summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/Kconfig27
-rw-r--r--net/can/isotp.c49
-rw-r--r--net/core/dev.c29
-rw-r--r--net/core/filter.c1
-rw-r--r--net/core/page_pool.c12
-rw-r--r--net/core/sock.c8
-rw-r--r--net/dsa/master.c5
-rw-r--r--net/dsa/slave.c12
-rw-r--r--net/ethtool/stats.c2
-rw-r--r--net/hsr/hsr_device.c2
-rw-r--r--net/hsr/hsr_forward.c30
-rw-r--r--net/hsr/hsr_forward.h8
-rw-r--r--net/hsr/hsr_main.h4
-rw-r--r--net/hsr/hsr_slave.c11
-rw-r--r--net/ipv4/bpf_tcp_ca.c2
-rw-r--r--net/ipv6/mcast.c3
-rw-r--r--net/ipv6/reassembly.c4
-rw-r--r--net/mac80211/ieee80211_i.h36
-rw-r--r--net/mac80211/iface.c11
-rw-r--r--net/mac80211/key.c7
-rw-r--r--net/mac80211/key.h2
-rw-r--r--net/mac80211/rx.c150
-rw-r--r--net/mac80211/sta_info.c6
-rw-r--r--net/mac80211/sta_info.h33
-rw-r--r--net/mac80211/wpa.c13
-rw-r--r--net/mptcp/options.c3
-rw-r--r--net/mptcp/pm_netlink.c8
-rw-r--r--net/mptcp/protocol.c20
-rw-r--r--net/mptcp/protocol.h3
-rw-r--r--net/mptcp/sockopt.c4
-rw-r--r--net/mptcp/subflow.c1
-rw-r--r--net/netfilter/nf_flow_table_core.c3
-rw-r--r--net/netfilter/nf_flow_table_offload.c7
-rw-r--r--net/netfilter/nft_set_pipapo.c4
-rw-r--r--net/netfilter/nft_set_pipapo.h2
-rw-r--r--net/netfilter/nft_set_pipapo_avx2.c3
-rw-r--r--net/netlink/af_netlink.c6
-rw-r--r--net/nfc/nci/core.c1
-rw-r--r--net/nfc/nci/hci.c5
-rw-r--r--net/nfc/rawsock.c2
-rw-r--r--net/openvswitch/meter.c8
-rw-r--r--net/packet/af_packet.c10
-rw-r--r--net/rds/connection.c23
-rw-r--r--net/rds/tcp.c4
-rw-r--r--net/rds/tcp.h3
-rw-r--r--net/rds/tcp_listen.c6
-rw-r--r--net/sched/cls_api.c2
-rw-r--r--net/sched/sch_dsmark.c3
-rw-r--r--net/sched/sch_fq_pie.c19
-rw-r--r--net/sched/sch_generic.c50
-rw-r--r--net/sctp/socket.c1
-rw-r--r--net/sctp/sysctl.c2
-rw-r--r--net/smc/smc_ism.c26
-rw-r--r--net/sunrpc/clnt.c7
-rw-r--r--net/sunrpc/xprt.c40
-rw-r--r--net/sunrpc/xprtrdma/rpc_rdma.c27
-rw-r--r--net/sunrpc/xprtrdma/transport.c12
-rw-r--r--net/sunrpc/xprtrdma/verbs.c18
-rw-r--r--net/sunrpc/xprtrdma/xprt_rdma.h1
-rw-r--r--net/sunrpc/xprtsock.c2
-rw-r--r--net/tipc/core.c6
-rw-r--r--net/tipc/core.h10
-rw-r--r--net/tipc/discover.c4
-rw-r--r--net/tipc/link.c5
-rw-r--r--net/tipc/link.h1
-rw-r--r--net/tipc/msg.c9
-rw-r--r--net/tipc/net.c15
-rw-r--r--net/tipc/node.c12
-rw-r--r--net/tipc/socket.c5
-rw-r--r--net/tipc/udp_media.c2
-rw-r--r--net/tls/tls_sw.c11
-rw-r--r--net/wireless/util.c7
72 files changed, 600 insertions, 290 deletions
diff --git a/net/Kconfig b/net/Kconfig
index f5ee7c65e6b4..c7392c449b25 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -302,21 +302,6 @@ config BQL
select DQL
default y
-config BPF_JIT
- bool "enable BPF Just In Time compiler"
- depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT
- depends on MODULES
- help
- Berkeley Packet Filter filtering capabilities are normally handled
- by an interpreter. This option allows kernel to generate a native
- code when filter is loaded in memory. This should speedup
- packet sniffing (libpcap/tcpdump).
-
- Note, admin should enable this feature changing:
- /proc/sys/net/core/bpf_jit_enable
- /proc/sys/net/core/bpf_jit_harden (optional)
- /proc/sys/net/core/bpf_jit_kallsyms (optional)
-
config BPF_STREAM_PARSER
bool "enable BPF STREAM_PARSER"
depends on INET
@@ -470,15 +455,3 @@ config ETHTOOL_NETLINK
e.g. notification messages.
endif # if NET
-
-# Used by archs to tell that they support BPF JIT compiler plus which flavour.
-# Only one of the two can be selected for a specific arch since eBPF JIT supersedes
-# the cBPF JIT.
-
-# Classic BPF JIT (cBPF)
-config HAVE_CBPF_JIT
- bool
-
-# Extended BPF JIT (eBPF)
-config HAVE_EBPF_JIT
- bool
diff --git a/net/can/isotp.c b/net/can/isotp.c
index 9f94ad3caee9..253b24417c8e 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1062,27 +1062,31 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
if (len < ISOTP_MIN_NAMELEN)
return -EINVAL;
+ if (addr->can_addr.tp.tx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG))
+ return -EADDRNOTAVAIL;
+
+ if (!addr->can_ifindex)
+ return -ENODEV;
+
+ lock_sock(sk);
+
/* do not register frame reception for functional addressing */
if (so->opt.flags & CAN_ISOTP_SF_BROADCAST)
do_rx_reg = 0;
/* do not validate rx address for functional addressing */
if (do_rx_reg) {
- if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id)
- return -EADDRNOTAVAIL;
+ if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id) {
+ err = -EADDRNOTAVAIL;
+ goto out;
+ }
- if (addr->can_addr.tp.rx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG))
- return -EADDRNOTAVAIL;
+ if (addr->can_addr.tp.rx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) {
+ err = -EADDRNOTAVAIL;
+ goto out;
+ }
}
- if (addr->can_addr.tp.tx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG))
- return -EADDRNOTAVAIL;
-
- if (!addr->can_ifindex)
- return -ENODEV;
-
- lock_sock(sk);
-
if (so->bound && addr->can_ifindex == so->ifindex &&
addr->can_addr.tp.rx_id == so->rxid &&
addr->can_addr.tp.tx_id == so->txid)
@@ -1164,16 +1168,13 @@ static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
return ISOTP_MIN_NAMELEN;
}
-static int isotp_setsockopt(struct socket *sock, int level, int optname,
+static int isotp_setsockopt_locked(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
struct isotp_sock *so = isotp_sk(sk);
int ret = 0;
- if (level != SOL_CAN_ISOTP)
- return -EINVAL;
-
if (so->bound)
return -EISCONN;
@@ -1248,6 +1249,22 @@ static int isotp_setsockopt(struct socket *sock, int level, int optname,
return ret;
}
+static int isotp_setsockopt(struct socket *sock, int level, int optname,
+ sockptr_t optval, unsigned int optlen)
+
+{
+ struct sock *sk = sock->sk;
+ int ret;
+
+ if (level != SOL_CAN_ISOTP)
+ return -EINVAL;
+
+ lock_sock(sk);
+ ret = isotp_setsockopt_locked(sock, level, optname, optval, optlen);
+ release_sock(sk);
+ return ret;
+}
+
static int isotp_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
diff --git a/net/core/dev.c b/net/core/dev.c
index 222b1d322c96..ef8cf7619baf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3853,7 +3853,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
if (q->flags & TCQ_F_NOLOCK) {
rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
- qdisc_run(q);
+ if (likely(!netif_xmit_frozen_or_stopped(txq)))
+ qdisc_run(q);
if (unlikely(to_free))
kfree_skb_list(to_free);
@@ -5025,25 +5026,43 @@ static __latent_entropy void net_tx_action(struct softirq_action *h)
sd->output_queue_tailp = &sd->output_queue;
local_irq_enable();
+ rcu_read_lock();
+
while (head) {
struct Qdisc *q = head;
spinlock_t *root_lock = NULL;
head = head->next_sched;
- if (!(q->flags & TCQ_F_NOLOCK)) {
- root_lock = qdisc_lock(q);
- spin_lock(root_lock);
- }
/* We need to make sure head->next_sched is read
* before clearing __QDISC_STATE_SCHED
*/
smp_mb__before_atomic();
+
+ if (!(q->flags & TCQ_F_NOLOCK)) {
+ root_lock = qdisc_lock(q);
+ spin_lock(root_lock);
+ } else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
+ &q->state))) {
+ /* There is a synchronize_net() between
+ * STATE_DEACTIVATED flag being set and
+ * qdisc_reset()/some_qdisc_is_busy() in
+ * dev_deactivate(), so we can safely bail out
+ * early here to avoid data race between
+ * qdisc_deactivate() and some_qdisc_is_busy()
+ * for lockless qdisc.
+ */
+ clear_bit(__QDISC_STATE_SCHED, &q->state);
+ continue;
+ }
+
clear_bit(__QDISC_STATE_SCHED, &q->state);
qdisc_run(q);
if (root_lock)
spin_unlock(root_lock);
}
+
+ rcu_read_unlock();
}
xfrm_dev_backlog(sd);
diff --git a/net/core/filter.c b/net/core/filter.c
index cae56d08a670..65ab4e21c087 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3784,6 +3784,7 @@ static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room,
__skb_push(skb, head_room);
memset(skb->data, 0, head_room);
skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
}
return ret;
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 9ec1aa9640ad..3c4c4c7a0402 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool,
struct page *page,
unsigned int dma_sync_size)
{
+ dma_addr_t dma_addr = page_pool_get_dma_addr(page);
+
dma_sync_size = min(dma_sync_size, pool->p.max_len);
- dma_sync_single_range_for_device(pool->p.dev, page->dma_addr,
+ dma_sync_single_range_for_device(pool->p.dev, dma_addr,
pool->p.offset, dma_sync_size,
pool->p.dma_dir);
}
@@ -195,7 +197,7 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
if (dma_mapping_error(pool->p.dev, dma))
return false;
- page->dma_addr = dma;
+ page_pool_set_dma_addr(page, dma);
if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
@@ -331,13 +333,13 @@ void page_pool_release_page(struct page_pool *pool, struct page *page)
*/
goto skip_dma_unmap;
- dma = page->dma_addr;
+ dma = page_pool_get_dma_addr(page);
- /* When page is unmapped, it cannot be returned our pool */
+ /* When page is unmapped, it cannot be returned to our pool */
dma_unmap_page_attrs(pool->p.dev, dma,
PAGE_SIZE << pool->p.order, pool->p.dma_dir,
DMA_ATTR_SKIP_CPU_SYNC);
- page->dma_addr = 0;
+ page_pool_set_dma_addr(page, 0);
skip_dma_unmap:
/* This may be the last page returned, releasing the pool, so
* it is not safe to reference pool afterwards.
diff --git a/net/core/sock.c b/net/core/sock.c
index c761c4a0b66b..958614ea16ed 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2132,10 +2132,10 @@ void skb_orphan_partial(struct sk_buff *skb)
if (skb_is_tcp_pure_ack(skb))
return;
- if (can_skb_orphan_partial(skb))
- skb_set_owner_sk_safe(skb, skb->sk);
- else
- skb_orphan(skb);
+ if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk))
+ return;
+
+ skb_orphan(skb);
}
EXPORT_SYMBOL(skb_orphan_partial);
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 052a977914a6..63adbc21a735 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -147,8 +147,7 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset,
struct dsa_switch *ds = cpu_dp->ds;
int port = cpu_dp->index;
int len = ETH_GSTRING_LEN;
- int mcount = 0, count;
- unsigned int i;
+ int mcount = 0, count, i;
uint8_t pfx[4];
uint8_t *ndata;
@@ -178,6 +177,8 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset,
*/
ds->ops->get_strings(ds, port, stringset, ndata);
count = ds->ops->get_sset_count(ds, port, stringset);
+ if (count < 0)
+ return;
for (i = 0; i < count; i++) {
memmove(ndata + (i * len + sizeof(pfx)),
ndata + i * len, len - sizeof(pfx));
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 8c0f3c6ab365..d4756b920108 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -776,13 +776,15 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset)
struct dsa_switch *ds = dp->ds;
if (sset == ETH_SS_STATS) {
- int count;
+ int count = 0;
- count = 4;
- if (ds->ops->get_sset_count)
- count += ds->ops->get_sset_count(ds, dp->index, sset);
+ if (ds->ops->get_sset_count) {
+ count = ds->ops->get_sset_count(ds, dp->index, sset);
+ if (count < 0)
+ return count;
+ }
- return count;
+ return count + 4;
} else if (sset == ETH_SS_TEST) {
return net_selftest_get_count();
}
diff --git a/net/ethtool/stats.c b/net/ethtool/stats.c
index b7642dc96d50..ec07f5765e03 100644
--- a/net/ethtool/stats.c
+++ b/net/ethtool/stats.c
@@ -119,7 +119,7 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base,
*/
memset(&data->phy_stats, 0xff, sizeof(data->phy_stats));
memset(&data->mac_stats, 0xff, sizeof(data->mac_stats));
- memset(&data->ctrl_stats, 0xff, sizeof(data->mac_stats));
+ memset(&data->ctrl_stats, 0xff, sizeof(data->ctrl_stats));
memset(&data->rmon_stats, 0xff, sizeof(data->rmon_stats));
if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask) &&
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index bfcdc75fc01e..26c32407f029 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -218,6 +218,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
if (master) {
skb->dev = master->dev;
skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
hsr_forward_skb(skb, master);
} else {
atomic_long_inc(&dev->tx_dropped);
@@ -259,6 +260,7 @@ static struct sk_buff *hsr_init_skb(struct hsr_port *master)
goto out;
skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 6852e9bccf5b..ceb8afb2a62f 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -474,8 +474,8 @@ static void handle_std_frame(struct sk_buff *skb,
}
}
-void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb,
- struct hsr_frame_info *frame)
+int hsr_fill_frame_info(__be16 proto, struct sk_buff *skb,
+ struct hsr_frame_info *frame)
{
struct hsr_port *port = frame->port_rcv;
struct hsr_priv *hsr = port->hsr;
@@ -483,20 +483,26 @@ void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb,
/* HSRv0 supervisory frames double as a tag so treat them as tagged. */
if ((!hsr->prot_version && proto == htons(ETH_P_PRP)) ||
proto == htons(ETH_P_HSR)) {
+ /* Check if skb contains hsr_ethhdr */
+ if (skb->mac_len < sizeof(struct hsr_ethhdr))
+ return -EINVAL;
+
/* HSR tagged frame :- Data or Supervision */
frame->skb_std = NULL;
frame->skb_prp = NULL;
frame->skb_hsr = skb;
frame->sequence_nr = hsr_get_skb_sequence_nr(skb);
- return;
+ return 0;
}
/* Standard frame or PRP from master port */
handle_std_frame(skb, frame);
+
+ return 0;
}
-void prp_fill_frame_info(__be16 proto, struct sk_buff *skb,
- struct hsr_frame_info *frame)
+int prp_fill_frame_info(__be16 proto, struct sk_buff *skb,
+ struct hsr_frame_info *frame)
{
/* Supervision frame */
struct prp_rct *rct = skb_get_PRP_rct(skb);
@@ -507,9 +513,11 @@ void prp_fill_frame_info(__be16 proto, struct sk_buff *skb,
frame->skb_std = NULL;
frame->skb_prp = skb;
frame->sequence_nr = prp_get_skb_sequence_nr(rct);
- return;
+ return 0;
}
handle_std_frame(skb, frame);
+
+ return 0;
}
static int fill_frame_info(struct hsr_frame_info *frame,
@@ -519,9 +527,10 @@ static int fill_frame_info(struct hsr_frame_info *frame,
struct hsr_vlan_ethhdr *vlan_hdr;
struct ethhdr *ethhdr;
__be16 proto;
+ int ret;
- /* Check if skb contains hsr_ethhdr */
- if (skb->mac_len < sizeof(struct hsr_ethhdr))
+ /* Check if skb contains ethhdr */
+ if (skb->mac_len < sizeof(struct ethhdr))
return -EINVAL;
memset(frame, 0, sizeof(*frame));
@@ -548,7 +557,10 @@ static int fill_frame_info(struct hsr_frame_info *frame,
frame->is_from_san = false;
frame->port_rcv = port;
- hsr->proto_ops->fill_frame_info(proto, skb, frame);
+ ret = hsr->proto_ops->fill_frame_info(proto, skb, frame);
+ if (ret)
+ return ret;
+
check_local_dest(port->hsr, skb, frame);
return 0;
diff --git a/net/hsr/hsr_forward.h b/net/hsr/hsr_forward.h
index b6acaafa83fc..206636750b30 100644
--- a/net/hsr/hsr_forward.h
+++ b/net/hsr/hsr_forward.h
@@ -24,8 +24,8 @@ struct sk_buff *prp_get_untagged_frame(struct hsr_frame_info *frame,
struct hsr_port *port);
bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port);
bool hsr_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port);
-void prp_fill_frame_info(__be16 proto, struct sk_buff *skb,
- struct hsr_frame_info *frame);
-void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb,
- struct hsr_frame_info *frame);
+int prp_fill_frame_info(__be16 proto, struct sk_buff *skb,
+ struct hsr_frame_info *frame);
+int hsr_fill_frame_info(__be16 proto, struct sk_buff *skb,
+ struct hsr_frame_info *frame);
#endif /* __HSR_FORWARD_H */
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index 8f264672b70b..53d1f7a82463 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -186,8 +186,8 @@ struct hsr_proto_ops {
struct hsr_port *port);
struct sk_buff * (*create_tagged_frame)(struct hsr_frame_info *frame,
struct hsr_port *port);
- void (*fill_frame_info)(__be16 proto, struct sk_buff *skb,
- struct hsr_frame_info *frame);
+ int (*fill_frame_info)(__be16 proto, struct sk_buff *skb,
+ struct hsr_frame_info *frame);
bool (*invalid_dan_ingress_frame)(__be16 protocol);
void (*update_san_info)(struct hsr_node *node, bool is_sup);
};
diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index c5227d42faf5..b70e6bbf6021 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -60,12 +60,11 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb)
goto finish_pass;
skb_push(skb, ETH_HLEN);
-
- if (skb_mac_header(skb) != skb->data) {
- WARN_ONCE(1, "%s:%d: Malformed frame at source port %s)\n",
- __func__, __LINE__, port->dev->name);
- goto finish_consume;
- }
+ skb_reset_mac_header(skb);
+ if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) ||
+ protocol == htons(ETH_P_HSR))
+ skb_set_network_header(skb, ETH_HLEN + HSR_HLEN);
+ skb_reset_mac_len(skb);
hsr_forward_skb(skb, port);
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index dff4f0eb96b0..9e41eff4a685 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -185,6 +185,7 @@ BTF_ID(func, tcp_reno_cong_avoid)
BTF_ID(func, tcp_reno_undo_cwnd)
BTF_ID(func, tcp_slow_start)
BTF_ID(func, tcp_cong_avoid_ai)
+#ifdef CONFIG_X86
#ifdef CONFIG_DYNAMIC_FTRACE
#if IS_BUILTIN(CONFIG_TCP_CONG_CUBIC)
BTF_ID(func, cubictcp_init)
@@ -213,6 +214,7 @@ BTF_ID(func, bbr_min_tso_segs)
BTF_ID(func, bbr_set_state)
#endif
#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_X86 */
BTF_SET_END(bpf_tcp_ca_kfunc_ids)
static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id)
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 0d59efb6b49e..d36ef9d25e73 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1745,10 +1745,7 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
IPV6_TLV_PADN, 0 };
/* we assume size > sizeof(ra) here */
- /* limit our allocations to order-0 page */
- size = min_t(int, size, SKB_MAX_ORDER(0, 0));
skb = sock_alloc_send_skb(sk, size, 1, &err);
-
if (!skb)
return NULL;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 47a0dc46cbdb..28e44782c94d 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -343,7 +343,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
hdr = ipv6_hdr(skb);
fhdr = (struct frag_hdr *)skb_transport_header(skb);
- if (!(fhdr->frag_off & htons(0xFFF9))) {
+ if (!(fhdr->frag_off & htons(IP6_OFFSET | IP6_MF))) {
/* It is not a fragmented frame */
skb->transport_header += sizeof(struct frag_hdr);
__IP6_INC_STATS(net,
@@ -351,6 +351,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
+ IP6CB(skb)->frag_max_size = ntohs(hdr->payload_len) +
+ sizeof(struct ipv6hdr);
return 1;
}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 8fcbaa1eedf3..214404a558fb 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -50,12 +50,6 @@ struct ieee80211_local;
#define IEEE80211_ENCRYPT_HEADROOM 8
#define IEEE80211_ENCRYPT_TAILROOM 18
-/* IEEE 802.11 (Ch. 9.5 Defragmentation) requires support for concurrent
- * reception of at least three fragmented frames. This limit can be increased
- * by changing this define, at the cost of slower frame reassembly and
- * increased memory use (about 2 kB of RAM per entry). */
-#define IEEE80211_FRAGMENT_MAX 4
-
/* power level hasn't been configured (or set to automatic) */
#define IEEE80211_UNSET_POWER_LEVEL INT_MIN
@@ -88,18 +82,6 @@ extern const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS];
#define IEEE80211_MAX_NAN_INSTANCE_ID 255
-struct ieee80211_fragment_entry {
- struct sk_buff_head skb_list;
- unsigned long first_frag_time;
- u16 seq;
- u16 extra_len;
- u16 last_frag;
- u8 rx_queue;
- bool check_sequential_pn; /* needed for CCMP/GCMP */
- u8 last_pn[6]; /* PN of the last fragment if CCMP was used */
-};
-
-
struct ieee80211_bss {
u32 device_ts_beacon, device_ts_presp;
@@ -241,8 +223,15 @@ struct ieee80211_rx_data {
*/
int security_idx;
- u32 tkip_iv32;
- u16 tkip_iv16;
+ union {
+ struct {
+ u32 iv32;
+ u16 iv16;
+ } tkip;
+ struct {
+ u8 pn[IEEE80211_CCMP_PN_LEN];
+ } ccm_gcm;
+ };
};
struct ieee80211_csa_settings {
@@ -902,9 +891,7 @@ struct ieee80211_sub_if_data {
char name[IFNAMSIZ];
- /* Fragment table for host-based reassembly */
- struct ieee80211_fragment_entry fragments[IEEE80211_FRAGMENT_MAX];
- unsigned int fragment_next;
+ struct ieee80211_fragment_cache frags;
/* TID bitmap for NoAck policy */
u16 noack_map;
@@ -2320,4 +2307,7 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw,
#define debug_noinline
#endif
+void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache);
+void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache);
+
#endif /* IEEE80211_I_H */
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 7032a2b59249..2e2f73a4aa73 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -8,7 +8,7 @@
* Copyright 2008, Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright (c) 2016 Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
*/
#include <linux/slab.h>
#include <linux/kernel.h>
@@ -677,16 +677,12 @@ static void ieee80211_set_multicast_list(struct net_device *dev)
*/
static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata)
{
- int i;
-
/* free extra data */
ieee80211_free_keys(sdata, false);
ieee80211_debugfs_remove_netdev(sdata);
- for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++)
- __skb_queue_purge(&sdata->fragments[i].skb_list);
- sdata->fragment_next = 0;
+ ieee80211_destroy_frag_cache(&sdata->frags);
if (ieee80211_vif_is_mesh(&sdata->vif))
ieee80211_mesh_teardown_sdata(sdata);
@@ -1930,8 +1926,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
sdata->wdev.wiphy = local->hw.wiphy;
sdata->local = local;
- for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++)
- skb_queue_head_init(&sdata->fragments[i].skb_list);
+ ieee80211_init_frag_cache(&sdata->frags);
INIT_LIST_HEAD(&sdata->key_list);
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 56c068cb49c4..f695fc80088b 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -799,6 +799,7 @@ int ieee80211_key_link(struct ieee80211_key *key,
struct ieee80211_sub_if_data *sdata,
struct sta_info *sta)
{
+ static atomic_t key_color = ATOMIC_INIT(0);
struct ieee80211_key *old_key;
int idx = key->conf.keyidx;
bool pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE;
@@ -850,6 +851,12 @@ int ieee80211_key_link(struct ieee80211_key *key,
key->sdata = sdata;
key->sta = sta;
+ /*
+ * Assign a unique ID to every key so we can easily prevent mixed
+ * key and fragment cache attacks.
+ */
+ key->color = atomic_inc_return(&key_color);
+
increment_tailroom_need_count(sdata);
ret = ieee80211_key_replace(sdata, sta, pairwise, old_key, key);
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index 7ad72e9b4991..1e326c89d721 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -128,6 +128,8 @@ struct ieee80211_key {
} debugfs;
#endif
+ unsigned int color;
+
/*
* key config, must be last because it contains key
* material as variable length member
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 62047e93e217..1bb43edd47b6 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -6,7 +6,7 @@
* Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
*/
#include <linux/jiffies.h>
@@ -2123,19 +2123,34 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
return result;
}
+void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(cache->entries); i++)
+ skb_queue_head_init(&cache->entries[i].skb_list);
+}
+
+void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(cache->entries); i++)
+ __skb_queue_purge(&cache->entries[i].skb_list);
+}
+
static inline struct ieee80211_fragment_entry *
-ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata,
+ieee80211_reassemble_add(struct ieee80211_fragment_cache *cache,
unsigned int frag, unsigned int seq, int rx_queue,
struct sk_buff **skb)
{
struct ieee80211_fragment_entry *entry;
- entry = &sdata->fragments[sdata->fragment_next++];
- if (sdata->fragment_next >= IEEE80211_FRAGMENT_MAX)
- sdata->fragment_next = 0;
+ entry = &cache->entries[cache->next++];
+ if (cache->next >= IEEE80211_FRAGMENT_MAX)
+ cache->next = 0;
- if (!skb_queue_empty(&entry->skb_list))
- __skb_queue_purge(&entry->skb_list);
+ __skb_queue_purge(&entry->skb_list);
__skb_queue_tail(&entry->skb_list, *skb); /* no need for locking */
*skb = NULL;
@@ -2150,14 +2165,14 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata,
}
static inline struct ieee80211_fragment_entry *
-ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata,
+ieee80211_reassemble_find(struct ieee80211_fragment_cache *cache,
unsigned int frag, unsigned int seq,
int rx_queue, struct ieee80211_hdr *hdr)
{
struct ieee80211_fragment_entry *entry;
int i, idx;
- idx = sdata->fragment_next;
+ idx = cache->next;
for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) {
struct ieee80211_hdr *f_hdr;
struct sk_buff *f_skb;
@@ -2166,7 +2181,7 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata,
if (idx < 0)
idx = IEEE80211_FRAGMENT_MAX - 1;
- entry = &sdata->fragments[idx];
+ entry = &cache->entries[idx];
if (skb_queue_empty(&entry->skb_list) || entry->seq != seq ||
entry->rx_queue != rx_queue ||
entry->last_frag + 1 != frag)
@@ -2194,15 +2209,27 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata,
return NULL;
}
+static bool requires_sequential_pn(struct ieee80211_rx_data *rx, __le16 fc)
+{
+ return rx->key &&
+ (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP ||
+ rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 ||
+ rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP ||
+ rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) &&
+ ieee80211_has_protected(fc);
+}
+
static ieee80211_rx_result debug_noinline
ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
{
+ struct ieee80211_fragment_cache *cache = &rx->sdata->frags;
struct ieee80211_hdr *hdr;
u16 sc;
__le16 fc;
unsigned int frag, seq;
struct ieee80211_fragment_entry *entry;
struct sk_buff *skb;
+ struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
hdr = (struct ieee80211_hdr *)rx->skb->data;
fc = hdr->frame_control;
@@ -2218,6 +2245,9 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
goto out_no_led;
}
+ if (rx->sta)
+ cache = &rx->sta->frags;
+
if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
goto out;
@@ -2236,20 +2266,17 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
if (frag == 0) {
/* This is the first fragment of a new frame. */
- entry = ieee80211_reassemble_add(rx->sdata, frag, seq,
+ entry = ieee80211_reassemble_add(cache, frag, seq,
rx->seqno_idx, &(rx->skb));
- if (rx->key &&
- (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP ||
- rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 ||
- rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP ||
- rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) &&
- ieee80211_has_protected(fc)) {
+ if (requires_sequential_pn(rx, fc)) {
int queue = rx->security_idx;
/* Store CCMP/GCMP PN so that we can verify that the
* next fragment has a sequential PN value.
*/
entry->check_sequential_pn = true;
+ entry->is_protected = true;
+ entry->key_color = rx->key->color;
memcpy(entry->last_pn,
rx->key->u.ccmp.rx_pn[queue],
IEEE80211_CCMP_PN_LEN);
@@ -2261,6 +2288,11 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
sizeof(rx->key->u.gcmp.rx_pn[queue]));
BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN !=
IEEE80211_GCMP_PN_LEN);
+ } else if (rx->key &&
+ (ieee80211_has_protected(fc) ||
+ (status->flag & RX_FLAG_DECRYPTED))) {
+ entry->is_protected = true;
+ entry->key_color = rx->key->color;
}
return RX_QUEUED;
}
@@ -2268,7 +2300,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
/* This is a fragment for a frame that should already be pending in
* fragment cache. Add this fragment to the end of the pending entry.
*/
- entry = ieee80211_reassemble_find(rx->sdata, frag, seq,
+ entry = ieee80211_reassemble_find(cache, frag, seq,
rx->seqno_idx, hdr);
if (!entry) {
I802_DEBUG_INC(rx->local->rx_handlers_drop_defrag);
@@ -2283,25 +2315,39 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
if (entry->check_sequential_pn) {
int i;
u8 pn[IEEE80211_CCMP_PN_LEN], *rpn;
- int queue;
- if (!rx->key ||
- (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP &&
- rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 &&
- rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP &&
- rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256))
+ if (!requires_sequential_pn(rx, fc))
+ return RX_DROP_UNUSABLE;
+
+ /* Prevent mixed key and fragment cache attacks */
+ if (entry->key_color != rx->key->color)
return RX_DROP_UNUSABLE;
+
memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN);
for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) {
pn[i]++;
if (pn[i])
break;
}
- queue = rx->security_idx;
- rpn = rx->key->u.ccmp.rx_pn[queue];
+
+ rpn = rx->ccm_gcm.pn;
if (memcmp(pn, rpn, IEEE80211_CCMP_PN_LEN))
return RX_DROP_UNUSABLE;
memcpy(entry->last_pn, pn, IEEE80211_CCMP_PN_LEN);
+ } else if (entry->is_protected &&
+ (!rx->key ||
+ (!ieee80211_has_protected(fc) &&
+ !(status->flag & RX_FLAG_DECRYPTED)) ||
+ rx->key->color != entry->key_color)) {
+ /* Drop this as a mixed key or fragment cache attack, even
+ * if for TKIP Michael MIC should protect us, and WEP is a
+ * lost cause anyway.
+ */
+ return RX_DROP_UNUSABLE;
+ } else if (entry->is_protected && rx->key &&
+ entry->key_color != rx->key->color &&
+ (status->flag & RX_FLAG_DECRYPTED)) {
+ return RX_DROP_UNUSABLE;
}
skb_pull(rx->skb, ieee80211_hdrlen(fc));
@@ -2494,13 +2540,13 @@ static bool ieee80211_frame_allowed(struct ieee80211_rx_data *rx, __le16 fc)
struct ethhdr *ehdr = (struct ethhdr *) rx->skb->data;
/*
- * Allow EAPOL frames to us/the PAE group address regardless
- * of whether the frame was encrypted or not.
+ * Allow EAPOL frames to us/the PAE group address regardless of
+ * whether the frame was encrypted or not, and always disallow
+ * all other destination addresses for them.
*/
- if (ehdr->h_proto == rx->sdata->control_port_protocol &&
- (ether_addr_equal(ehdr->h_dest, rx->sdata->vif.addr) ||
- ether_addr_equal(ehdr->h_dest, pae_group_addr)))
- return true;
+ if (unlikely(ehdr->h_proto == rx->sdata->control_port_protocol))
+ return ether_addr_equal(ehdr->h_dest, rx->sdata->vif.addr) ||
+ ether_addr_equal(ehdr->h_dest, pae_group_addr);
if (ieee80211_802_1x_port_control(rx) ||
ieee80211_drop_unencrypted(rx, fc))
@@ -2525,8 +2571,28 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb,
cfg80211_rx_control_port(dev, skb, noencrypt);
dev_kfree_skb(skb);
} else {
+ struct ethhdr *ehdr = (void *)skb_mac_header(skb);
+
memset(skb->cb, 0, sizeof(skb->cb));
+ /*
+ * 802.1X over 802.11 requires that the authenticator address
+ * be used for EAPOL frames. However, 802.1X allows the use of
+ * the PAE group address instead. If the interface is part of
+ * a bridge and we pass the frame with the PAE group address,
+ * then the bridge will forward it to the network (even if the
+ * client was not associated yet), which isn't supposed to
+ * happen.
+ * To avoid that, rewrite the destination address to our own
+ * address, so that the authenticator (e.g. hostapd) will see
+ * the frame, but bridge won't forward it anywhere else. Note
+ * that due to earlier filtering, the only other address can
+ * be the PAE group address.
+ */
+ if (unlikely(skb->protocol == sdata->control_port_protocol &&
+ !ether_addr_equal(ehdr->h_dest, sdata->vif.addr)))
+ ether_addr_copy(ehdr->h_dest, sdata->vif.addr);
+
/* deliver to local stack */
if (rx->list)
list_add_tail(&skb->list, rx->list);
@@ -2566,6 +2632,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx)
if ((sdata->vif.type == NL80211_IFTYPE_AP ||
sdata->vif.type == NL80211_IFTYPE_AP_VLAN) &&
!(sdata->flags & IEEE80211_SDATA_DONT_BRIDGE_PACKETS) &&
+ ehdr->h_proto != rx->sdata->control_port_protocol &&
(sdata->vif.type != NL80211_IFTYPE_AP_VLAN || !sdata->u.vlan.sta)) {
if (is_multicast_ether_addr(ehdr->h_dest) &&
ieee80211_vif_get_num_mcast_if(sdata) != 0) {
@@ -2675,7 +2742,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset)
if (ieee80211_data_to_8023_exthdr(skb, &ethhdr,
rx->sdata->vif.addr,
rx->sdata->vif.type,
- data_offset))
+ data_offset, true))
return RX_DROP_UNUSABLE;
ieee80211_amsdu_to_8023s(skb, &frame_list, dev->dev_addr,
@@ -2732,6 +2799,23 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
if (is_multicast_ether_addr(hdr->addr1))
return RX_DROP_UNUSABLE;
+ if (rx->key) {
+ /*
+ * We should not receive A-MSDUs on pre-HT connections,
+ * and HT connections cannot use old ciphers. Thus drop
+ * them, as in those cases we couldn't even have SPP
+ * A-MSDUs or such.
+ */
+ switch (rx->key->conf.cipher) {
+ case WLAN_CIPHER_SUITE_WEP40:
+ case WLAN_CIPHER_SUITE_WEP104:
+ case WLAN_CIPHER_SUITE_TKIP:
+ return RX_DROP_UNUSABLE;
+ default:
+ break;
+ }
+ }
+
return __ieee80211_rx_h_amsdu(rx, 0);
}
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index ec6973ee88ef..f2fb69da9b6e 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -4,7 +4,7 @@
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
*/
#include <linux/module.h>
@@ -392,6 +392,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
u64_stats_init(&sta->rx_stats.syncp);
+ ieee80211_init_frag_cache(&sta->frags);
+
sta->sta_state = IEEE80211_STA_NONE;
/* Mark TID as unreserved */
@@ -1102,6 +1104,8 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
ieee80211_sta_debugfs_remove(sta);
+ ieee80211_destroy_frag_cache(&sta->frags);
+
cleanup_single_sta(sta);
}
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 78b9d0c7cc58..0333072ebd98 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -3,7 +3,7 @@
* Copyright 2002-2005, Devicescape Software, Inc.
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright(c) 2015-2017 Intel Deutschland GmbH
- * Copyright(c) 2020 Intel Corporation
+ * Copyright(c) 2020-2021 Intel Corporation
*/
#ifndef STA_INFO_H
@@ -439,6 +439,34 @@ struct ieee80211_sta_rx_stats {
};
/*
+ * IEEE 802.11-2016 (10.6 "Defragmentation") recommends support for "concurrent
+ * reception of at least one MSDU per access category per associated STA"
+ * on APs, or "at least one MSDU per access category" on other interface types.
+ *
+ * This limit can be increased by changing this define, at the cost of slower
+ * frame reassembly and increased memory use while fragments are pending.
+ */
+#define IEEE80211_FRAGMENT_MAX 4
+
+struct ieee80211_fragment_entry {
+ struct sk_buff_head skb_list;
+ unsigned long first_frag_time;
+ u16 seq;
+ u16 extra_len;
+ u16 last_frag;
+ u8 rx_queue;
+ u8 check_sequential_pn:1, /* needed for CCMP/GCMP */
+ is_protected:1;
+ u8 last_pn[6]; /* PN of the last fragment if CCMP was used */
+ unsigned int key_color;
+};
+
+struct ieee80211_fragment_cache {
+ struct ieee80211_fragment_entry entries[IEEE80211_FRAGMENT_MAX];
+ unsigned int next;
+};
+
+/*
* The bandwidth threshold below which the per-station CoDel parameters will be
* scaled to be more lenient (to prevent starvation of slow stations). This
* value will be scaled by the number of active stations when it is being
@@ -531,6 +559,7 @@ struct ieee80211_sta_rx_stats {
* @status_stats.last_ack_signal: last ACK signal
* @status_stats.ack_signal_filled: last ACK signal validity
* @status_stats.avg_ack_signal: average ACK signal
+ * @frags: fragment cache
*/
struct sta_info {
/* General information, mostly static */
@@ -639,6 +668,8 @@ struct sta_info {
struct cfg80211_chan_def tdls_chandef;
+ struct ieee80211_fragment_cache frags;
+
/* keep last! */
struct ieee80211_sta sta;
};
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index 91bf32af55e9..bca47fad5a16 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -3,6 +3,7 @@
* Copyright 2002-2004, Instant802 Networks, Inc.
* Copyright 2008, Jouni Malinen <j@w1.fi>
* Copyright (C) 2016-2017 Intel Deutschland GmbH
+ * Copyright (C) 2020-2021 Intel Corporation
*/
#include <linux/netdevice.h>
@@ -167,8 +168,8 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx)
update_iv:
/* update IV in key information to be able to detect replays */
- rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip_iv32;
- rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip_iv16;
+ rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip.iv32;
+ rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip.iv16;
return RX_CONTINUE;
@@ -294,8 +295,8 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx)
key, skb->data + hdrlen,
skb->len - hdrlen, rx->sta->sta.addr,
hdr->addr1, hwaccel, rx->security_idx,
- &rx->tkip_iv32,
- &rx->tkip_iv16);
+ &rx->tkip.iv32,
+ &rx->tkip.iv16);
if (res != TKIP_DECRYPT_OK)
return RX_DROP_UNUSABLE;
@@ -553,6 +554,8 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx,
}
memcpy(key->u.ccmp.rx_pn[queue], pn, IEEE80211_CCMP_PN_LEN);
+ if (unlikely(ieee80211_is_frag(hdr)))
+ memcpy(rx->ccm_gcm.pn, pn, IEEE80211_CCMP_PN_LEN);
}
/* Remove CCMP header and MIC */
@@ -781,6 +784,8 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx)
}
memcpy(key->u.gcmp.rx_pn[queue], pn, IEEE80211_GCMP_PN_LEN);
+ if (unlikely(ieee80211_is_frag(hdr)))
+ memcpy(rx->ccm_gcm.pn, pn, IEEE80211_CCMP_PN_LEN);
}
/* Remove GCMP header and MIC */
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 99fc21406168..6b825fb3fa83 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -130,7 +130,6 @@ static void mptcp_parse_option(const struct sk_buff *skb,
memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN);
pr_debug("MP_JOIN hmac");
} else {
- pr_warn("MP_JOIN bad option size");
mp_opt->mp_join = 0;
}
break;
@@ -1024,7 +1023,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR);
} else {
mptcp_pm_add_addr_echoed(msk, &mp_opt.addr);
- mptcp_pm_del_add_timer(msk, &mp_opt.addr);
+ mptcp_pm_del_add_timer(msk, &mp_opt.addr, true);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD);
}
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 6ba040897738..2469e06a3a9d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -346,18 +346,18 @@ out:
struct mptcp_pm_add_entry *
mptcp_pm_del_add_timer(struct mptcp_sock *msk,
- struct mptcp_addr_info *addr)
+ struct mptcp_addr_info *addr, bool check_id)
{
struct mptcp_pm_add_entry *entry;
struct sock *sk = (struct sock *)msk;
spin_lock_bh(&msk->pm.lock);
entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
- if (entry)
+ if (entry && (!check_id || entry->addr.id == addr->id))
entry->retrans_times = ADD_ADDR_RETRANS_MAX;
spin_unlock_bh(&msk->pm.lock);
- if (entry)
+ if (entry && (!check_id || entry->addr.id == addr->id))
sk_stop_timer_sync(sk, &entry->add_timer);
return entry;
@@ -1064,7 +1064,7 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
{
struct mptcp_pm_add_entry *entry;
- entry = mptcp_pm_del_add_timer(msk, addr);
+ entry = mptcp_pm_del_add_timer(msk, addr, false);
if (entry) {
list_del(&entry->list);
kfree(entry);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 29a2d690d8d5..2bc199549a88 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -879,12 +879,18 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq,
!mpext->frozen;
}
+/* we can append data to the given data frag if:
+ * - there is space available in the backing page_frag
+ * - the data frag tail matches the current page_frag free offset
+ * - the data frag end sequence number matches the current write seq
+ */
static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
const struct page_frag *pfrag,
const struct mptcp_data_frag *df)
{
return df && pfrag->page == df->page &&
pfrag->size - pfrag->offset > 0 &&
+ pfrag->offset == (df->offset + df->data_len) &&
df->data_seq + df->data_len == msk->write_seq;
}
@@ -2418,13 +2424,12 @@ static int __mptcp_init_sock(struct sock *sk)
timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
- tcp_assign_congestion_control(sk);
-
return 0;
}
static int mptcp_init_sock(struct sock *sk)
{
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct net *net = sock_net(sk);
int ret;
@@ -2442,6 +2447,16 @@ static int mptcp_init_sock(struct sock *sk)
if (ret)
return ret;
+ /* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will
+ * propagate the correct value
+ */
+ tcp_assign_congestion_control(sk);
+ strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name);
+
+ /* no need to keep a reference to the ops, the name will suffice */
+ tcp_cleanup_congestion_control(sk);
+ icsk->icsk_ca_ops = NULL;
+
sk_sockets_allocated_inc(sk);
sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
@@ -2616,7 +2631,6 @@ static void __mptcp_destroy_sock(struct sock *sk)
sk_stream_kill_queues(sk);
xfrm_sk_free_policy(sk);
- tcp_cleanup_congestion_control(sk);
sk_refcnt_debug_release(sk);
mptcp_dispose_initial_subflow(msk);
sock_put(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index edc0128730df..0c6f99c67345 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -258,6 +258,7 @@ struct mptcp_sock {
} rcvq_space;
u32 setsockopt_seq;
+ char ca_name[TCP_CA_NAME_MAX];
};
#define mptcp_lock_sock(___sk, cb) do { \
@@ -671,7 +672,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
struct mptcp_pm_add_entry *
mptcp_pm_del_add_timer(struct mptcp_sock *msk,
- struct mptcp_addr_info *addr);
+ struct mptcp_addr_info *addr, bool check_id);
struct mptcp_pm_add_entry *
mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk,
struct mptcp_addr_info *addr);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 00d941b66c1e..a79798189599 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -547,7 +547,7 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t
}
if (ret == 0)
- tcp_set_congestion_control(sk, name, false, cap_net_admin);
+ strcpy(msk->ca_name, name);
release_sock(sk);
return ret;
@@ -705,7 +705,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
sock_valbool_flag(ssk, SOCK_DBG, sock_flag(sk, SOCK_DBG));
if (inet_csk(sk)->icsk_ca_ops != inet_csk(ssk)->icsk_ca_ops)
- tcp_set_congestion_control(ssk, inet_csk(sk)->icsk_ca_ops->name, false, true);
+ tcp_set_congestion_control(ssk, msk->ca_name, false, true);
}
static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index a5ede357cfbc..bde6be77ea73 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -867,7 +867,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
data_len = mpext->data_len;
if (data_len == 0) {
- pr_err("Infinite mapping not handled");
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
return MAPPING_INVALID;
}
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 39c02d1aeedf..1d02650dd715 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -306,8 +306,7 @@ void flow_offload_refresh(struct nf_flowtable *flow_table,
{
flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
- if (likely(!nf_flowtable_hw_offload(flow_table) ||
- !test_and_clear_bit(NF_FLOW_HW_REFRESH, &flow->flags)))
+ if (likely(!nf_flowtable_hw_offload(flow_table)))
return;
nf_flow_offload_add(flow_table, flow);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 2af7bdb38407..528b2f172684 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -902,10 +902,11 @@ static void flow_offload_work_add(struct flow_offload_work *offload)
err = flow_offload_rule_add(offload, flow_rule);
if (err < 0)
- set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags);
- else
- set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status);
+ goto out;
+
+ set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status);
+out:
nf_flow_offload_destroy(flow_rule);
}
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 528a2d7ca991..dce866d93fee 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -408,8 +408,8 @@ int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst,
*
* Return: true on match, false otherwise.
*/
-static bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
- const u32 *key, const struct nft_set_ext **ext)
+bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
+ const u32 *key, const struct nft_set_ext **ext)
{
struct nft_pipapo *priv = nft_set_priv(set);
unsigned long *res_map, *fill_map;
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index 25a75591583e..d84afb8fa79a 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -178,6 +178,8 @@ struct nft_pipapo_elem {
int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst,
union nft_pipapo_map_bucket *mt, bool match_only);
+bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
+ const u32 *key, const struct nft_set_ext **ext);
/**
* pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index d65ae0e23028..eabdb8d552ee 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1131,6 +1131,9 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
bool map_index;
int i, ret = 0;
+ if (unlikely(!irq_fpu_usable()))
+ return nft_pipapo_lookup(net, set, key, ext);
+
m = rcu_dereference(priv->match);
/* This also protects access to all data related to scratch maps */
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 3a62f97acf39..6133e412b948 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -461,11 +461,13 @@ void netlink_table_ungrab(void)
static inline void
netlink_lock_table(void)
{
+ unsigned long flags;
+
/* read_lock() synchronizes us to netlink_table_grab */
- read_lock(&nl_table_lock);
+ read_lock_irqsave(&nl_table_lock, flags);
atomic_inc(&nl_table_users);
- read_unlock(&nl_table_lock);
+ read_unlock_irqrestore(&nl_table_lock, flags);
}
static inline void
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 9a585332ea84..da7fe9db1b00 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1191,6 +1191,7 @@ EXPORT_SYMBOL(nci_allocate_device);
void nci_free_device(struct nci_dev *ndev)
{
nfc_free_device(ndev->nfc_dev);
+ nci_hci_deallocate(ndev);
kfree(ndev);
}
EXPORT_SYMBOL(nci_free_device);
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
index 6b275a387a92..96865142104f 100644
--- a/net/nfc/nci/hci.c
+++ b/net/nfc/nci/hci.c
@@ -792,3 +792,8 @@ struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev)
return hdev;
}
+
+void nci_hci_deallocate(struct nci_dev *ndev)
+{
+ kfree(ndev->hci_dev);
+}
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index 9c7eb8455ba8..5f1d438a0a23 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -329,7 +329,7 @@ static int rawsock_create(struct net *net, struct socket *sock,
return -ESOCKTNOSUPPORT;
if (sock->type == SOCK_RAW) {
- if (!capable(CAP_NET_RAW))
+ if (!ns_capable(net->user_ns, CAP_NET_RAW))
return -EPERM;
sock->ops = &rawsock_raw_ops;
} else {
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 96b524ceabca..896b8f5bc885 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -611,6 +611,14 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
spin_lock(&meter->lock);
long_delta_ms = (now_ms - meter->used); /* ms */
+ if (long_delta_ms < 0) {
+ /* This condition means that we have several threads fighting
+ * for a meter lock, and the one who received the packets a
+ * bit later wins. Assuming that all racing threads received
+ * packets at the same time to avoid overflow.
+ */
+ long_delta_ms = 0;
+ }
/* Make sure delta_ms will not be too large, so that bucket will not
* wrap around below.
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ba96db1880ea..ae906eb4b269 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -422,7 +422,8 @@ static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts,
ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts))
return TP_STATUS_TS_RAW_HARDWARE;
- if (ktime_to_timespec64_cond(skb->tstamp, ts))
+ if ((flags & SOF_TIMESTAMPING_SOFTWARE) &&
+ ktime_to_timespec64_cond(skb->tstamp, ts))
return TP_STATUS_TS_SOFTWARE;
return 0;
@@ -2340,7 +2341,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
- if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
+ /* Always timestamp; prefer an existing software timestamp taken
+ * closer to the time of capture.
+ */
+ ts_status = tpacket_get_timestamp(skb, &ts,
+ po->tp_tstamp | SOF_TIMESTAMPING_SOFTWARE);
+ if (!ts_status)
ktime_get_real_ts64(&ts);
status |= ts_status;
diff --git a/net/rds/connection.c b/net/rds/connection.c
index f2fcab182095..a3bc4b54d491 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -240,12 +240,23 @@ static struct rds_connection *__rds_conn_create(struct net *net,
if (loop_trans) {
rds_trans_put(loop_trans);
conn->c_loopback = 1;
- if (is_outgoing && trans->t_prefer_loopback) {
- /* "outgoing" connection - and the transport
- * says it wants the connection handled by the
- * loopback transport. This is what TCP does.
- */
- trans = &rds_loop_transport;
+ if (trans->t_prefer_loopback) {
+ if (likely(is_outgoing)) {
+ /* "outgoing" connection to local address.
+ * Protocol says it wants the connection
+ * handled by the loopback transport.
+ * This is what TCP does.
+ */
+ trans = &rds_loop_transport;
+ } else {
+ /* No transport currently in use
+ * should end up here, but if it
+ * does, reset/destroy the connection.
+ */
+ kmem_cache_free(rds_conn_slab, conn);
+ conn = ERR_PTR(-EOPNOTSUPP);
+ goto out;
+ }
}
}
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 43db0eca911f..abf19c0e3ba0 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -313,8 +313,8 @@ out:
}
#endif
-static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
- __u32 scope_id)
+int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
+ __u32 scope_id)
{
struct net_device *dev = NULL;
#if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index bad9cf49d565..dc8d745d6857 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -59,7 +59,8 @@ u32 rds_tcp_snd_una(struct rds_tcp_connection *tc);
u64 rds_tcp_map_seq(struct rds_tcp_connection *tc, u32 seq);
extern struct rds_transport rds_tcp_transport;
void rds_tcp_accept_work(struct sock *sk);
-
+int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
+ __u32 scope_id);
/* tcp_connect.c */
int rds_tcp_conn_path_connect(struct rds_conn_path *cp);
void rds_tcp_conn_path_shutdown(struct rds_conn_path *conn);
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 101cf14215a0..09cadd556d1e 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -167,6 +167,12 @@ int rds_tcp_accept_one(struct socket *sock)
}
#endif
+ if (!rds_tcp_laddr_check(sock_net(sock->sk), peer_addr, dev_if)) {
+ /* local address connection is only allowed via loopback */
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
conn = rds_conn_create(sock_net(sock->sk),
my_addr, peer_addr,
&rds_tcp_transport, 0, GFP_KERNEL, dev_if);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 40fbea626dfd..279f9e2a2319 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1624,7 +1624,7 @@ int tcf_classify_ingress(struct sk_buff *skb,
/* If we missed on some chain */
if (ret == TC_ACT_UNSPEC && last_executed_chain) {
- ext = skb_ext_add(skb, TC_SKB_EXT);
+ ext = tc_skb_ext_alloc(skb);
if (WARN_ON_ONCE(!ext))
return TC_ACT_SHOT;
ext->chain = last_executed_chain;
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index cd2748e2d4a2..d320bcfb2da2 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -407,7 +407,8 @@ static void dsmark_reset(struct Qdisc *sch)
struct dsmark_qdisc_data *p = qdisc_priv(sch);
pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
- qdisc_reset(p->q);
+ if (p->q)
+ qdisc_reset(p->q);
sch->qstats.backlog = 0;
sch->q.qlen = 0;
}
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 949163fe68af..cac684952edc 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -138,8 +138,15 @@ static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
/* Classifies packet into corresponding flow */
idx = fq_pie_classify(skb, sch, &ret);
- sel_flow = &q->flows[idx];
+ if (idx == 0) {
+ if (ret & __NET_XMIT_BYPASS)
+ qdisc_qstats_drop(sch);
+ __qdisc_drop(skb, to_free);
+ return ret;
+ }
+ idx--;
+ sel_flow = &q->flows[idx];
/* Checks whether adding a new packet would exceed memory limit */
get_pie_cb(skb)->mem_usage = skb->truesize;
memory_limited = q->memory_usage > q->memory_limit + skb->truesize;
@@ -297,9 +304,9 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
goto flow_error;
}
q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]);
- if (!q->flows_cnt || q->flows_cnt >= 65536) {
+ if (!q->flows_cnt || q->flows_cnt > 65536) {
NL_SET_ERR_MSG_MOD(extack,
- "Number of flows must range in [1..65535]");
+ "Number of flows must range in [1..65536]");
goto flow_error;
}
}
@@ -367,7 +374,7 @@ static void fq_pie_timer(struct timer_list *t)
struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer);
struct Qdisc *sch = q->sch;
spinlock_t *root_lock; /* to lock qdisc for probability calculations */
- u16 idx;
+ u32 idx;
root_lock = qdisc_lock(qdisc_root_sleeping(sch));
spin_lock(root_lock);
@@ -388,7 +395,7 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt,
{
struct fq_pie_sched_data *q = qdisc_priv(sch);
int err;
- u16 idx;
+ u32 idx;
pie_params_init(&q->p_params);
sch->limit = 10 * 1024;
@@ -500,7 +507,7 @@ static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
static void fq_pie_reset(struct Qdisc *sch)
{
struct fq_pie_sched_data *q = qdisc_priv(sch);
- u16 idx;
+ u32 idx;
INIT_LIST_HEAD(&q->new_flows);
INIT_LIST_HEAD(&q->old_flows);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 44991ea726fc..fc8b56bcabf3 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -35,6 +35,25 @@
const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops;
EXPORT_SYMBOL(default_qdisc_ops);
+static void qdisc_maybe_clear_missed(struct Qdisc *q,
+ const struct netdev_queue *txq)
+{
+ clear_bit(__QDISC_STATE_MISSED, &q->state);
+
+ /* Make sure the below netif_xmit_frozen_or_stopped()
+ * checking happens after clearing STATE_MISSED.
+ */
+ smp_mb__after_atomic();
+
+ /* Checking netif_xmit_frozen_or_stopped() again to
+ * make sure STATE_MISSED is set if the STATE_MISSED
+ * set by netif_tx_wake_queue()'s rescheduling of
+ * net_tx_action() is cleared by the above clear_bit().
+ */
+ if (!netif_xmit_frozen_or_stopped(txq))
+ set_bit(__QDISC_STATE_MISSED, &q->state);
+}
+
/* Main transmission queue. */
/* Modifications to data participating in scheduling must be protected with
@@ -74,6 +93,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
}
} else {
skb = SKB_XOFF_MAGIC;
+ qdisc_maybe_clear_missed(q, txq);
}
}
@@ -242,6 +262,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
}
} else {
skb = NULL;
+ qdisc_maybe_clear_missed(q, txq);
}
if (lock)
spin_unlock(lock);
@@ -251,8 +272,10 @@ validate:
*validate = true;
if ((q->flags & TCQ_F_ONETXQUEUE) &&
- netif_xmit_frozen_or_stopped(txq))
+ netif_xmit_frozen_or_stopped(txq)) {
+ qdisc_maybe_clear_missed(q, txq);
return skb;
+ }
skb = qdisc_dequeue_skb_bad_txq(q);
if (unlikely(skb)) {
@@ -311,6 +334,8 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (!netif_xmit_frozen_or_stopped(txq))
skb = dev_hard_start_xmit(skb, dev, txq, &ret);
+ else
+ qdisc_maybe_clear_missed(q, txq);
HARD_TX_UNLOCK(dev, txq);
} else {
@@ -640,8 +665,10 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
{
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
struct sk_buff *skb = NULL;
+ bool need_retry = true;
int band;
+retry:
for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) {
struct skb_array *q = band2list(priv, band);
@@ -652,6 +679,23 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
}
if (likely(skb)) {
qdisc_update_stats_at_dequeue(qdisc, skb);
+ } else if (need_retry &&
+ test_bit(__QDISC_STATE_MISSED, &qdisc->state)) {
+ /* Delay clearing the STATE_MISSED here to reduce
+ * the overhead of the second spin_trylock() in
+ * qdisc_run_begin() and __netif_schedule() calling
+ * in qdisc_run_end().
+ */
+ clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
+
+ /* Make sure dequeuing happens after clearing
+ * STATE_MISSED.
+ */
+ smp_mb__after_atomic();
+
+ need_retry = false;
+
+ goto retry;
} else {
WRITE_ONCE(qdisc->empty, true);
}
@@ -1158,8 +1202,10 @@ static void dev_reset_queue(struct net_device *dev,
qdisc_reset(qdisc);
spin_unlock_bh(qdisc_lock(qdisc));
- if (nolock)
+ if (nolock) {
+ clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
spin_unlock_bh(&qdisc->seqlock);
+ }
}
static bool some_qdisc_is_busy(struct net_device *dev)
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 40f9f6c4a0a1..a79d193ff872 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4473,6 +4473,7 @@ static int sctp_setsockopt_encap_port(struct sock *sk,
transports)
t->encap_port = encap_port;
+ asoc->encap_port = encap_port;
return 0;
}
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index e92df779af73..55871b277f47 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -307,7 +307,7 @@ static struct ctl_table sctp_net_table[] = {
.data = &init_net.sctp.encap_port,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = &udp_port_max,
},
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 9c6e95882553..967712ba52a0 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -402,6 +402,14 @@ struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
return NULL;
}
+ smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
+ WQ_MEM_RECLAIM, name);
+ if (!smcd->event_wq) {
+ kfree(smcd->conn);
+ kfree(smcd);
+ return NULL;
+ }
+
smcd->dev.parent = parent;
smcd->dev.release = smcd_release;
device_initialize(&smcd->dev);
@@ -415,19 +423,14 @@ struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
INIT_LIST_HEAD(&smcd->vlan);
INIT_LIST_HEAD(&smcd->lgr_list);
init_waitqueue_head(&smcd->lgrs_deleted);
- smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
- WQ_MEM_RECLAIM, name);
- if (!smcd->event_wq) {
- kfree(smcd->conn);
- kfree(smcd);
- return NULL;
- }
return smcd;
}
EXPORT_SYMBOL_GPL(smcd_alloc_dev);
int smcd_register_dev(struct smcd_dev *smcd)
{
+ int rc;
+
mutex_lock(&smcd_dev_list.mutex);
if (list_empty(&smcd_dev_list.list)) {
u8 *system_eid = NULL;
@@ -447,7 +450,14 @@ int smcd_register_dev(struct smcd_dev *smcd)
dev_name(&smcd->dev), smcd->pnetid,
smcd->pnetid_by_user ? " (user defined)" : "");
- return device_add(&smcd->dev);
+ rc = device_add(&smcd->dev);
+ if (rc) {
+ mutex_lock(&smcd_dev_list.mutex);
+ list_del(&smcd->list);
+ mutex_unlock(&smcd_dev_list.mutex);
+ }
+
+ return rc;
}
EXPORT_SYMBOL_GPL(smcd_register_dev);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index f555d335e910..42623d6b8f0e 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1677,13 +1677,6 @@ call_reserveresult(struct rpc_task *task)
return;
}
- /*
- * Even though there was an error, we may have acquired
- * a request slot somehow. Make sure not to leak it.
- */
- if (task->tk_rqstp)
- xprt_release(task);
-
switch (status) {
case -ENOMEM:
rpc_delay(task, HZ >> 2);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index e5b5a960a69b..3509a7f139b9 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -70,6 +70,7 @@
static void xprt_init(struct rpc_xprt *xprt, struct net *net);
static __be32 xprt_alloc_xid(struct rpc_xprt *xprt);
static void xprt_destroy(struct rpc_xprt *xprt);
+static void xprt_request_init(struct rpc_task *task);
static DEFINE_SPINLOCK(xprt_list_lock);
static LIST_HEAD(xprt_list);
@@ -1606,17 +1607,40 @@ xprt_transmit(struct rpc_task *task)
spin_unlock(&xprt->queue_lock);
}
-static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task)
+static void xprt_complete_request_init(struct rpc_task *task)
+{
+ if (task->tk_rqstp)
+ xprt_request_init(task);
+}
+
+void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task)
{
set_bit(XPRT_CONGESTED, &xprt->state);
- rpc_sleep_on(&xprt->backlog, task, NULL);
+ rpc_sleep_on(&xprt->backlog, task, xprt_complete_request_init);
+}
+EXPORT_SYMBOL_GPL(xprt_add_backlog);
+
+static bool __xprt_set_rq(struct rpc_task *task, void *data)
+{
+ struct rpc_rqst *req = data;
+
+ if (task->tk_rqstp == NULL) {
+ memset(req, 0, sizeof(*req)); /* mark unused */
+ task->tk_rqstp = req;
+ return true;
+ }
+ return false;
}
-static void xprt_wake_up_backlog(struct rpc_xprt *xprt)
+bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req)
{
- if (rpc_wake_up_next(&xprt->backlog) == NULL)
+ if (rpc_wake_up_first(&xprt->backlog, __xprt_set_rq, req) == NULL) {
clear_bit(XPRT_CONGESTED, &xprt->state);
+ return false;
+ }
+ return true;
}
+EXPORT_SYMBOL_GPL(xprt_wake_up_backlog);
static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task)
{
@@ -1626,7 +1650,7 @@ static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task
goto out;
spin_lock(&xprt->reserve_lock);
if (test_bit(XPRT_CONGESTED, &xprt->state)) {
- rpc_sleep_on(&xprt->backlog, task, NULL);
+ xprt_add_backlog(xprt, task);
ret = true;
}
spin_unlock(&xprt->reserve_lock);
@@ -1703,11 +1727,11 @@ EXPORT_SYMBOL_GPL(xprt_alloc_slot);
void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req)
{
spin_lock(&xprt->reserve_lock);
- if (!xprt_dynamic_free_slot(xprt, req)) {
+ if (!xprt_wake_up_backlog(xprt, req) &&
+ !xprt_dynamic_free_slot(xprt, req)) {
memset(req, 0, sizeof(*req)); /* mark unused */
list_add(&req->rq_list, &xprt->free);
}
- xprt_wake_up_backlog(xprt);
spin_unlock(&xprt->reserve_lock);
}
EXPORT_SYMBOL_GPL(xprt_free_slot);
@@ -1894,10 +1918,10 @@ void xprt_release(struct rpc_task *task)
xdr_free_bvec(&req->rq_snd_buf);
if (req->rq_cred != NULL)
put_rpccred(req->rq_cred);
- task->tk_rqstp = NULL;
if (req->rq_release_snd_buf)
req->rq_release_snd_buf(req);
+ task->tk_rqstp = NULL;
if (likely(!bc_prealloc(req)))
xprt->ops->free_slot(xprt, req);
else
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 649f7d8b9733..c335c1361564 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -628,8 +628,9 @@ out_mapping_err:
return false;
}
-/* The tail iovec might not reside in the same page as the
- * head iovec.
+/* The tail iovec may include an XDR pad for the page list,
+ * as well as additional content, and may not reside in the
+ * same page as the head iovec.
*/
static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req,
struct xdr_buf *xdr,
@@ -747,19 +748,27 @@ static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt,
struct rpcrdma_req *req,
struct xdr_buf *xdr)
{
- struct kvec *tail = &xdr->tail[0];
-
if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len))
return false;
- /* If there is a Read chunk, the page list is handled
+ /* If there is a Read chunk, the page list is being handled
* via explicit RDMA, and thus is skipped here.
*/
- if (tail->iov_len) {
- if (!rpcrdma_prepare_tail_iov(req, xdr,
- offset_in_page(tail->iov_base),
- tail->iov_len))
+ /* Do not include the tail if it is only an XDR pad */
+ if (xdr->tail[0].iov_len > 3) {
+ unsigned int page_base, len;
+
+ /* If the content in the page list is an odd length,
+ * xdr_write_pages() adds a pad at the beginning of
+ * the tail iovec. Force the tail's non-pad content to
+ * land at the next XDR position in the Send message.
+ */
+ page_base = offset_in_page(xdr->tail[0].iov_base);
+ len = xdr->tail[0].iov_len;
+ page_base += len & 3;
+ len -= len & 3;
+ if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len))
return false;
kref_get(&req->rl_kref);
}
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 09953597d055..19a49d26b1e4 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -520,9 +520,8 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
return;
out_sleep:
- set_bit(XPRT_CONGESTED, &xprt->state);
- rpc_sleep_on(&xprt->backlog, task, NULL);
task->tk_status = -EAGAIN;
+ xprt_add_backlog(xprt, task);
}
/**
@@ -537,10 +536,11 @@ xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst)
struct rpcrdma_xprt *r_xprt =
container_of(xprt, struct rpcrdma_xprt, rx_xprt);
- memset(rqst, 0, sizeof(*rqst));
- rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst));
- if (unlikely(!rpc_wake_up_next(&xprt->backlog)))
- clear_bit(XPRT_CONGESTED, &xprt->state);
+ rpcrdma_reply_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst));
+ if (!xprt_wake_up_backlog(xprt, rqst)) {
+ memset(rqst, 0, sizeof(*rqst));
+ rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst));
+ }
}
static bool rpcrdma_check_regbuf(struct rpcrdma_xprt *r_xprt,
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 1e965a380896..649c23518ec0 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1201,6 +1201,20 @@ rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt)
}
/**
+ * rpcrdma_reply_put - Put reply buffers back into pool
+ * @buffers: buffer pool
+ * @req: object to return
+ *
+ */
+void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req)
+{
+ if (req->rl_reply) {
+ rpcrdma_rep_put(buffers, req->rl_reply);
+ req->rl_reply = NULL;
+ }
+}
+
+/**
* rpcrdma_buffer_get - Get a request buffer
* @buffers: Buffer pool from which to obtain a buffer
*
@@ -1228,9 +1242,7 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
*/
void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req)
{
- if (req->rl_reply)
- rpcrdma_rep_put(buffers, req->rl_reply);
- req->rl_reply = NULL;
+ rpcrdma_reply_put(buffers, req);
spin_lock(&buffers->rb_lock);
list_add(&req->rl_list, &buffers->rb_send_bufs);
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 436ad7312614..5d231d94e944 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -479,6 +479,7 @@ struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *);
void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers,
struct rpcrdma_req *req);
void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep);
+void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req);
bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size,
gfp_t flags);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 47aa47a2b07c..316d04945587 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1010,6 +1010,8 @@ static int xs_tcp_send_request(struct rpc_rqst *req)
kernel_sock_shutdown(transport->sock, SHUT_RDWR);
return -ENOTCONN;
}
+ if (!transport->inet)
+ return -ENOTCONN;
xs_pktdump("packet data:",
req->rq_svec->iov_base,
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 5cc1f0307215..3f4542e0f065 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -60,7 +60,7 @@ static int __net_init tipc_init_net(struct net *net)
tn->trial_addr = 0;
tn->addr_trial_end = 0;
tn->capabilities = TIPC_NODE_CAPABILITIES;
- INIT_WORK(&tn->final_work.work, tipc_net_finalize_work);
+ INIT_WORK(&tn->work, tipc_net_finalize_work);
memset(tn->node_id, 0, sizeof(tn->node_id));
memset(tn->node_id_string, 0, sizeof(tn->node_id_string));
tn->mon_threshold = TIPC_DEF_MON_THRESHOLD;
@@ -110,7 +110,7 @@ static void __net_exit tipc_exit_net(struct net *net)
tipc_detach_loopback(net);
/* Make sure the tipc_net_finalize_work() finished */
- cancel_work_sync(&tn->final_work.work);
+ cancel_work_sync(&tn->work);
tipc_net_stop(net);
tipc_bcast_stop(net);
@@ -119,6 +119,8 @@ static void __net_exit tipc_exit_net(struct net *net)
#ifdef CONFIG_TIPC_CRYPTO
tipc_crypto_stop(&tipc_net(net)->crypto_tx);
#endif
+ while (atomic_read(&tn->wq_count))
+ cond_resched();
}
static void __net_exit tipc_pernet_pre_exit(struct net *net)
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 03de7b213f55..0a3f7a70a50a 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -91,12 +91,6 @@ extern unsigned int tipc_net_id __read_mostly;
extern int sysctl_tipc_rmem[3] __read_mostly;
extern int sysctl_tipc_named_timeout __read_mostly;
-struct tipc_net_work {
- struct work_struct work;
- struct net *net;
- u32 addr;
-};
-
struct tipc_net {
u8 node_id[NODE_ID_LEN];
u32 node_addr;
@@ -148,7 +142,9 @@ struct tipc_net {
struct tipc_crypto *crypto_tx;
#endif
/* Work item for net finalize */
- struct tipc_net_work final_work;
+ struct work_struct work;
+ /* The numbers of work queues in schedule */
+ atomic_t wq_count;
};
static inline struct tipc_net *tipc_net(struct net *net)
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 5380f605b851..da69e1abf68f 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -168,7 +168,7 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d,
/* Apply trial address if we just left trial period */
if (!trial && !self) {
- tipc_sched_net_finalize(net, tn->trial_addr);
+ schedule_work(&tn->work);
msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
}
@@ -308,7 +308,7 @@ static void tipc_disc_timeout(struct timer_list *t)
if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) {
mod_timer(&d->timer, jiffies + TIPC_DISC_INIT);
spin_unlock_bh(&d->lock);
- tipc_sched_net_finalize(net, tn->trial_addr);
+ schedule_work(&tn->work);
return;
}
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 115109259430..c44b4bfaaee6 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -372,6 +372,11 @@ char tipc_link_plane(struct tipc_link *l)
return l->net_plane;
}
+struct net *tipc_link_net(struct tipc_link *l)
+{
+ return l->net;
+}
+
void tipc_link_update_caps(struct tipc_link *l, u16 capabilities)
{
l->peer_caps = capabilities;
diff --git a/net/tipc/link.h b/net/tipc/link.h
index fc07232c9a12..a16f401fdabd 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -156,4 +156,5 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr,
int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb,
struct sk_buff_head *xmitq);
bool tipc_link_too_silent(struct tipc_link *l);
+struct net *tipc_link_net(struct tipc_link *l);
#endif
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 3f0a25345a7c..ce6ab54822d8 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -149,18 +149,13 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
if (unlikely(head))
goto err;
*buf = NULL;
+ if (skb_has_frag_list(frag) && __skb_linearize(frag))
+ goto err;
frag = skb_unshare(frag, GFP_ATOMIC);
if (unlikely(!frag))
goto err;
head = *headbuf = frag;
TIPC_SKB_CB(head)->tail = NULL;
- if (skb_is_nonlinear(head)) {
- skb_walk_frags(head, tail) {
- TIPC_SKB_CB(head)->tail = tail;
- }
- } else {
- skb_frag_list_init(head);
- }
return 0;
}
diff --git a/net/tipc/net.c b/net/tipc/net.c
index a130195af188..0e95572e56b4 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -41,6 +41,7 @@
#include "socket.h"
#include "node.h"
#include "bcast.h"
+#include "link.h"
#include "netlink.h"
#include "monitor.h"
@@ -142,19 +143,9 @@ static void tipc_net_finalize(struct net *net, u32 addr)
void tipc_net_finalize_work(struct work_struct *work)
{
- struct tipc_net_work *fwork;
+ struct tipc_net *tn = container_of(work, struct tipc_net, work);
- fwork = container_of(work, struct tipc_net_work, work);
- tipc_net_finalize(fwork->net, fwork->addr);
-}
-
-void tipc_sched_net_finalize(struct net *net, u32 addr)
-{
- struct tipc_net *tn = tipc_net(net);
-
- tn->final_work.net = net;
- tn->final_work.addr = addr;
- schedule_work(&tn->final_work.work);
+ tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr);
}
void tipc_net_stop(struct net *net)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 8217905348f4..81af92954c6c 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -423,18 +423,18 @@ static void tipc_node_write_unlock(struct tipc_node *n)
write_unlock_bh(&n->lock);
if (flags & TIPC_NOTIFY_NODE_DOWN)
- tipc_publ_notify(net, publ_list, n->addr, n->capabilities);
+ tipc_publ_notify(net, publ_list, sk.node, n->capabilities);
if (flags & TIPC_NOTIFY_NODE_UP)
- tipc_named_node_up(net, n->addr, n->capabilities);
+ tipc_named_node_up(net, sk.node, n->capabilities);
if (flags & TIPC_NOTIFY_LINK_UP) {
- tipc_mon_peer_up(net, n->addr, bearer_id);
- tipc_nametbl_publish(net, &ua, &sk, n->link_id);
+ tipc_mon_peer_up(net, sk.node, bearer_id);
+ tipc_nametbl_publish(net, &ua, &sk, sk.ref);
}
if (flags & TIPC_NOTIFY_LINK_DOWN) {
- tipc_mon_peer_down(net, n->addr, bearer_id);
- tipc_nametbl_withdraw(net, &ua, &sk, n->link_id);
+ tipc_mon_peer_down(net, sk.node, bearer_id);
+ tipc_nametbl_withdraw(net, &ua, &sk, sk.ref);
}
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 58935cd0d068..53af72824c9c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1262,7 +1262,10 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
spin_lock_bh(&inputq->lock);
if (skb_peek(arrvq) == skb) {
skb_queue_splice_tail_init(&tmpq, inputq);
- __skb_dequeue(arrvq);
+ /* Decrease the skb's refcnt as increasing in the
+ * function tipc_skb_peek
+ */
+ kfree_skb(__skb_dequeue(arrvq));
}
spin_unlock_bh(&inputq->lock);
__skb_queue_purge(&tmpq);
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index e556d2cdc064..c2bb818704c8 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -814,6 +814,7 @@ static void cleanup_bearer(struct work_struct *work)
kfree_rcu(rcast, rcu);
}
+ atomic_dec(&tipc_net(sock_net(ub->ubsock->sk))->wq_count);
dst_cache_destroy(&ub->rcast.dst_cache);
udp_tunnel_sock_release(ub->ubsock);
synchronize_net();
@@ -834,6 +835,7 @@ static void tipc_udp_disable(struct tipc_bearer *b)
RCU_INIT_POINTER(ub->bearer, NULL);
/* sock_release need to be done outside of rtnl lock */
+ atomic_inc(&tipc_net(sock_net(ub->ubsock->sk))->wq_count);
INIT_WORK(&ub->work, cleanup_bearer);
schedule_work(&ub->work);
}
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 1dcb34dfd56b..694de024d0ee 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -37,6 +37,7 @@
#include <linux/sched/signal.h>
#include <linux/module.h>
+#include <linux/splice.h>
#include <crypto/aead.h>
#include <net/strparser.h>
@@ -1281,7 +1282,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
}
static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock,
- int flags, long timeo, int *err)
+ bool nonblock, long timeo, int *err)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
@@ -1306,7 +1307,7 @@ static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock,
if (sock_flag(sk, SOCK_DONE))
return NULL;
- if ((flags & MSG_DONTWAIT) || !timeo) {
+ if (nonblock || !timeo) {
*err = -EAGAIN;
return NULL;
}
@@ -1786,7 +1787,7 @@ int tls_sw_recvmsg(struct sock *sk,
bool async_capable;
bool async = false;
- skb = tls_wait_data(sk, psock, flags, timeo, &err);
+ skb = tls_wait_data(sk, psock, flags & MSG_DONTWAIT, timeo, &err);
if (!skb) {
if (psock) {
int ret = sk_msg_recvmsg(sk, psock, msg, len,
@@ -1990,9 +1991,9 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
lock_sock(sk);
- timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+ timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK);
- skb = tls_wait_data(sk, NULL, flags, timeo, &err);
+ skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, &err);
if (!skb)
goto splice_read_end;
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 382c5262d997..7ec021a610ae 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -542,7 +542,7 @@ EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen);
int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
const u8 *addr, enum nl80211_iftype iftype,
- u8 data_offset)
+ u8 data_offset, bool is_amsdu)
{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
struct {
@@ -629,7 +629,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
skb_copy_bits(skb, hdrlen, &payload, sizeof(payload));
tmp.h_proto = payload.proto;
- if (likely((ether_addr_equal(payload.hdr, rfc1042_header) &&
+ if (likely((!is_amsdu && ether_addr_equal(payload.hdr, rfc1042_header) &&
tmp.h_proto != htons(ETH_P_AARP) &&
tmp.h_proto != htons(ETH_P_IPX)) ||
ether_addr_equal(payload.hdr, bridge_tunnel_header)))
@@ -771,6 +771,9 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
remaining = skb->len - offset;
if (subframe_len > remaining)
goto purge;
+ /* mitigate A-MSDU aggregation injection attacks */
+ if (ether_addr_equal(eth.h_dest, rfc1042_header))
+ goto purge;
offset += sizeof(struct ethhdr);
last = remaining <= subframe_len + padding;