summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorDaiane Angolini <daiane.angolini@foundries.io>2022-11-08 16:35:18 -0300
committerDaiane Angolini <daiane.angolini@foundries.io>2022-11-08 16:35:18 -0300
commit28f04363b04142c45f8a29d0c32e21b060975e90 (patch)
tree8578cfe035db9bd4b78a0c504512c5e7f89a96cb /net
parent7540d075c97713a4366a00b5c928261436b93d2d (diff)
parentbd8a595958a5b02e58cdd6fed82d4ebc77b1988a (diff)
Merge tag 'v5.15.75' into 5.15-2.1.x-imx
This is the 5.15.75 stable release Conflicts: arch/arm/boot/dts/imx6dl.dtsi arch/arm/boot/dts/imx6q.dtsi arch/arm/boot/dts/imx6sl.dtsi arch/arm/boot/dts/imx6sll.dtsi arch/arm/boot/dts/imx6sx.dtsi arch/arm/boot/dts/imx7d-sdb.dts drivers/char/hw_random/imx-rngc.c drivers/dma/mxs-dma.c drivers/gpu/drm/bridge/adv7511/adv7511_drv.c drivers/tty/serial/fsl_lpuart.c drivers/usb/host/xhci.h Signed-off-by: Daiane Angolini <daiane.angolini@foundries.io>
Diffstat (limited to 'net')
-rw-r--r--net/bluetooth/hci_core.c34
-rw-r--r--net/bluetooth/hci_sysfs.c3
-rw-r--r--net/bluetooth/l2cap_core.c17
-rw-r--r--net/bluetooth/rfcomm/sock.c3
-rw-r--r--net/can/bcm.c7
-rw-r--r--net/core/skmsg.c12
-rw-r--r--net/core/stream.c3
-rw-r--r--net/ieee802154/socket.c4
-rw-r--r--net/ipv4/inet_hashtables.c4
-rw-r--r--net/ipv4/netfilter/nft_fib_ipv4.c3
-rw-r--r--net/ipv4/tcp.c16
-rw-r--r--net/ipv4/tcp_output.c19
-rw-r--r--net/ipv6/netfilter/nft_fib_ipv6.c6
-rw-r--r--net/mac80211/cfg.c3
-rw-r--r--net/netfilter/nf_conntrack_core.c18
-rw-r--r--net/openvswitch/datapath.c18
-rw-r--r--net/rds/tcp.c2
-rw-r--r--net/sctp/auth.c18
-rw-r--r--net/unix/garbage.c20
-rw-r--r--net/vmw_vsock/virtio_transport_common.c2
-rw-r--r--net/xdp/xsk.c22
-rw-r--r--net/xdp/xsk_queue.h22
-rw-r--r--net/xfrm/xfrm_input.c18
-rw-r--r--net/xfrm/xfrm_ipcomp.c1
24 files changed, 191 insertions, 84 deletions
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index cdca53732304..396696241d17 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -4673,15 +4673,27 @@ static inline int __get_blocks(struct hci_dev *hdev, struct sk_buff *skb)
return DIV_ROUND_UP(skb->len - HCI_ACL_HDR_SIZE, hdev->block_len);
}
-static void __check_timeout(struct hci_dev *hdev, unsigned int cnt)
+static void __check_timeout(struct hci_dev *hdev, unsigned int cnt, u8 type)
{
- if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
- /* ACL tx timeout must be longer than maximum
- * link supervision timeout (40.9 seconds) */
- if (!cnt && time_after(jiffies, hdev->acl_last_tx +
- HCI_ACL_TX_TIMEOUT))
- hci_link_tx_to(hdev, ACL_LINK);
+ unsigned long last_tx;
+
+ if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED))
+ return;
+
+ switch (type) {
+ case LE_LINK:
+ last_tx = hdev->le_last_tx;
+ break;
+ default:
+ last_tx = hdev->acl_last_tx;
+ break;
}
+
+ /* tx timeout must be longer than maximum link supervision timeout
+ * (40.9 seconds)
+ */
+ if (!cnt && time_after(jiffies, last_tx + HCI_ACL_TX_TIMEOUT))
+ hci_link_tx_to(hdev, type);
}
/* Schedule SCO */
@@ -4739,7 +4751,7 @@ static void hci_sched_acl_pkt(struct hci_dev *hdev)
struct sk_buff *skb;
int quote;
- __check_timeout(hdev, cnt);
+ __check_timeout(hdev, cnt, ACL_LINK);
while (hdev->acl_cnt &&
(chan = hci_chan_sent(hdev, ACL_LINK, &quote))) {
@@ -4782,8 +4794,6 @@ static void hci_sched_acl_blk(struct hci_dev *hdev)
int quote;
u8 type;
- __check_timeout(hdev, cnt);
-
BT_DBG("%s", hdev->name);
if (hdev->dev_type == HCI_AMP)
@@ -4791,6 +4801,8 @@ static void hci_sched_acl_blk(struct hci_dev *hdev)
else
type = ACL_LINK;
+ __check_timeout(hdev, cnt, type);
+
while (hdev->block_cnt > 0 &&
(chan = hci_chan_sent(hdev, type, &quote))) {
u32 priority = (skb_peek(&chan->data_q))->priority;
@@ -4864,7 +4876,7 @@ static void hci_sched_le(struct hci_dev *hdev)
cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt;
- __check_timeout(hdev, cnt);
+ __check_timeout(hdev, cnt, LE_LINK);
tmp = cnt;
while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, &quote))) {
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index 4e3e0451b08c..08542dfc2dc5 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -48,6 +48,9 @@ void hci_conn_add_sysfs(struct hci_conn *conn)
BT_DBG("conn %p", conn);
+ if (device_is_registered(&conn->dev))
+ return;
+
dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle);
if (device_add(&conn->dev) < 0) {
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index e8de1e7d6ff4..8f1a95b9d320 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -61,6 +61,9 @@ static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err);
static void l2cap_tx(struct l2cap_chan *chan, struct l2cap_ctrl *control,
struct sk_buff_head *skbs, u8 event);
+static void l2cap_retrans_timeout(struct work_struct *work);
+static void l2cap_monitor_timeout(struct work_struct *work);
+static void l2cap_ack_timeout(struct work_struct *work);
static inline u8 bdaddr_type(u8 link_type, u8 bdaddr_type)
{
@@ -476,6 +479,9 @@ struct l2cap_chan *l2cap_chan_create(void)
write_unlock(&chan_list_lock);
INIT_DELAYED_WORK(&chan->chan_timer, l2cap_chan_timeout);
+ INIT_DELAYED_WORK(&chan->retrans_timer, l2cap_retrans_timeout);
+ INIT_DELAYED_WORK(&chan->monitor_timer, l2cap_monitor_timeout);
+ INIT_DELAYED_WORK(&chan->ack_timer, l2cap_ack_timeout);
chan->state = BT_OPEN;
@@ -3320,10 +3326,6 @@ int l2cap_ertm_init(struct l2cap_chan *chan)
chan->rx_state = L2CAP_RX_STATE_RECV;
chan->tx_state = L2CAP_TX_STATE_XMIT;
- INIT_DELAYED_WORK(&chan->retrans_timer, l2cap_retrans_timeout);
- INIT_DELAYED_WORK(&chan->monitor_timer, l2cap_monitor_timeout);
- INIT_DELAYED_WORK(&chan->ack_timer, l2cap_ack_timeout);
-
skb_queue_head_init(&chan->srej_q);
err = l2cap_seq_list_init(&chan->srej_list, chan->tx_win);
@@ -4307,6 +4309,12 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn,
}
}
+ chan = l2cap_chan_hold_unless_zero(chan);
+ if (!chan) {
+ err = -EBADSLT;
+ goto unlock;
+ }
+
err = 0;
l2cap_chan_lock(chan);
@@ -4336,6 +4344,7 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn,
}
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
unlock:
mutex_unlock(&conn->chan_lock);
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 4bf4ea6cbb5e..21e24da4847f 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -902,7 +902,10 @@ static int rfcomm_sock_shutdown(struct socket *sock, int how)
lock_sock(sk);
if (!sk->sk_shutdown) {
sk->sk_shutdown = SHUTDOWN_MASK;
+
+ release_sock(sk);
__rfcomm_sock_close(sk);
+ lock_sock(sk);
if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
!(current->flags & PF_EXITING))
diff --git a/net/can/bcm.c b/net/can/bcm.c
index e5ffd2bd62ab..aab3a18f4a90 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -274,6 +274,7 @@ static void bcm_can_tx(struct bcm_op *op)
struct sk_buff *skb;
struct net_device *dev;
struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe;
+ int err;
/* no target device? => exit */
if (!op->ifindex)
@@ -298,11 +299,11 @@ static void bcm_can_tx(struct bcm_op *op)
/* send with loopback */
skb->dev = dev;
can_skb_set_owner(skb, op->sk);
- can_send(skb, 1);
+ err = can_send(skb, 1);
+ if (!err)
+ op->frames_abs++;
- /* update statistics */
op->currframe++;
- op->frames_abs++;
/* reached last frame? */
if (op->currframe >= op->nframes)
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 054073c7cbb9..736d8b035a67 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -435,8 +435,10 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
if (copied + copy > len)
copy = len - copied;
copy = copy_page_to_iter(page, sge->offset, copy, iter);
- if (!copy)
- return copied ? copied : -EFAULT;
+ if (!copy) {
+ copied = copied ? copied : -EFAULT;
+ goto out;
+ }
copied += copy;
if (likely(!peek)) {
@@ -456,7 +458,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
* didn't copy the entire length lets just break.
*/
if (copy != sge->length)
- return copied;
+ goto out;
sk_msg_iter_var_next(i);
}
@@ -478,7 +480,9 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
}
msg_rx = sk_psock_peek_msg(psock);
}
-
+out:
+ if (psock->work_state.skb && copied > 0)
+ schedule_work(&psock->work);
return copied;
}
EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
diff --git a/net/core/stream.c b/net/core/stream.c
index a166a32b411f..a61130504827 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -159,7 +159,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
*timeo_p = current_timeo;
}
out:
- remove_wait_queue(sk_sleep(sk), &wait);
+ if (!sock_flag(sk, SOCK_DEAD))
+ remove_wait_queue(sk_sleep(sk), &wait);
return err;
do_error:
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index fd5862f9e26a..d0aaa0346cb1 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -272,6 +272,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
err = -EMSGSIZE;
goto out_dev;
}
+ if (!size) {
+ err = 0;
+ goto out_dev;
+ }
hlen = LL_RESERVED_SPACE(dev);
tlen = dev->needed_tailroom;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 26c4dd4ec459..ce6a3873f89e 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -771,8 +771,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
if (likely(remaining > 1))
remaining &= ~1U;
- net_get_random_once(table_perturb,
- INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb));
+ get_random_slow_once(table_perturb,
+ INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb));
index = port_offset & (INET_TABLE_PERTURB_SIZE - 1);
offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32);
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 03df986217b7..9e6f0f1275e2 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -83,6 +83,9 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
else
oif = NULL;
+ if (priv->flags & NFTA_FIB_F_IIF)
+ fl4.flowi4_oif = l3mdev_master_ifindex_rcu(oif);
+
if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
nft_fib_store_result(dest, priv, nft_in(pkt));
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4f6b897ccf23..5b4e170b6a34 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3025,6 +3025,8 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
tp->snd_cwnd_cnt = 0;
+ tp->is_cwnd_limited = 0;
+ tp->max_packets_out = 0;
tp->window_clamp = 0;
tp->delivered = 0;
tp->delivered_ce = 0;
@@ -4329,12 +4331,16 @@ static void __tcp_alloc_md5sig_pool(void)
* to memory. See smp_rmb() in tcp_get_md5sig_pool()
*/
smp_wmb();
- tcp_md5sig_pool_populated = true;
+ /* Paired with READ_ONCE() from tcp_alloc_md5sig_pool()
+ * and tcp_get_md5sig_pool().
+ */
+ WRITE_ONCE(tcp_md5sig_pool_populated, true);
}
bool tcp_alloc_md5sig_pool(void)
{
- if (unlikely(!tcp_md5sig_pool_populated)) {
+ /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */
+ if (unlikely(!READ_ONCE(tcp_md5sig_pool_populated))) {
mutex_lock(&tcp_md5sig_mutex);
if (!tcp_md5sig_pool_populated) {
@@ -4345,7 +4351,8 @@ bool tcp_alloc_md5sig_pool(void)
mutex_unlock(&tcp_md5sig_mutex);
}
- return tcp_md5sig_pool_populated;
+ /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */
+ return READ_ONCE(tcp_md5sig_pool_populated);
}
EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
@@ -4361,7 +4368,8 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
{
local_bh_disable();
- if (tcp_md5sig_pool_populated) {
+ /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */
+ if (READ_ONCE(tcp_md5sig_pool_populated)) {
/* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */
smp_rmb();
return this_cpu_ptr(&tcp_md5sig_pool);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ed2e1836c0c0..33ba1268a111 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1878,15 +1878,20 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
struct tcp_sock *tp = tcp_sk(sk);
- /* Track the maximum number of outstanding packets in each
- * window, and remember whether we were cwnd-limited then.
+ /* Track the strongest available signal of the degree to which the cwnd
+ * is fully utilized. If cwnd-limited then remember that fact for the
+ * current window. If not cwnd-limited then track the maximum number of
+ * outstanding packets in the current window. (If cwnd-limited then we
+ * chose to not update tp->max_packets_out to avoid an extra else
+ * clause with no functional impact.)
*/
- if (!before(tp->snd_una, tp->max_packets_seq) ||
- tp->packets_out > tp->max_packets_out ||
- is_cwnd_limited) {
- tp->max_packets_out = tp->packets_out;
- tp->max_packets_seq = tp->snd_nxt;
+ if (!before(tp->snd_una, tp->cwnd_usage_seq) ||
+ is_cwnd_limited ||
+ (!tp->is_cwnd_limited &&
+ tp->packets_out > tp->max_packets_out)) {
tp->is_cwnd_limited = is_cwnd_limited;
+ tp->max_packets_out = tp->packets_out;
+ tp->cwnd_usage_seq = tp->snd_nxt;
}
if (tcp_is_cwnd_limited(sk)) {
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index 92f3235fa287..602743f6dcee 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -37,6 +37,9 @@ static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv,
if (ipv6_addr_type(&fl6->daddr) & IPV6_ADDR_LINKLOCAL) {
lookup_flags |= RT6_LOOKUP_F_IFACE;
fl6->flowi6_oif = get_ifindex(dev ? dev : pkt->skb->dev);
+ } else if ((priv->flags & NFTA_FIB_F_IIF) &&
+ (netif_is_l3_master(dev) || netif_is_l3_slave(dev))) {
+ fl6->flowi6_oif = dev->ifindex;
}
if (ipv6_addr_type(&fl6->saddr) & IPV6_ADDR_UNICAST)
@@ -193,7 +196,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL))
goto put_rt_err;
- if (oif && oif != rt->rt6i_idev->dev)
+ if (oif && oif != rt->rt6i_idev->dev &&
+ l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex)
goto put_rt_err;
nft_fib_store_result(dest, priv, rt->rt6i_idev->dev);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 3f625e836a03..4fa216a108ae 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3384,9 +3384,6 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata,
case NL80211_IFTYPE_MESH_POINT: {
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
- if (params->chandef.width != sdata->vif.bss_conf.chandef.width)
- return -EINVAL;
-
/* changes into another band are not supported */
if (sdata->vif.bss_conf.chandef.chan->band !=
params->chandef.chan->band)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 31399c53dfb1..9da5ee6c50cd 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -67,6 +67,7 @@ struct conntrack_gc_work {
struct delayed_work dwork;
u32 next_bucket;
u32 avg_timeout;
+ u32 count;
u32 start_time;
bool exiting;
bool early_drop;
@@ -85,10 +86,12 @@ static DEFINE_MUTEX(nf_conntrack_mutex);
/* clamp timeouts to this value (TCP unacked) */
#define GC_SCAN_INTERVAL_CLAMP (300ul * HZ)
-/* large initial bias so that we don't scan often just because we have
- * three entries with a 1s timeout.
+/* Initial bias pretending we have 100 entries at the upper bound so we don't
+ * wakeup often just because we have three entries with a 1s timeout while still
+ * allowing non-idle machines to wakeup more often when needed.
*/
-#define GC_SCAN_INTERVAL_INIT INT_MAX
+#define GC_SCAN_INITIAL_COUNT 100
+#define GC_SCAN_INTERVAL_INIT GC_SCAN_INTERVAL_MAX
#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10)
#define GC_SCAN_EXPIRED_MAX (64000u / HZ)
@@ -1439,6 +1442,7 @@ static void gc_worker(struct work_struct *work)
unsigned int expired_count = 0;
unsigned long next_run;
s32 delta_time;
+ long count;
gc_work = container_of(work, struct conntrack_gc_work, dwork.work);
@@ -1448,10 +1452,12 @@ static void gc_worker(struct work_struct *work)
if (i == 0) {
gc_work->avg_timeout = GC_SCAN_INTERVAL_INIT;
+ gc_work->count = GC_SCAN_INITIAL_COUNT;
gc_work->start_time = start_time;
}
next_run = gc_work->avg_timeout;
+ count = gc_work->count;
end_time = start_time + GC_SCAN_MAX_DURATION;
@@ -1471,8 +1477,8 @@ static void gc_worker(struct work_struct *work)
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) {
struct nf_conntrack_net *cnet;
- unsigned long expires;
struct net *net;
+ long expires;
tmp = nf_ct_tuplehash_to_ctrack(h);
@@ -1486,6 +1492,7 @@ static void gc_worker(struct work_struct *work)
gc_work->next_bucket = i;
gc_work->avg_timeout = next_run;
+ gc_work->count = count;
delta_time = nfct_time_stamp - gc_work->start_time;
@@ -1501,8 +1508,8 @@ static void gc_worker(struct work_struct *work)
}
expires = clamp(nf_ct_expires(tmp), GC_SCAN_INTERVAL_MIN, GC_SCAN_INTERVAL_CLAMP);
+ expires = (expires - (long)next_run) / ++count;
next_run += expires;
- next_run /= 2u;
if (nf_conntrack_max95 == 0 || gc_worker_skip_ct(tmp))
continue;
@@ -1540,6 +1547,7 @@ static void gc_worker(struct work_struct *work)
delta_time = nfct_time_stamp - end_time;
if (delta_time > 0 && i < hashsz) {
gc_work->avg_timeout = next_run;
+ gc_work->count = count;
gc_work->next_bucket = i;
next_run = 0;
goto early_exit;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 5e2c83cb7b12..46ef1525b2e5 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -251,10 +251,17 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
upcall.mru = OVS_CB(skb)->mru;
error = ovs_dp_upcall(dp, skb, key, &upcall, 0);
- if (unlikely(error))
- kfree_skb(skb);
- else
+ switch (error) {
+ case 0:
+ case -EAGAIN:
+ case -ERESTARTSYS:
+ case -EINTR:
consume_skb(skb);
+ break;
+ default:
+ kfree_skb(skb);
+ break;
+ }
stats_counter = &stats->n_missed;
goto out;
}
@@ -550,8 +557,9 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
out:
if (err)
skb_tx_error(skb);
- kfree_skb(user_skb);
- kfree_skb(nskb);
+ consume_skb(user_skb);
+ consume_skb(nskb);
+
return err;
}
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 5327d130c4b5..b560d06e6d96 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -166,10 +166,10 @@ void rds_tcp_reset_callbacks(struct socket *sock,
*/
atomic_set(&cp->cp_state, RDS_CONN_RESETTING);
wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags));
- lock_sock(osock->sk);
/* reset receive side state for rds_tcp_data_recv() for osock */
cancel_delayed_work_sync(&cp->cp_send_w);
cancel_delayed_work_sync(&cp->cp_recv_w);
+ lock_sock(osock->sk);
if (tc->t_tinc) {
rds_inc_put(&tc->t_tinc->ti_inc);
tc->t_tinc = NULL;
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index db6b7373d16c..34964145514e 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -863,12 +863,17 @@ int sctp_auth_set_key(struct sctp_endpoint *ep,
}
list_del_init(&shkey->key_list);
- sctp_auth_shkey_release(shkey);
list_add(&cur_key->key_list, sh_keys);
- if (asoc && asoc->active_key_id == auth_key->sca_keynumber)
- sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
+ if (asoc && asoc->active_key_id == auth_key->sca_keynumber &&
+ sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL)) {
+ list_del_init(&cur_key->key_list);
+ sctp_auth_shkey_release(cur_key);
+ list_add(&shkey->key_list, sh_keys);
+ return -ENOMEM;
+ }
+ sctp_auth_shkey_release(shkey);
return 0;
}
@@ -902,8 +907,13 @@ int sctp_auth_set_active_key(struct sctp_endpoint *ep,
return -EINVAL;
if (asoc) {
+ __u16 active_key_id = asoc->active_key_id;
+
asoc->active_key_id = key_id;
- sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
+ if (sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL)) {
+ asoc->active_key_id = active_key_id;
+ return -ENOMEM;
+ }
} else
ep->active_key_id = key_id;
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index d45d5366115a..dc2763540393 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -204,6 +204,7 @@ void wait_for_unix_gc(void)
/* The external entry point: unix_gc() */
void unix_gc(void)
{
+ struct sk_buff *next_skb, *skb;
struct unix_sock *u;
struct unix_sock *next;
struct sk_buff_head hitlist;
@@ -297,11 +298,30 @@ void unix_gc(void)
spin_unlock(&unix_gc_lock);
+ /* We need io_uring to clean its registered files, ignore all io_uring
+ * originated skbs. It's fine as io_uring doesn't keep references to
+ * other io_uring instances and so killing all other files in the cycle
+ * will put all io_uring references forcing it to go through normal
+ * release.path eventually putting registered files.
+ */
+ skb_queue_walk_safe(&hitlist, skb, next_skb) {
+ if (skb->scm_io_uring) {
+ __skb_unlink(skb, &hitlist);
+ skb_queue_tail(&skb->sk->sk_receive_queue, skb);
+ }
+ }
+
/* Here we are. Hitlist is filled. Die. */
__skb_queue_purge(&hitlist);
spin_lock(&unix_gc_lock);
+ /* There could be io_uring registered files, just push them back to
+ * the inflight list
+ */
+ list_for_each_entry_safe(u, next, &gc_candidates, link)
+ list_move_tail(&u->link, &gc_inflight_list);
+
/* All candidates should have been detached by now. */
BUG_ON(!list_empty(&gc_candidates));
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index ec2c2afbf0d0..3a12aee33e92 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1342,7 +1342,7 @@ EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt);
void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt)
{
- kfree(pkt->buf);
+ kvfree(pkt->buf);
kfree(pkt);
}
EXPORT_SYMBOL_GPL(virtio_transport_free_pkt);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 553cd9415c89..716fd22bc3ce 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -370,16 +370,15 @@ static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, u32 max_entr
return nb_pkts;
}
-u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries)
+u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 nb_pkts)
{
struct xdp_sock *xs;
- u32 nb_pkts;
rcu_read_lock();
if (!list_is_singular(&pool->xsk_tx_list)) {
/* Fallback to the non-batched version */
rcu_read_unlock();
- return xsk_tx_peek_release_fallback(pool, max_entries);
+ return xsk_tx_peek_release_fallback(pool, nb_pkts);
}
xs = list_first_or_null_rcu(&pool->xsk_tx_list, struct xdp_sock, tx_list);
@@ -388,12 +387,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries)
goto out;
}
- max_entries = xskq_cons_nb_entries(xs->tx, max_entries);
- nb_pkts = xskq_cons_read_desc_batch(xs->tx, pool, max_entries);
- if (!nb_pkts) {
- xs->tx->queue_empty_descs++;
- goto out;
- }
+ nb_pkts = xskq_cons_nb_entries(xs->tx, nb_pkts);
/* This is the backpressure mechanism for the Tx path. Try to
* reserve space in the completion queue for all packets, but
@@ -401,12 +395,18 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries)
* packets. This avoids having to implement any buffering in
* the Tx path.
*/
- nb_pkts = xskq_prod_reserve_addr_batch(pool->cq, pool->tx_descs, nb_pkts);
+ nb_pkts = xskq_prod_nb_free(pool->cq, nb_pkts);
if (!nb_pkts)
goto out;
- xskq_cons_release_n(xs->tx, max_entries);
+ nb_pkts = xskq_cons_read_desc_batch(xs->tx, pool, nb_pkts);
+ if (!nb_pkts) {
+ xs->tx->queue_empty_descs++;
+ goto out;
+ }
+
__xskq_cons_release(xs->tx);
+ xskq_prod_write_addr_batch(pool->cq, pool->tx_descs, nb_pkts);
xs->sk.sk_write_space(&xs->sk);
out:
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 4d092e7a33d1..029cf7a1c9d7 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -205,6 +205,11 @@ static inline bool xskq_cons_read_desc(struct xsk_queue *q,
return false;
}
+static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt)
+{
+ q->cached_cons += cnt;
+}
+
static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool,
u32 max)
{
@@ -226,6 +231,8 @@ static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff
cached_cons++;
}
+ /* Release valid plus any invalid entries */
+ xskq_cons_release_n(q, cached_cons - q->cached_cons);
return nb_entries;
}
@@ -291,11 +298,6 @@ static inline void xskq_cons_release(struct xsk_queue *q)
q->cached_cons++;
}
-static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt)
-{
- q->cached_cons += cnt;
-}
-
static inline bool xskq_cons_is_full(struct xsk_queue *q)
{
/* No barriers needed since data is not accessed */
@@ -357,21 +359,17 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr)
return 0;
}
-static inline u32 xskq_prod_reserve_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
- u32 max)
+static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
+ u32 nb_entries)
{
struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
- u32 nb_entries, i, cached_prod;
-
- nb_entries = xskq_prod_nb_free(q, max);
+ u32 i, cached_prod;
/* A, matches D */
cached_prod = q->cached_prod;
for (i = 0; i < nb_entries; i++)
ring->desc[cached_prod++ & q->ring_mask] = descs[i].addr;
q->cached_prod = cached_prod;
-
- return nb_entries;
}
static inline int xskq_prod_reserve_desc(struct xsk_queue *q,
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 5f34bc378fdc..3d8668d62e63 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -24,7 +24,8 @@
#include "xfrm_inout.h"
struct xfrm_trans_tasklet {
- struct tasklet_struct tasklet;
+ struct work_struct work;
+ spinlock_t queue_lock;
struct sk_buff_head queue;
};
@@ -760,18 +761,22 @@ int xfrm_input_resume(struct sk_buff *skb, int nexthdr)
}
EXPORT_SYMBOL(xfrm_input_resume);
-static void xfrm_trans_reinject(struct tasklet_struct *t)
+static void xfrm_trans_reinject(struct work_struct *work)
{
- struct xfrm_trans_tasklet *trans = from_tasklet(trans, t, tasklet);
+ struct xfrm_trans_tasklet *trans = container_of(work, struct xfrm_trans_tasklet, work);
struct sk_buff_head queue;
struct sk_buff *skb;
__skb_queue_head_init(&queue);
+ spin_lock_bh(&trans->queue_lock);
skb_queue_splice_init(&trans->queue, &queue);
+ spin_unlock_bh(&trans->queue_lock);
+ local_bh_disable();
while ((skb = __skb_dequeue(&queue)))
XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net,
NULL, skb);
+ local_bh_enable();
}
int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
@@ -789,8 +794,10 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
XFRM_TRANS_SKB_CB(skb)->finish = finish;
XFRM_TRANS_SKB_CB(skb)->net = net;
+ spin_lock_bh(&trans->queue_lock);
__skb_queue_tail(&trans->queue, skb);
- tasklet_schedule(&trans->tasklet);
+ spin_unlock_bh(&trans->queue_lock);
+ schedule_work(&trans->work);
return 0;
}
EXPORT_SYMBOL(xfrm_trans_queue_net);
@@ -817,7 +824,8 @@ void __init xfrm_input_init(void)
struct xfrm_trans_tasklet *trans;
trans = &per_cpu(xfrm_trans_tasklet, i);
+ spin_lock_init(&trans->queue_lock);
__skb_queue_head_init(&trans->queue);
- tasklet_setup(&trans->tasklet, xfrm_trans_reinject);
+ INIT_WORK(&trans->work, xfrm_trans_reinject);
}
}
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index cb40ff0ff28d..92ad336a83ab 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -203,6 +203,7 @@ static void ipcomp_free_scratches(void)
vfree(*per_cpu_ptr(scratches, i));
free_percpu(scratches);
+ ipcomp_scratches = NULL;
}
static void * __percpu *ipcomp_alloc_scratches(void)