *tmp;
struct sctp_cmsgs cmsgs;
union sctp_addr *daddr;
bool new = false;
@@ -2053,7 +2053,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
/* SCTP_SENDALL process */
if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) {
- list_for_each_entry(asoc, &ep->asocs, asocs) {
+ list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) {
err = sctp_sendmsg_check_sflags(asoc, sflags, msg,
msg_len);
if (err == 0)
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 80e0ae5534ec..f24633114dfd 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -84,6 +84,19 @@ static void fa_zero(struct flex_array *fa, size_t index, size_t count)
}
}
+static size_t fa_index(struct flex_array *fa, void *elem, size_t count)
+{
+ size_t index = 0;
+
+ while (count--) {
+ if (elem == flex_array_get(fa, index))
+ break;
+ index++;
+ }
+
+ return index;
+}
+
/* Migrates chunks from stream queues to new stream queues if needed,
* but not across associations. Also, removes those chunks to streams
* higher than the new max.
@@ -147,6 +160,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
if (stream->out) {
fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt));
+ if (stream->out_curr) {
+ size_t index = fa_index(stream->out, stream->out_curr,
+ stream->outcnt);
+
+ BUG_ON(index == stream->outcnt);
+ stream->out_curr = flex_array_get(out, index);
+ }
fa_free(stream->out);
}
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 48ea7669161f..46fa9f3016cc 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1523,6 +1523,11 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
smc = smc_sk(sk);
lock_sock(sk);
+ if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) {
+ /* socket was connected before, no more data to read */
+ rc = 0;
+ goto out;
+ }
if ((sk->sk_state == SMC_INIT) ||
(sk->sk_state == SMC_LISTEN) ||
(sk->sk_state == SMC_CLOSED))
@@ -1858,7 +1863,11 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos,
smc = smc_sk(sk);
lock_sock(sk);
-
+ if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) {
+ /* socket was connected before, no more data to read */
+ rc = 0;
+ goto out;
+ }
if (sk->sk_state == SMC_INIT ||
sk->sk_state == SMC_LISTEN ||
sk->sk_state == SMC_CLOSED)
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index db83332ac1c8..a712c9f8699b 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -21,13 +21,6 @@
/********************************** send *************************************/
-struct smc_cdc_tx_pend {
- struct smc_connection *conn; /* socket connection */
- union smc_host_cursor cursor; /* tx sndbuf cursor sent */
- union smc_host_cursor p_cursor; /* rx RMBE cursor produced */
- u16 ctrl_seq; /* conn. tx sequence # */
-};
-
/* handler for send/transmission completion of a CDC msg */
static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
struct smc_link *link,
@@ -61,12 +54,14 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
int smc_cdc_get_free_slot(struct smc_connection *conn,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wr_rdma_buf,
struct smc_cdc_tx_pend **pend)
{
struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
int rc;
rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf,
+ wr_rdma_buf,
(struct smc_wr_tx_pend_priv **)pend);
if (!conn->alert_token_local)
/* abnormal termination */
@@ -96,6 +91,7 @@ int smc_cdc_msg_send(struct smc_connection *conn,
struct smc_wr_buf *wr_buf,
struct smc_cdc_tx_pend *pend)
{
+ union smc_host_cursor cfed;
struct smc_link *link;
int rc;
@@ -107,10 +103,10 @@ int smc_cdc_msg_send(struct smc_connection *conn,
conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf,
&conn->local_tx_ctrl, conn);
+ smc_curs_copy(&cfed, &((struct smc_host_cdc_msg *)wr_buf)->cons, conn);
rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
if (!rc)
- smc_curs_copy(&conn->rx_curs_confirmed,
- &conn->local_tx_ctrl.cons, conn);
+ smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn);
return rc;
}
@@ -121,11 +117,14 @@ static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn)
struct smc_wr_buf *wr_buf;
int rc;
- rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
+ rc = smc_cdc_get_free_slot(conn, &wr_buf, NULL, &pend);
if (rc)
return rc;
- return smc_cdc_msg_send(conn, wr_buf, pend);
+ spin_lock_bh(&conn->send_lock);
+ rc = smc_cdc_msg_send(conn, wr_buf, pend);
+ spin_unlock_bh(&conn->send_lock);
+ return rc;
}
int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index e8c214b992b6..e3b6b367f3b6 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -160,7 +160,9 @@ static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt,
#endif
}
-/* calculate cursor difference between old and new, where old <= new */
+/* calculate cursor difference between old and new, where old <= new and
+ * difference cannot exceed size
+ */
static inline int smc_curs_diff(unsigned int size,
union smc_host_cursor *old,
union smc_host_cursor *new)
@@ -185,6 +187,28 @@ static inline int smc_curs_comp(unsigned int size,
return smc_curs_diff(size, old, new);
}
+/* calculate cursor difference between old and new, where old <= new and
+ * difference may exceed size
+ */
+static inline int smc_curs_diff_large(unsigned int size,
+ union smc_host_cursor *old,
+ union smc_host_cursor *new)
+{
+ if (old->wrap < new->wrap)
+ return min_t(int,
+ (size - old->count) + new->count +
+ (new->wrap - old->wrap - 1) * size,
+ size);
+
+ if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */
+ return min_t(int,
+ (size - old->count) + new->count +
+ (new->wrap + 0xffff - old->wrap) * size,
+ size);
+
+ return max_t(int, 0, (new->count - old->count));
+}
+
static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer,
union smc_host_cursor *local,
struct smc_connection *conn)
@@ -271,10 +295,16 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
smcr_cdc_msg_to_host(local, peer, conn);
}
-struct smc_cdc_tx_pend;
+struct smc_cdc_tx_pend {
+ struct smc_connection *conn; /* socket connection */
+ union smc_host_cursor cursor; /* tx sndbuf cursor sent */
+ union smc_host_cursor p_cursor; /* rx RMBE cursor produced */
+ u16 ctrl_seq; /* conn. tx sequence # */
+};
int smc_cdc_get_free_slot(struct smc_connection *conn,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wr_rdma_buf,
struct smc_cdc_tx_pend **pend);
void smc_cdc_tx_dismiss_slots(struct smc_connection *conn);
int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 776e9dfc915d..d53fd588d1f5 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -378,7 +378,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
vec.iov_len = sizeof(struct smc_clc_msg_decline);
len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
sizeof(struct smc_clc_msg_decline));
- if (len < sizeof(struct smc_clc_msg_decline))
+ if (len < 0 || len < sizeof(struct smc_clc_msg_decline))
len = -EPROTO;
return len > 0 ? 0 : len;
}
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 0e60dd741698..2ad37e998509 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -345,14 +345,7 @@ static void smc_close_passive_work(struct work_struct *work)
switch (sk->sk_state) {
case SMC_INIT:
- if (atomic_read(&conn->bytes_to_rcv) ||
- (rxflags->peer_done_writing &&
- !smc_cdc_rxed_any_close(conn))) {
- sk->sk_state = SMC_APPCLOSEWAIT1;
- } else {
- sk->sk_state = SMC_CLOSED;
- sock_put(sk); /* passive closing */
- }
+ sk->sk_state = SMC_APPCLOSEWAIT1;
break;
case SMC_ACTIVE:
sk->sk_state = SMC_APPCLOSEWAIT1;
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index a1a6d351ae1b..349d789a9728 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -127,6 +127,8 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn)
{
struct smc_link_group *lgr = conn->lgr;
+ if (!lgr)
+ return;
write_lock_bh(&lgr->conns_lock);
if (conn->alert_token_local) {
__smc_lgr_unregister_conn(conn);
@@ -299,13 +301,13 @@ static void smc_buf_unuse(struct smc_connection *conn,
conn->sndbuf_desc->used = 0;
if (conn->rmb_desc) {
if (!conn->rmb_desc->regerr) {
- conn->rmb_desc->used = 0;
if (!lgr->is_smcd) {
/* unregister rmb with peer */
smc_llc_do_delete_rkey(
&lgr->lnk[SMC_SINGLE_LINK],
conn->rmb_desc);
}
+ conn->rmb_desc->used = 0;
} else {
/* buf registration failed, reuse not possible */
write_lock_bh(&lgr->rmbs_lock);
@@ -629,6 +631,8 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
local_contact = SMC_REUSE_CONTACT;
conn->lgr = lgr;
smc_lgr_register_conn(conn); /* add smc conn to lgr */
+ if (delayed_work_pending(&lgr->free_work))
+ cancel_delayed_work(&lgr->free_work);
write_unlock_bh(&lgr->conns_lock);
break;
}
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index b00287989a3d..8806d2afa6ed 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -52,6 +52,24 @@ enum smc_wr_reg_state {
FAILED /* ib_wr_reg_mr response: failure */
};
+struct smc_rdma_sge { /* sges for RDMA writes */
+ struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE];
+};
+
+#define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per
+ * message send
+ */
+
+struct smc_rdma_sges { /* sges per message send */
+ struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES];
+};
+
+struct smc_rdma_wr { /* work requests per message
+ * send
+ */
+ struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES];
+};
+
struct smc_link {
struct smc_ib_device *smcibdev; /* ib-device */
u8 ibport; /* port - values 1 | 2 */
@@ -64,6 +82,8 @@ struct smc_link {
struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */
struct ib_send_wr *wr_tx_ibs; /* WR send meta data */
struct ib_sge *wr_tx_sges; /* WR send gather meta data */
+ struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/
+ struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */
struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */
/* above four vectors have wr_tx_cnt elements and use the same index */
dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index e519ef29c0ff..76487a16934e 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -289,8 +289,8 @@ int smc_ib_create_protection_domain(struct smc_link *lnk)
static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv)
{
- struct smc_ib_device *smcibdev =
- (struct smc_ib_device *)ibevent->device;
+ struct smc_link *lnk = (struct smc_link *)priv;
+ struct smc_ib_device *smcibdev = lnk->smcibdev;
u8 port_idx;
switch (ibevent->event) {
@@ -298,7 +298,7 @@ static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv)
case IB_EVENT_GID_CHANGE:
case IB_EVENT_PORT_ERR:
case IB_EVENT_QP_ACCESS_ERR:
- port_idx = ibevent->element.port_num - 1;
+ port_idx = ibevent->element.qp->port - 1;
set_bit(port_idx, &smcibdev->port_event_mask);
schedule_work(&smcibdev->port_event_work);
break;
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index a6d3623d06f4..4fd60c522802 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -166,7 +166,8 @@ static int smc_llc_add_pending_send(struct smc_link *link,
{
int rc;
- rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, pend);
+ rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, NULL,
+ pend);
if (rc < 0)
return rc;
BUILD_BUG_ON_MSG(
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 7cb3e4f07c10..632c3109dee5 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -27,7 +27,7 @@
static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
[SMC_PNETID_NAME] = {
.type = NLA_NUL_STRING,
- .len = SMC_MAX_PNETID_LEN - 1
+ .len = SMC_MAX_PNETID_LEN
},
[SMC_PNETID_ETHNAME] = {
.type = NLA_NUL_STRING,
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index d8366ed51757..f93f3580c100 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -165,12 +165,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
conn->local_tx_ctrl.prod_flags.urg_data_pending = 1;
if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) {
+ if (send_done)
+ return send_done;
rc = smc_tx_wait(smc, msg->msg_flags);
- if (rc) {
- if (send_done)
- return send_done;
+ if (rc)
goto out_err;
- }
continue;
}
@@ -267,27 +266,23 @@ int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len,
/* sndbuf consumer: actual data transfer of one target chunk with RDMA write */
static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset,
- int num_sges, struct ib_sge sges[])
+ int num_sges, struct ib_rdma_wr *rdma_wr)
{
struct smc_link_group *lgr = conn->lgr;
- struct ib_rdma_wr rdma_wr;
struct smc_link *link;
int rc;
- memset(&rdma_wr, 0, sizeof(rdma_wr));
link = &lgr->lnk[SMC_SINGLE_LINK];
- rdma_wr.wr.wr_id = smc_wr_tx_get_next_wr_id(link);
- rdma_wr.wr.sg_list = sges;
- rdma_wr.wr.num_sge = num_sges;
- rdma_wr.wr.opcode = IB_WR_RDMA_WRITE;
- rdma_wr.remote_addr =
+ rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link);
+ rdma_wr->wr.num_sge = num_sges;
+ rdma_wr->remote_addr =
lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr +
/* RMBE within RMB */
conn->tx_off +
/* offset within RMBE */
peer_rmbe_offset;
- rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey;
- rc = ib_post_send(link->roce_qp, &rdma_wr.wr, NULL);
+ rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey;
+ rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL);
if (rc) {
conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
smc_lgr_terminate(lgr);
@@ -314,24 +309,25 @@ static inline void smc_tx_advance_cursors(struct smc_connection *conn,
/* SMC-R helper for smc_tx_rdma_writes() */
static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len,
size_t src_off, size_t src_len,
- size_t dst_off, size_t dst_len)
+ size_t dst_off, size_t dst_len,
+ struct smc_rdma_wr *wr_rdma_buf)
{
dma_addr_t dma_addr =
sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl);
- struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
int src_len_sum = src_len, dst_len_sum = dst_len;
- struct ib_sge sges[SMC_IB_MAX_SEND_SGE];
int sent_count = src_off;
int srcchunk, dstchunk;
int num_sges;
int rc;
for (dstchunk = 0; dstchunk < 2; dstchunk++) {
+ struct ib_sge *sge =
+ wr_rdma_buf->wr_tx_rdma[dstchunk].wr.sg_list;
+
num_sges = 0;
for (srcchunk = 0; srcchunk < 2; srcchunk++) {
- sges[srcchunk].addr = dma_addr + src_off;
- sges[srcchunk].length = src_len;
- sges[srcchunk].lkey = link->roce_pd->local_dma_lkey;
+ sge[srcchunk].addr = dma_addr + src_off;
+ sge[srcchunk].length = src_len;
num_sges++;
src_off += src_len;
@@ -344,7 +340,8 @@ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len,
src_len = dst_len - src_len; /* remainder */
src_len_sum += src_len;
}
- rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges);
+ rc = smc_tx_rdma_write(conn, dst_off, num_sges,
+ &wr_rdma_buf->wr_tx_rdma[dstchunk]);
if (rc)
return rc;
if (dst_len_sum == len)
@@ -403,7 +400,8 @@ static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len,
/* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit;
* usable snd_wnd as max transmit
*/
-static int smc_tx_rdma_writes(struct smc_connection *conn)
+static int smc_tx_rdma_writes(struct smc_connection *conn,
+ struct smc_rdma_wr *wr_rdma_buf)
{
size_t len, src_len, dst_off, dst_len; /* current chunk values */
union smc_host_cursor sent, prep, prod, cons;
@@ -464,7 +462,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
dst_off, dst_len);
else
rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len,
- dst_off, dst_len);
+ dst_off, dst_len, wr_rdma_buf);
if (rc)
return rc;
@@ -485,31 +483,30 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
{
struct smc_cdc_producer_flags *pflags;
+ struct smc_rdma_wr *wr_rdma_buf;
struct smc_cdc_tx_pend *pend;
struct smc_wr_buf *wr_buf;
int rc;
- spin_lock_bh(&conn->send_lock);
- rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
+ rc = smc_cdc_get_free_slot(conn, &wr_buf, &wr_rdma_buf, &pend);
if (rc < 0) {
if (rc == -EBUSY) {
struct smc_sock *smc =
container_of(conn, struct smc_sock, conn);
- if (smc->sk.sk_err == ECONNABORTED) {
- rc = sock_error(&smc->sk);
- goto out_unlock;
- }
+ if (smc->sk.sk_err == ECONNABORTED)
+ return sock_error(&smc->sk);
rc = 0;
if (conn->alert_token_local) /* connection healthy */
mod_delayed_work(system_wq, &conn->tx_work,
SMC_TX_WORK_DELAY);
}
- goto out_unlock;
+ return rc;
}
+ spin_lock_bh(&conn->send_lock);
if (!conn->local_tx_ctrl.prod_flags.urg_data_present) {
- rc = smc_tx_rdma_writes(conn);
+ rc = smc_tx_rdma_writes(conn, wr_rdma_buf);
if (rc) {
smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK],
(struct smc_wr_tx_pend_priv *)pend);
@@ -536,7 +533,7 @@ static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn)
spin_lock_bh(&conn->send_lock);
if (!pflags->urg_data_present)
- rc = smc_tx_rdma_writes(conn);
+ rc = smc_tx_rdma_writes(conn, NULL);
if (!rc)
rc = smcd_cdc_msg_send(conn);
@@ -598,7 +595,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
if (to_confirm > conn->rmbe_update_limit) {
smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn);
sender_free = conn->rmb_desc->len -
- smc_curs_diff(conn->rmb_desc->len, &prod, &cfed);
+ smc_curs_diff_large(conn->rmb_desc->len,
+ &cfed, &prod);
}
if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index c2694750a6a8..253aa75dc2b6 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -160,6 +160,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx)
* @link: Pointer to smc_link used to later send the message.
* @handler: Send completion handler function pointer.
* @wr_buf: Out value returns pointer to message buffer.
+ * @wr_rdma_buf: Out value returns pointer to rdma work request.
* @wr_pend_priv: Out value returns pointer serving as handler context.
*
* Return: 0 on success, or -errno on error.
@@ -167,6 +168,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx)
int smc_wr_tx_get_free_slot(struct smc_link *link,
smc_wr_tx_handler handler,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wr_rdma_buf,
struct smc_wr_tx_pend_priv **wr_pend_priv)
{
struct smc_wr_tx_pend *wr_pend;
@@ -204,6 +206,8 @@ int smc_wr_tx_get_free_slot(struct smc_link *link,
wr_ib = &link->wr_tx_ibs[idx];
wr_ib->wr_id = wr_id;
*wr_buf = &link->wr_tx_bufs[idx];
+ if (wr_rdma_buf)
+ *wr_rdma_buf = &link->wr_tx_rdmas[idx];
*wr_pend_priv = &wr_pend->priv;
return 0;
}
@@ -218,10 +222,10 @@ int smc_wr_tx_put_slot(struct smc_link *link,
u32 idx = pend->idx;
/* clear the full struct smc_wr_tx_pend including .priv */
- memset(&link->wr_tx_pends[pend->idx], 0,
- sizeof(link->wr_tx_pends[pend->idx]));
- memset(&link->wr_tx_bufs[pend->idx], 0,
- sizeof(link->wr_tx_bufs[pend->idx]));
+ memset(&link->wr_tx_pends[idx], 0,
+ sizeof(link->wr_tx_pends[idx]));
+ memset(&link->wr_tx_bufs[idx], 0,
+ sizeof(link->wr_tx_bufs[idx]));
test_and_clear_bit(idx, link->wr_tx_mask);
return 1;
}
@@ -465,12 +469,26 @@ static void smc_wr_init_sge(struct smc_link *lnk)
lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE;
lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE;
lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[0].lkey =
+ lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[1].lkey =
+ lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[0].lkey =
+ lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[1].lkey =
+ lnk->roce_pd->local_dma_lkey;
lnk->wr_tx_ibs[i].next = NULL;
lnk->wr_tx_ibs[i].sg_list = &lnk->wr_tx_sges[i];
lnk->wr_tx_ibs[i].num_sge = 1;
lnk->wr_tx_ibs[i].opcode = IB_WR_SEND;
lnk->wr_tx_ibs[i].send_flags =
IB_SEND_SIGNALED | IB_SEND_SOLICITED;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list =
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.sg_list =
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge;
}
for (i = 0; i < lnk->wr_rx_cnt; i++) {
lnk->wr_rx_sges[i].addr =
@@ -521,8 +539,12 @@ void smc_wr_free_link_mem(struct smc_link *lnk)
lnk->wr_tx_mask = NULL;
kfree(lnk->wr_tx_sges);
lnk->wr_tx_sges = NULL;
+ kfree(lnk->wr_tx_rdma_sges);
+ lnk->wr_tx_rdma_sges = NULL;
kfree(lnk->wr_rx_sges);
lnk->wr_rx_sges = NULL;
+ kfree(lnk->wr_tx_rdmas);
+ lnk->wr_tx_rdmas = NULL;
kfree(lnk->wr_rx_ibs);
lnk->wr_rx_ibs = NULL;
kfree(lnk->wr_tx_ibs);
@@ -552,10 +574,20 @@ int smc_wr_alloc_link_mem(struct smc_link *link)
GFP_KERNEL);
if (!link->wr_rx_ibs)
goto no_mem_wr_tx_ibs;
+ link->wr_tx_rdmas = kcalloc(SMC_WR_BUF_CNT,
+ sizeof(link->wr_tx_rdmas[0]),
+ GFP_KERNEL);
+ if (!link->wr_tx_rdmas)
+ goto no_mem_wr_rx_ibs;
+ link->wr_tx_rdma_sges = kcalloc(SMC_WR_BUF_CNT,
+ sizeof(link->wr_tx_rdma_sges[0]),
+ GFP_KERNEL);
+ if (!link->wr_tx_rdma_sges)
+ goto no_mem_wr_tx_rdmas;
link->wr_tx_sges = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_sges[0]),
GFP_KERNEL);
if (!link->wr_tx_sges)
- goto no_mem_wr_rx_ibs;
+ goto no_mem_wr_tx_rdma_sges;
link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3,
sizeof(link->wr_rx_sges[0]),
GFP_KERNEL);
@@ -579,6 +611,10 @@ no_mem_wr_rx_sges:
kfree(link->wr_rx_sges);
no_mem_wr_tx_sges:
kfree(link->wr_tx_sges);
+no_mem_wr_tx_rdma_sges:
+ kfree(link->wr_tx_rdma_sges);
+no_mem_wr_tx_rdmas:
+ kfree(link->wr_tx_rdmas);
no_mem_wr_rx_ibs:
kfree(link->wr_rx_ibs);
no_mem_wr_tx_ibs:
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index 1d85bb14fd6f..09bf32fd3959 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -85,6 +85,7 @@ void smc_wr_add_dev(struct smc_ib_device *smcibdev);
int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wrs,
struct smc_wr_tx_pend_priv **wr_pend_priv);
int smc_wr_tx_put_slot(struct smc_link *link,
struct smc_wr_tx_pend_priv *wr_pend_priv);
diff --git a/net/socket.c b/net/socket.c
index d51930689b98..643a1648fcc2 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -963,8 +963,7 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
EXPORT_SYMBOL(dlci_ioctl_set);
static long sock_do_ioctl(struct net *net, struct socket *sock,
- unsigned int cmd, unsigned long arg,
- unsigned int ifreq_size)
+ unsigned int cmd, unsigned long arg)
{
int err;
void __user *argp = (void __user *)arg;
@@ -990,11 +989,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock,
} else {
struct ifreq ifr;
bool need_copyout;
- if (copy_from_user(&ifr, argp, ifreq_size))
+ if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
return -EFAULT;
err = dev_ioctl(net, cmd, &ifr, &need_copyout);
if (!err && need_copyout)
- if (copy_to_user(argp, &ifr, ifreq_size))
+ if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
return -EFAULT;
}
return err;
@@ -1093,8 +1092,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
err = open_related_ns(&net->ns, get_net_ns);
break;
default:
- err = sock_do_ioctl(net, sock, cmd, arg,
- sizeof(struct ifreq));
+ err = sock_do_ioctl(net, sock, cmd, arg);
break;
}
return err;
@@ -2802,8 +2800,7 @@ static int do_siocgstamp(struct net *net, struct socket *sock,
int err;
set_fs(KERNEL_DS);
- err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv,
- sizeof(struct compat_ifreq));
+ err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv);
set_fs(old_fs);
if (!err)
err = compat_put_timeval(&ktv, up);
@@ -2819,8 +2816,7 @@ static int do_siocgstampns(struct net *net, struct socket *sock,
int err;
set_fs(KERNEL_DS);
- err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts,
- sizeof(struct compat_ifreq));
+ err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts);
set_fs(old_fs);
if (!err)
err = compat_put_timespec(&kts, up);
@@ -3016,6 +3012,54 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd,
return dev_ioctl(net, cmd, &ifreq, NULL);
}
+static int compat_ifreq_ioctl(struct net *net, struct socket *sock,
+ unsigned int cmd,
+ struct compat_ifreq __user *uifr32)
+{
+ struct ifreq __user *uifr;
+ int err;
+
+ /* Handle the fact that while struct ifreq has the same *layout* on
+ * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data,
+ * which are handled elsewhere, it still has different *size* due to
+ * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit,
+ * resulting in struct ifreq being 32 and 40 bytes respectively).
+ * As a result, if the struct happens to be at the end of a page and
+ * the next page isn't readable/writable, we get a fault. To prevent
+ * that, copy back and forth to the full size.
+ */
+
+ uifr = compat_alloc_user_space(sizeof(*uifr));
+ if (copy_in_user(uifr, uifr32, sizeof(*uifr32)))
+ return -EFAULT;
+
+ err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr);
+
+ if (!err) {
+ switch (cmd) {
+ case SIOCGIFFLAGS:
+ case SIOCGIFMETRIC:
+ case SIOCGIFMTU:
+ case SIOCGIFMEM:
+ case SIOCGIFHWADDR:
+ case SIOCGIFINDEX:
+ case SIOCGIFADDR:
+ case SIOCGIFBRDADDR:
+ case SIOCGIFDSTADDR:
+ case SIOCGIFNETMASK:
+ case SIOCGIFPFLAGS:
+ case SIOCGIFTXQLEN:
+ case SIOCGMIIPHY:
+ case SIOCGMIIREG:
+ case SIOCGIFNAME:
+ if (copy_in_user(uifr32, uifr, sizeof(*uifr32)))
+ err = -EFAULT;
+ break;
+ }
+ }
+ return err;
+}
+
static int compat_sioc_ifmap(struct net *net, unsigned int cmd,
struct compat_ifreq __user *uifr32)
{
@@ -3131,8 +3175,7 @@ static int routing_ioctl(struct net *net, struct socket *sock,
}
set_fs(KERNEL_DS);
- ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r,
- sizeof(struct compat_ifreq));
+ ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r);
set_fs(old_fs);
out:
@@ -3232,21 +3275,22 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
case SIOCSIFTXQLEN:
case SIOCBRADDIF:
case SIOCBRDELIF:
+ case SIOCGIFNAME:
case SIOCSIFNAME:
case SIOCGMIIPHY:
case SIOCGMIIREG:
case SIOCSMIIREG:
- case SIOCSARP:
- case SIOCGARP:
- case SIOCDARP:
- case SIOCATMARK:
case SIOCBONDENSLAVE:
case SIOCBONDRELEASE:
case SIOCBONDSETHWADDR:
case SIOCBONDCHANGEACTIVE:
- case SIOCGIFNAME:
- return sock_do_ioctl(net, sock, cmd, arg,
- sizeof(struct compat_ifreq));
+ return compat_ifreq_ioctl(net, sock, cmd, argp);
+
+ case SIOCSARP:
+ case SIOCGARP:
+ case SIOCDARP:
+ case SIOCATMARK:
+ return sock_do_ioctl(net, sock, cmd, arg);
}
return -ENOIOCTLCMD;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index cf51b8f9b15f..1f200119268c 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -537,6 +537,99 @@ void svc_rdma_sync_reply_hdr(struct svcxprt_rdma *rdma,
DMA_TO_DEVICE);
}
+/* If the xdr_buf has more elements than the device can
+ * transmit in a single RDMA Send, then the reply will
+ * have to be copied into a bounce buffer.
+ */
+static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma,
+ struct xdr_buf *xdr,
+ __be32 *wr_lst)
+{
+ int elements;
+
+ /* xdr->head */
+ elements = 1;
+
+ /* xdr->pages */
+ if (!wr_lst) {
+ unsigned int remaining;
+ unsigned long pageoff;
+
+ pageoff = xdr->page_base & ~PAGE_MASK;
+ remaining = xdr->page_len;
+ while (remaining) {
+ ++elements;
+ remaining -= min_t(u32, PAGE_SIZE - pageoff,
+ remaining);
+ pageoff = 0;
+ }
+ }
+
+ /* xdr->tail */
+ if (xdr->tail[0].iov_len)
+ ++elements;
+
+ /* assume 1 SGE is needed for the transport header */
+ return elements >= rdma->sc_max_send_sges;
+}
+
+/* The device is not capable of sending the reply directly.
+ * Assemble the elements of @xdr into the transport header
+ * buffer.
+ */
+static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma,
+ struct svc_rdma_send_ctxt *ctxt,
+ struct xdr_buf *xdr, __be32 *wr_lst)
+{
+ unsigned char *dst, *tailbase;
+ unsigned int taillen;
+
+ dst = ctxt->sc_xprt_buf;
+ dst += ctxt->sc_sges[0].length;
+
+ memcpy(dst, xdr->head[0].iov_base, xdr->head[0].iov_len);
+ dst += xdr->head[0].iov_len;
+
+ tailbase = xdr->tail[0].iov_base;
+ taillen = xdr->tail[0].iov_len;
+ if (wr_lst) {
+ u32 xdrpad;
+
+ xdrpad = xdr_padsize(xdr->page_len);
+ if (taillen && xdrpad) {
+ tailbase += xdrpad;
+ taillen -= xdrpad;
+ }
+ } else {
+ unsigned int len, remaining;
+ unsigned long pageoff;
+ struct page **ppages;
+
+ ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
+ pageoff = xdr->page_base & ~PAGE_MASK;
+ remaining = xdr->page_len;
+ while (remaining) {
+ len = min_t(u32, PAGE_SIZE - pageoff, remaining);
+
+ memcpy(dst, page_address(*ppages), len);
+ remaining -= len;
+ dst += len;
+ pageoff = 0;
+ }
+ }
+
+ if (taillen)
+ memcpy(dst, tailbase, taillen);
+
+ ctxt->sc_sges[0].length += xdr->len;
+ ib_dma_sync_single_for_device(rdma->sc_pd->device,
+ ctxt->sc_sges[0].addr,
+ ctxt->sc_sges[0].length,
+ DMA_TO_DEVICE);
+
+ return 0;
+}
+
/* svc_rdma_map_reply_msg - Map the buffer holding RPC message
* @rdma: controlling transport
* @ctxt: send_ctxt for the Send WR
@@ -559,8 +652,10 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
u32 xdr_pad;
int ret;
- if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges)
- return -EIO;
+ if (svc_rdma_pull_up_needed(rdma, xdr, wr_lst))
+ return svc_rdma_pull_up_reply_msg(rdma, ctxt, xdr, wr_lst);
+
+ ++ctxt->sc_cur_sge_no;
ret = svc_rdma_dma_map_buf(rdma, ctxt,
xdr->head[0].iov_base,
xdr->head[0].iov_len);
@@ -591,8 +686,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
while (remaining) {
len = min_t(u32, PAGE_SIZE - page_off, remaining);
- if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges)
- return -EIO;
+ ++ctxt->sc_cur_sge_no;
ret = svc_rdma_dma_map_page(rdma, ctxt, *ppages++,
page_off, len);
if (ret < 0)
@@ -606,8 +700,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
len = xdr->tail[0].iov_len;
tail:
if (len) {
- if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges)
- return -EIO;
+ ++ctxt->sc_cur_sge_no;
ret = svc_rdma_dma_map_buf(rdma, ctxt, base, len);
if (ret < 0)
return ret;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 924c17d46903..57f86c63a463 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -419,12 +419,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
/* Transport header, head iovec, tail iovec */
newxprt->sc_max_send_sges = 3;
/* Add one SGE per page list entry */
- newxprt->sc_max_send_sges += svcrdma_max_req_size / PAGE_SIZE;
- if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) {
- pr_err("svcrdma: too few Send SGEs available (%d needed)\n",
- newxprt->sc_max_send_sges);
- goto errout;
- }
+ newxprt->sc_max_send_sges += (svcrdma_max_req_size / PAGE_SIZE) + 1;
+ if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge)
+ newxprt->sc_max_send_sges = dev->attrs.max_send_sge;
newxprt->sc_max_req_size = svcrdma_max_req_size;
newxprt->sc_max_requests = svcrdma_max_requests;
newxprt->sc_max_bc_requests = svcrdma_max_bc_requests;
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 5d3cce9e8744..15eb5d3d4750 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -75,6 +75,9 @@ static u32 virtio_transport_get_local_cid(void)
{
struct virtio_vsock *vsock = virtio_vsock_get();
+ if (!vsock)
+ return VMADDR_CID_ANY;
+
return vsock->guest_cid;
}
@@ -584,10 +587,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
virtio_vsock_update_guest_cid(vsock);
- ret = vsock_core_init(&virtio_transport.transport);
- if (ret < 0)
- goto out_vqs;
-
vsock->rx_buf_nr = 0;
vsock->rx_buf_max_nr = 0;
atomic_set(&vsock->queued_replies, 0);
@@ -618,8 +617,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
mutex_unlock(&the_virtio_vsock_mutex);
return 0;
-out_vqs:
- vsock->vdev->config->del_vqs(vsock->vdev);
out:
kfree(vsock);
mutex_unlock(&the_virtio_vsock_mutex);
@@ -637,6 +634,9 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
flush_work(&vsock->event_work);
flush_work(&vsock->send_pkt_work);
+ /* Reset all connected sockets when the device disappear */
+ vsock_for_each_connected_socket(virtio_vsock_reset_sock);
+
vdev->config->reset(vdev);
mutex_lock(&vsock->rx_lock);
@@ -669,7 +669,6 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
mutex_lock(&the_virtio_vsock_mutex);
the_virtio_vsock = NULL;
- vsock_core_exit();
mutex_unlock(&the_virtio_vsock_mutex);
vdev->config->del_vqs(vdev);
@@ -702,14 +701,28 @@ static int __init virtio_vsock_init(void)
virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0);
if (!virtio_vsock_workqueue)
return -ENOMEM;
+
ret = register_virtio_driver(&virtio_vsock_driver);
if (ret)
- destroy_workqueue(virtio_vsock_workqueue);
+ goto out_wq;
+
+ ret = vsock_core_init(&virtio_transport.transport);
+ if (ret)
+ goto out_vdr;
+
+ return 0;
+
+out_vdr:
+ unregister_virtio_driver(&virtio_vsock_driver);
+out_wq:
+ destroy_workqueue(virtio_vsock_workqueue);
return ret;
+
}
static void __exit virtio_vsock_exit(void)
{
+ vsock_core_exit();
unregister_virtio_driver(&virtio_vsock_driver);
destroy_workqueue(virtio_vsock_workqueue);
}
diff --git a/net/wireless/ap.c b/net/wireless/ap.c
index 882d97bdc6bf..550ac9d827fe 100644
--- a/net/wireless/ap.c
+++ b/net/wireless/ap.c
@@ -41,6 +41,8 @@ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
cfg80211_sched_dfs_chan_update(rdev);
}
+ schedule_work(&cfg80211_disconnect_work);
+
return err;
}
diff --git a/net/wireless/core.h b/net/wireless/core.h
index c5d6f3418601..f6b40563dc63 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -445,6 +445,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev);
bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range,
u32 center_freq_khz, u32 bw_khz);
+extern struct work_struct cfg80211_disconnect_work;
+
/**
* cfg80211_chandef_dfs_usable - checks if chandef is DFS usable
* @wiphy: the wiphy to validate against
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index f741d8376a46..7d34cb884840 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -667,7 +667,7 @@ static void disconnect_work(struct work_struct *work)
rtnl_unlock();
}
-static DECLARE_WORK(cfg80211_disconnect_work, disconnect_work);
+DECLARE_WORK(cfg80211_disconnect_work, disconnect_work);
/*