summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-10-19 12:08:18 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2023-10-19 12:08:18 -0700
commitce55c22ec8b223a90ff3e084d842f73cfba35588 (patch)
tree919fc51c26a8b5f57b3c89f6a62d0f3bb1bdfd2c /net
parent74e9347ebc5be452935fe4f3eddb150aa5a6f4fe (diff)
parent524515020f2552759a7ef1c9d03e7dac9b1ff3c2 (diff)
Merge tag 'net-6.6-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski: "Including fixes from bluetooth, netfilter, WiFi. Feels like an up-tick in regression fixes, mostly for older releases. The hfsc fix, tcp_disconnect() and Intel WWAN fixes stand out as fairly clear-cut user reported regressions. The mlx5 DMA bug was causing strife for 390x folks. The fixes themselves are not particularly scary, tho. No open investigations / outstanding reports at the time of writing. Current release - regressions: - eth: mlx5: perform DMA operations in the right locations, make devices usable on s390x, again - sched: sch_hfsc: upgrade 'rt' to 'sc' when it becomes a inner curve, previous fix of rejecting invalid config broke some scripts - rfkill: reduce data->mtx scope in rfkill_fop_open, avoid deadlock - revert "ethtool: Fix mod state of verbose no_mask bitset", needs more work Current release - new code bugs: - tcp: fix listen() warning with v4-mapped-v6 address Previous releases - regressions: - tcp: allow tcp_disconnect() again when threads are waiting, it was denied to plug a constant source of bugs but turns out .NET depends on it - eth: mlx5: fix double-free if buffer refill fails under OOM - revert "net: wwan: iosm: enable runtime pm support for 7560", it's causing regressions and the WWAN team at Intel disappeared - tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb, fix single-stream perf regression on some devices Previous releases - always broken: - Bluetooth: - fix issues in legacy BR/EDR PIN code pairing - correctly bounds check and pad HCI_MON_NEW_INDEX name - netfilter: - more fixes / follow ups for the large "commit protocol" rework, which went in as a fix to 6.5 - fix null-derefs on netlink attrs which user may not pass in - tcp: fix excessive TLP and RACK timeouts from HZ rounding (bless Debian for keeping HZ=250 alive) - net: more strict VIRTIO_NET_HDR_GSO_UDP_L4 validation, prevent letting frankenstein UDP super-frames from getting into the stack - net: fix interface altnames when ifc moves to a new namespace - eth: qed: fix the size of the RX buffers - mptcp: avoid sending RST when closing the initial subflow" * tag 'net-6.6-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (94 commits) Revert "ethtool: Fix mod state of verbose no_mask bitset" selftests: mptcp: join: no RST when rm subflow/addr mptcp: avoid sending RST when closing the initial subflow mptcp: more conservative check for zero probes tcp: check mptcp-level constraints for backlog coalescing selftests: mptcp: join: correctly check for no RST net: ti: icssg-prueth: Fix r30 CMDs bitmasks selftests: net: add very basic test for netdev names and namespaces net: move altnames together with the netdevice net: avoid UAF on deleted altname net: check for altname conflicts when changing netdev's netns net: fix ifname in netlink ntf during netns move net: ethernet: ti: Fix mixed module-builtin object net: phy: bcm7xxx: Add missing 16nm EPHY statistics ipv4: fib: annotate races around nh->nh_saddr_genid and nh->nh_saddr tcp_bpf: properly release resources on error paths net/sched: sch_hfsc: upgrade 'rt' to 'sc' when it becomes a inner curve net: mdio-mux: fix C45 access returning -EIO after API change tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb octeon_ep: update BQL sent bytes before ringing doorbell ...
Diffstat (limited to 'net')
-rw-r--r--net/bluetooth/hci_conn.c9
-rw-r--r--net/bluetooth/hci_event.c48
-rw-r--r--net/bluetooth/hci_sock.c3
-rw-r--r--net/bluetooth/hci_sync.c26
-rw-r--r--net/core/dev.c65
-rw-r--r--net/core/dev.h3
-rw-r--r--net/core/pktgen.c14
-rw-r--r--net/core/rtnetlink.c4
-rw-r--r--net/core/stream.c12
-rw-r--r--net/ethtool/bitset.c32
-rw-r--r--net/ipv4/af_inet.c10
-rw-r--r--net/ipv4/esp4.c4
-rw-r--r--net/ipv4/fib_semantics.c14
-rw-r--r--net/ipv4/inet_connection_sock.c1
-rw-r--r--net/ipv4/inet_hashtables.c24
-rw-r--r--net/ipv4/tcp.c16
-rw-r--r--net/ipv4/tcp_bpf.c12
-rw-r--r--net/ipv4/tcp_ipv4.c1
-rw-r--r--net/ipv4/tcp_output.c25
-rw-r--r--net/ipv4/tcp_recovery.c2
-rw-r--r--net/ipv6/esp6.c4
-rw-r--r--net/ipv6/xfrm6_policy.c4
-rw-r--r--net/mac80211/key.c3
-rw-r--r--net/mptcp/protocol.c43
-rw-r--r--net/netfilter/nf_tables_api.c70
-rw-r--r--net/netfilter/nfnetlink_log.c2
-rw-r--r--net/netfilter/nft_inner.c1
-rw-r--r--net/netfilter/nft_payload.c2
-rw-r--r--net/netfilter/nft_set_pipapo.h2
-rw-r--r--net/netfilter/nft_set_rbtree.c2
-rw-r--r--net/nfc/nci/spi.c2
-rw-r--r--net/rfkill/core.c5
-rw-r--r--net/rfkill/rfkill-gpio.c4
-rw-r--r--net/sched/sch_hfsc.c18
-rw-r--r--net/smc/af_smc.c5
-rw-r--r--net/smc/smc_ib.c7
-rw-r--r--net/smc/smc_ib.h2
-rw-r--r--net/tls/tls_main.c10
-rw-r--r--net/tls/tls_sw.c19
-rw-r--r--net/wireless/core.c2
-rw-r--r--net/xfrm/xfrm_interface_core.c22
-rw-r--r--net/xfrm/xfrm_policy.c27
42 files changed, 350 insertions, 231 deletions
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 7a6f20338db8..73470cc3518a 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1627,6 +1627,15 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst,
return ERR_PTR(-EOPNOTSUPP);
}
+ /* Reject outgoing connection to device with same BD ADDR against
+ * CVE-2020-26555
+ */
+ if (!bacmp(&hdev->bdaddr, dst)) {
+ bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n",
+ dst);
+ return ERR_PTR(-ECONNREFUSED);
+ }
+
acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst);
if (!acl) {
acl = hci_conn_add(hdev, ACL_LINK, dst, HCI_ROLE_MASTER);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 31d02b54eea1..1e1c9147356c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -26,6 +26,8 @@
/* Bluetooth HCI event handling. */
#include <asm/unaligned.h>
+#include <linux/crypto.h>
+#include <crypto/algapi.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
@@ -3268,6 +3270,16 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data,
bt_dev_dbg(hdev, "bdaddr %pMR type 0x%x", &ev->bdaddr, ev->link_type);
+ /* Reject incoming connection from device with same BD ADDR against
+ * CVE-2020-26555
+ */
+ if (hdev && !bacmp(&hdev->bdaddr, &ev->bdaddr)) {
+ bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n",
+ &ev->bdaddr);
+ hci_reject_conn(hdev, &ev->bdaddr);
+ return;
+ }
+
mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type,
&flags);
@@ -4742,6 +4754,15 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, void *data,
if (!conn)
goto unlock;
+ /* Ignore NULL link key against CVE-2020-26555 */
+ if (!crypto_memneq(ev->link_key, ZERO_KEY, HCI_LINK_KEY_SIZE)) {
+ bt_dev_dbg(hdev, "Ignore NULL link key (ZERO KEY) for %pMR",
+ &ev->bdaddr);
+ hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE);
+ hci_conn_drop(conn);
+ goto unlock;
+ }
+
hci_conn_hold(conn);
conn->disc_timeout = HCI_DISCONN_TIMEOUT;
hci_conn_drop(conn);
@@ -5274,8 +5295,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn)
* available, then do not declare that OOB data is
* present.
*/
- if (!memcmp(data->rand256, ZERO_KEY, 16) ||
- !memcmp(data->hash256, ZERO_KEY, 16))
+ if (!crypto_memneq(data->rand256, ZERO_KEY, 16) ||
+ !crypto_memneq(data->hash256, ZERO_KEY, 16))
return 0x00;
return 0x02;
@@ -5285,8 +5306,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn)
* not supported by the hardware, then check that if
* P-192 data values are present.
*/
- if (!memcmp(data->rand192, ZERO_KEY, 16) ||
- !memcmp(data->hash192, ZERO_KEY, 16))
+ if (!crypto_memneq(data->rand192, ZERO_KEY, 16) ||
+ !crypto_memneq(data->hash192, ZERO_KEY, 16))
return 0x00;
return 0x01;
@@ -5303,7 +5324,7 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data,
hci_dev_lock(hdev);
conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
- if (!conn)
+ if (!conn || !hci_conn_ssp_enabled(conn))
goto unlock;
hci_conn_hold(conn);
@@ -5550,7 +5571,7 @@ static void hci_simple_pair_complete_evt(struct hci_dev *hdev, void *data,
hci_dev_lock(hdev);
conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
- if (!conn)
+ if (!conn || !hci_conn_ssp_enabled(conn))
goto unlock;
/* Reset the authentication requirement to unknown */
@@ -7021,6 +7042,14 @@ unlock:
hci_dev_unlock(hdev);
}
+static int hci_iso_term_big_sync(struct hci_dev *hdev, void *data)
+{
+ u8 handle = PTR_UINT(data);
+
+ return hci_le_terminate_big_sync(hdev, handle,
+ HCI_ERROR_LOCAL_HOST_TERM);
+}
+
static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data,
struct sk_buff *skb)
{
@@ -7065,16 +7094,17 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data,
rcu_read_lock();
}
+ rcu_read_unlock();
+
if (!ev->status && !i)
/* If no BISes have been connected for the BIG,
* terminate. This is in case all bound connections
* have been closed before the BIG creation
* has completed.
*/
- hci_le_terminate_big_sync(hdev, ev->handle,
- HCI_ERROR_LOCAL_HOST_TERM);
+ hci_cmd_sync_queue(hdev, hci_iso_term_big_sync,
+ UINT_PTR(ev->handle), NULL);
- rcu_read_unlock();
hci_dev_unlock(hdev);
}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 5e4f718073b7..3e7cd330d731 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -488,7 +488,8 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event)
ni->type = hdev->dev_type;
ni->bus = hdev->bus;
bacpy(&ni->bdaddr, &hdev->bdaddr);
- memcpy(ni->name, hdev->name, 8);
+ memcpy_and_pad(ni->name, sizeof(ni->name), hdev->name,
+ strnlen(hdev->name, sizeof(ni->name)), '\0');
opcode = cpu_to_le16(HCI_MON_NEW_INDEX);
break;
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index d06e07a0ea5a..a15ab0b874a9 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5369,6 +5369,7 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
{
int err = 0;
u16 handle = conn->handle;
+ bool disconnect = false;
struct hci_conn *c;
switch (conn->state) {
@@ -5399,24 +5400,15 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
hci_dev_unlock(hdev);
return 0;
case BT_BOUND:
- hci_dev_lock(hdev);
- hci_conn_failed(conn, reason);
- hci_dev_unlock(hdev);
- return 0;
+ break;
default:
- hci_dev_lock(hdev);
- conn->state = BT_CLOSED;
- hci_disconn_cfm(conn, reason);
- hci_conn_del(conn);
- hci_dev_unlock(hdev);
- return 0;
+ disconnect = true;
+ break;
}
hci_dev_lock(hdev);
- /* Check if the connection hasn't been cleanup while waiting
- * commands to complete.
- */
+ /* Check if the connection has been cleaned up concurrently */
c = hci_conn_hash_lookup_handle(hdev, handle);
if (!c || c != conn) {
err = 0;
@@ -5428,7 +5420,13 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
* or in case of LE it was still scanning so it can be cleanup
* safely.
*/
- hci_conn_failed(conn, reason);
+ if (disconnect) {
+ conn->state = BT_CLOSED;
+ hci_disconn_cfm(conn, reason);
+ hci_conn_del(conn);
+ } else {
+ hci_conn_failed(conn, reason);
+ }
unlock:
hci_dev_unlock(hdev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 5aaf5753d4e4..9f3f8930c691 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -345,7 +345,6 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name)
static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node)
{
list_del(&name_node->list);
- netdev_name_node_del(name_node);
kfree(name_node->name);
netdev_name_node_free(name_node);
}
@@ -364,6 +363,8 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name)
if (name_node == dev->name_node || name_node->dev != dev)
return -EINVAL;
+ netdev_name_node_del(name_node);
+ synchronize_rcu();
__netdev_name_node_alt_destroy(name_node);
return 0;
@@ -380,6 +381,7 @@ static void netdev_name_node_alt_flush(struct net_device *dev)
/* Device list insertion */
static void list_netdevice(struct net_device *dev)
{
+ struct netdev_name_node *name_node;
struct net *net = dev_net(dev);
ASSERT_RTNL();
@@ -390,6 +392,10 @@ static void list_netdevice(struct net_device *dev)
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
write_unlock(&dev_base_lock);
+
+ netdev_for_each_altname(dev, name_node)
+ netdev_name_node_add(net, name_node);
+
/* We reserved the ifindex, this can't fail */
WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL));
@@ -401,12 +407,16 @@ static void list_netdevice(struct net_device *dev)
*/
static void unlist_netdevice(struct net_device *dev, bool lock)
{
+ struct netdev_name_node *name_node;
struct net *net = dev_net(dev);
ASSERT_RTNL();
xa_erase(&net->dev_by_index, dev->ifindex);
+ netdev_for_each_altname(dev, name_node)
+ netdev_name_node_del(name_node);
+
/* Unlink dev from the device chain */
if (lock)
write_lock(&dev_base_lock);
@@ -1086,7 +1096,8 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
for_each_netdev(net, d) {
struct netdev_name_node *name_node;
- list_for_each_entry(name_node, &d->name_node->list, list) {
+
+ netdev_for_each_altname(d, name_node) {
if (!sscanf(name_node->name, name, &i))
continue;
if (i < 0 || i >= max_netdevices)
@@ -1123,6 +1134,26 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
return -ENFILE;
}
+static int dev_prep_valid_name(struct net *net, struct net_device *dev,
+ const char *want_name, char *out_name)
+{
+ int ret;
+
+ if (!dev_valid_name(want_name))
+ return -EINVAL;
+
+ if (strchr(want_name, '%')) {
+ ret = __dev_alloc_name(net, want_name, out_name);
+ return ret < 0 ? ret : 0;
+ } else if (netdev_name_in_use(net, want_name)) {
+ return -EEXIST;
+ } else if (out_name != want_name) {
+ strscpy(out_name, want_name, IFNAMSIZ);
+ }
+
+ return 0;
+}
+
static int dev_alloc_name_ns(struct net *net,
struct net_device *dev,
const char *name)
@@ -1160,19 +1191,13 @@ EXPORT_SYMBOL(dev_alloc_name);
static int dev_get_valid_name(struct net *net, struct net_device *dev,
const char *name)
{
- BUG_ON(!net);
-
- if (!dev_valid_name(name))
- return -EINVAL;
-
- if (strchr(name, '%'))
- return dev_alloc_name_ns(net, dev, name);
- else if (netdev_name_in_use(net, name))
- return -EEXIST;
- else if (dev->name != name)
- strscpy(dev->name, name, IFNAMSIZ);
+ char buf[IFNAMSIZ];
+ int ret;
- return 0;
+ ret = dev_prep_valid_name(net, dev, name, buf);
+ if (ret >= 0)
+ strscpy(dev->name, buf, IFNAMSIZ);
+ return ret;
}
/**
@@ -11037,7 +11062,9 @@ EXPORT_SYMBOL(unregister_netdev);
int __dev_change_net_namespace(struct net_device *dev, struct net *net,
const char *pat, int new_ifindex)
{
+ struct netdev_name_node *name_node;
struct net *net_old = dev_net(dev);
+ char new_name[IFNAMSIZ] = {};
int err, new_nsid;
ASSERT_RTNL();
@@ -11064,10 +11091,15 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
/* We get here if we can't use the current device name */
if (!pat)
goto out;
- err = dev_get_valid_name(net, dev, pat);
+ err = dev_prep_valid_name(net, dev, pat, new_name);
if (err < 0)
goto out;
}
+ /* Check that none of the altnames conflicts. */
+ err = -EEXIST;
+ netdev_for_each_altname(dev, name_node)
+ if (netdev_name_in_use(net, name_node->name))
+ goto out;
/* Check that new_ifindex isn't used yet. */
if (new_ifindex) {
@@ -11135,6 +11167,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
kobject_uevent(&dev->dev.kobj, KOBJ_ADD);
netdev_adjacent_add_links(dev);
+ if (new_name[0]) /* Rename the netdev to prepared name */
+ strscpy(dev->name, new_name, IFNAMSIZ);
+
/* Fixup kobjects */
err = device_rename(&dev->dev, dev->name);
WARN_ON(err);
diff --git a/net/core/dev.h b/net/core/dev.h
index e075e198092c..fa2e9c5c4122 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -62,6 +62,9 @@ struct netdev_name_node {
int netdev_get_name(struct net *net, char *name, int ifindex);
int dev_change_name(struct net_device *dev, const char *newname);
+#define netdev_for_each_altname(dev, namenode) \
+ list_for_each_entry((namenode), &(dev)->name_node->list, list)
+
int netdev_name_node_alt_create(struct net_device *dev, const char *name);
int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index f56b8d697014..4d1696677c48 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -669,19 +669,19 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
seq_puts(seq, " Flags: ");
for (i = 0; i < NR_PKT_FLAGS; i++) {
- if (i == F_FLOW_SEQ)
+ if (i == FLOW_SEQ_SHIFT)
if (!pkt_dev->cflows)
continue;
- if (pkt_dev->flags & (1 << i))
+ if (pkt_dev->flags & (1 << i)) {
seq_printf(seq, "%s ", pkt_flag_names[i]);
- else if (i == F_FLOW_SEQ)
- seq_puts(seq, "FLOW_RND ");
-
#ifdef CONFIG_XFRM
- if (i == F_IPSEC && pkt_dev->spi)
- seq_printf(seq, "spi:%u", pkt_dev->spi);
+ if (i == IPSEC_SHIFT && pkt_dev->spi)
+ seq_printf(seq, "spi:%u ", pkt_dev->spi);
#endif
+ } else if (i == FLOW_SEQ_SHIFT) {
+ seq_puts(seq, "FLOW_RND ");
+ }
}
seq_puts(seq, "\n");
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4a2ec33bfb51..53c377d054f0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -5503,13 +5503,11 @@ static unsigned int
rtnl_offload_xstats_get_size_hw_s_info_one(const struct net_device *dev,
enum netdev_offload_xstats_type type)
{
- bool enabled = netdev_offload_xstats_enabled(dev, type);
-
return nla_total_size(0) +
/* IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST */
nla_total_size(sizeof(u8)) +
/* IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED */
- (enabled ? nla_total_size(sizeof(u8)) : 0) +
+ nla_total_size(sizeof(u8)) +
0;
}
diff --git a/net/core/stream.c b/net/core/stream.c
index f5c4e47df165..96fbcb9bbb30 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -117,7 +117,7 @@ EXPORT_SYMBOL(sk_stream_wait_close);
*/
int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
{
- int err = 0;
+ int ret, err = 0;
long vm_wait = 0;
long current_timeo = *timeo_p;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
@@ -142,11 +142,13 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk->sk_write_pending++;
- sk_wait_event(sk, &current_timeo, READ_ONCE(sk->sk_err) ||
- (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) ||
- (sk_stream_memory_free(sk) &&
- !vm_wait), &wait);
+ ret = sk_wait_event(sk, &current_timeo, READ_ONCE(sk->sk_err) ||
+ (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) ||
+ (sk_stream_memory_free(sk) && !vm_wait),
+ &wait);
sk->sk_write_pending--;
+ if (ret < 0)
+ goto do_error;
if (vm_wait) {
vm_wait -= current_timeo;
diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c
index 883ed9be81f9..0515d6604b3b 100644
--- a/net/ethtool/bitset.c
+++ b/net/ethtool/bitset.c
@@ -431,10 +431,8 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
ethnl_string_array_t names,
struct netlink_ext_ack *extack, bool *mod)
{
- u32 *orig_bitmap, *saved_bitmap = NULL;
struct nlattr *bit_attr;
bool no_mask;
- bool dummy;
int rem;
int ret;
@@ -450,22 +448,8 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
}
no_mask = tb[ETHTOOL_A_BITSET_NOMASK];
- if (no_mask) {
- unsigned int nwords = DIV_ROUND_UP(nbits, 32);
- unsigned int nbytes = nwords * sizeof(u32);
-
- /* The bitmap size is only the size of the map part without
- * its mask part.
- */
- saved_bitmap = kcalloc(nwords, sizeof(u32), GFP_KERNEL);
- if (!saved_bitmap)
- return -ENOMEM;
- memcpy(saved_bitmap, bitmap, nbytes);
- ethnl_bitmap32_clear(bitmap, 0, nbits, &dummy);
- orig_bitmap = saved_bitmap;
- } else {
- orig_bitmap = bitmap;
- }
+ if (no_mask)
+ ethnl_bitmap32_clear(bitmap, 0, nbits, mod);
nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) {
bool old_val, new_val;
@@ -474,14 +458,13 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
if (nla_type(bit_attr) != ETHTOOL_A_BITSET_BITS_BIT) {
NL_SET_ERR_MSG_ATTR(extack, bit_attr,
"only ETHTOOL_A_BITSET_BITS_BIT allowed in ETHTOOL_A_BITSET_BITS");
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
ret = ethnl_parse_bit(&idx, &new_val, nbits, bit_attr, no_mask,
names, extack);
if (ret < 0)
- goto out;
- old_val = orig_bitmap[idx / 32] & ((u32)1 << (idx % 32));
+ return ret;
+ old_val = bitmap[idx / 32] & ((u32)1 << (idx % 32));
if (new_val != old_val) {
if (new_val)
bitmap[idx / 32] |= ((u32)1 << (idx % 32));
@@ -491,10 +474,7 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
}
}
- ret = 0;
-out:
- kfree(saved_bitmap);
- return ret;
+ return 0;
}
static int ethnl_compact_sanity_checks(unsigned int nbits,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 3d2e30e20473..2713c9b06c4c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -597,7 +597,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
add_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending += writebias;
- sk->sk_wait_pending++;
/* Basic assumption: if someone sets sk->sk_err, he _must_
* change state of the socket from TCP_SYN_*.
@@ -613,7 +612,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
}
remove_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending -= writebias;
- sk->sk_wait_pending--;
return timeo;
}
@@ -642,6 +640,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
return -EINVAL;
if (uaddr->sa_family == AF_UNSPEC) {
+ sk->sk_disconnects++;
err = sk->sk_prot->disconnect(sk, flags);
sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
goto out;
@@ -696,6 +695,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
int writebias = (sk->sk_protocol == IPPROTO_TCP) &&
tcp_sk(sk)->fastopen_req &&
tcp_sk(sk)->fastopen_req->data ? 1 : 0;
+ int dis = sk->sk_disconnects;
/* Error code is set above */
if (!timeo || !inet_wait_for_connect(sk, timeo, writebias))
@@ -704,6 +704,11 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
err = sock_intr_errno(timeo);
if (signal_pending(current))
goto out;
+
+ if (dis != sk->sk_disconnects) {
+ err = -EPIPE;
+ goto out;
+ }
}
/* Connection was closed by RST, timeout, ICMP error
@@ -725,6 +730,7 @@ out:
sock_error:
err = sock_error(sk) ? : -ECONNABORTED;
sock->state = SS_UNCONNECTED;
+ sk->sk_disconnects++;
if (sk->sk_prot->disconnect(sk, flags))
sock->state = SS_DISCONNECTING;
goto out;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 2be2d4922557..d18f0f092fe7 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -732,7 +732,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb)
skb->csum = csum_block_sub(skb->csum, csumdiff,
skb->len - trimlen);
}
- pskb_trim(skb, skb->len - trimlen);
+ ret = pskb_trim(skb, skb->len - trimlen);
+ if (unlikely(ret))
+ return ret;
ret = nexthdr[1];
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 1ea82bc33ef1..5eb1b8d302bb 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1325,15 +1325,18 @@ __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc,
unsigned char scope)
{
struct fib_nh *nh;
+ __be32 saddr;
if (nhc->nhc_family != AF_INET)
return inet_select_addr(nhc->nhc_dev, 0, scope);
nh = container_of(nhc, struct fib_nh, nh_common);
- nh->nh_saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope);
- nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);
+ saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope);
- return nh->nh_saddr;
+ WRITE_ONCE(nh->nh_saddr, saddr);
+ WRITE_ONCE(nh->nh_saddr_genid, atomic_read(&net->ipv4.dev_addr_genid));
+
+ return saddr;
}
__be32 fib_result_prefsrc(struct net *net, struct fib_result *res)
@@ -1347,8 +1350,9 @@ __be32 fib_result_prefsrc(struct net *net, struct fib_result *res)
struct fib_nh *nh;
nh = container_of(nhc, struct fib_nh, nh_common);
- if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid))
- return nh->nh_saddr;
+ if (READ_ONCE(nh->nh_saddr_genid) ==
+ atomic_read(&net->ipv4.dev_addr_genid))
+ return READ_ONCE(nh->nh_saddr);
}
return fib_info_update_nhc_saddr(net, nhc, res->fi->fib_scope);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index aeebe8816689..394a498c2823 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1145,7 +1145,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
if (newsk) {
struct inet_connection_sock *newicsk = inet_csk(newsk);
- newsk->sk_wait_pending = 0;
inet_sk_set_state(newsk, TCP_SYN_RECV);
newicsk->icsk_bind_hash = NULL;
newicsk->icsk_bind2_hash = NULL;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index c32f5e28758b..598c1b114d2c 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -149,8 +149,14 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family != tb2->family)
- return false;
+ if (sk->sk_family != tb2->family) {
+ if (sk->sk_family == AF_INET)
+ return ipv6_addr_v4mapped(&tb2->v6_rcv_saddr) &&
+ tb2->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr;
+
+ return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) &&
+ sk->sk_v6_rcv_saddr.s6_addr32[3] == tb2->rcv_saddr;
+ }
if (sk->sk_family == AF_INET6)
return ipv6_addr_equal(&tb2->v6_rcv_saddr,
@@ -819,19 +825,7 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb,
tb->l3mdev != l3mdev)
return false;
-#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family != tb->family) {
- if (sk->sk_family == AF_INET)
- return ipv6_addr_v4mapped(&tb->v6_rcv_saddr) &&
- tb->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr;
-
- return false;
- }
-
- if (sk->sk_family == AF_INET6)
- return ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
-#endif
- return tb->rcv_saddr == sk->sk_rcv_saddr;
+ return inet_bind2_bucket_addr_match(tb, sk);
}
bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3f66cdeef7de..d3456cf840de 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -831,7 +831,9 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
*/
if (!skb_queue_empty(&sk->sk_receive_queue))
break;
- sk_wait_data(sk, &timeo, NULL);
+ ret = sk_wait_data(sk, &timeo, NULL);
+ if (ret < 0)
+ break;
if (signal_pending(current)) {
ret = sock_intr_errno(timeo);
break;
@@ -2442,7 +2444,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
__sk_flush_backlog(sk);
} else {
tcp_cleanup_rbuf(sk, copied);
- sk_wait_data(sk, &timeo, last);
+ err = sk_wait_data(sk, &timeo, last);
+ if (err < 0) {
+ err = copied ? : err;
+ goto out;
+ }
}
if ((flags & MSG_PEEK) &&
@@ -2966,12 +2972,6 @@ int tcp_disconnect(struct sock *sk, int flags)
int old_state = sk->sk_state;
u32 seq;
- /* Deny disconnect if other threads are blocked in sk_wait_event()
- * or inet_wait_for_connect().
- */
- if (sk->sk_wait_pending)
- return -EBUSY;
-
if (old_state != TCP_CLOSE)
tcp_set_state(sk, TCP_CLOSE);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 327268203001..53b0d62fd2c2 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -307,6 +307,10 @@ msg_bytes_ready:
}
data = tcp_msg_wait_data(sk, psock, timeo);
+ if (data < 0) {
+ copied = data;
+ goto unlock;
+ }
if (data && !sk_psock_queue_empty(psock))
goto msg_bytes_ready;
copied = -EAGAIN;
@@ -317,6 +321,8 @@ out:
tcp_rcv_space_adjust(sk);
if (copied > 0)
__tcp_cleanup_rbuf(sk, copied);
+
+unlock:
release_sock(sk);
sk_psock_put(sk, psock);
return copied;
@@ -351,6 +357,10 @@ msg_bytes_ready:
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
data = tcp_msg_wait_data(sk, psock, timeo);
+ if (data < 0) {
+ ret = data;
+ goto unlock;
+ }
if (data) {
if (!sk_psock_queue_empty(psock))
goto msg_bytes_ready;
@@ -361,6 +371,8 @@ msg_bytes_ready:
copied = -EAGAIN;
}
ret = copied;
+
+unlock:
release_sock(sk);
sk_psock_put(sk, psock);
return ret;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 27140e5cdc06..4167e8a48b60 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1869,6 +1869,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
#ifdef CONFIG_TLS_DEVICE
tail->decrypted != skb->decrypted ||
#endif
+ !mptcp_skb_can_collapse(tail, skb) ||
thtail->doff != th->doff ||
memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)))
goto no_coalesce;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9c8c42c280b7..f0723460753c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2542,6 +2542,18 @@ static bool tcp_pacing_check(struct sock *sk)
return true;
}
+static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk)
+{
+ const struct rb_node *node = sk->tcp_rtx_queue.rb_node;
+
+ /* No skb in the rtx queue. */
+ if (!node)
+ return true;
+
+ /* Only one skb in rtx queue. */
+ return !node->rb_left && !node->rb_right;
+}
+
/* TCP Small Queues :
* Control number of packets in qdisc/devices to two packets / or ~1 ms.
* (These limits are doubled for retransmits)
@@ -2579,12 +2591,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
limit += extra_bytes;
}
if (refcount_read(&sk->sk_wmem_alloc) > limit) {
- /* Always send skb if rtx queue is empty.
+ /* Always send skb if rtx queue is empty or has one skb.
* No need to wait for TX completion to call us back,
* after softirq/tasklet schedule.
* This helps when TX completions are delayed too much.
*/
- if (tcp_rtx_queue_empty(sk))
+ if (tcp_rtx_queue_empty_or_single_skb(sk))
return false;
set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
@@ -2788,7 +2800,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- u32 timeout, rto_delta_us;
+ u32 timeout, timeout_us, rto_delta_us;
int early_retrans;
/* Don't do any loss probe on a Fast Open connection before 3WHS
@@ -2812,11 +2824,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
* sample is available then probe after TCP_TIMEOUT_INIT.
*/
if (tp->srtt_us) {
- timeout = usecs_to_jiffies(tp->srtt_us >> 2);
+ timeout_us = tp->srtt_us >> 2;
if (tp->packets_out == 1)
- timeout += TCP_RTO_MIN;
+ timeout_us += tcp_rto_min_us(sk);
else
- timeout += TCP_TIMEOUT_MIN;
+ timeout_us += TCP_TIMEOUT_MIN_US;
+ timeout = usecs_to_jiffies(timeout_us);
} else {
timeout = TCP_TIMEOUT_INIT;
}
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index acf4869c5d3b..bba10110fbbc 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -104,7 +104,7 @@ bool tcp_rack_mark_lost(struct sock *sk)
tp->rack.advanced = 0;
tcp_rack_detect_loss(sk, &timeout);
if (timeout) {
- timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN;
+ timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
timeout, inet_csk(sk)->icsk_rto);
}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index fddd0cbdede1..e023d29e919c 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -770,7 +770,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb)
skb->csum = csum_block_sub(skb->csum, csumdiff,
skb->len - trimlen);
}
- pskb_trim(skb, skb->len - trimlen);
+ ret = pskb_trim(skb, skb->len - trimlen);
+ if (unlikely(ret))
+ return ret;
ret = nexthdr[1];
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 41a680c76d2e..42fb6996b077 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -117,10 +117,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
- if (likely(xdst->u.rt6.rt6i_idev))
- in6_dev_put(xdst->u.rt6.rt6i_idev);
dst_destroy_metrics_generic(dst);
rt6_uncached_list_del(&xdst->u.rt6);
+ if (likely(xdst->u.rt6.rt6i_idev))
+ in6_dev_put(xdst->u.rt6.rt6i_idev);
xfrm_dst_destroy(xdst);
}
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 0665ff5e456e..a2db0585dce0 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -912,7 +912,7 @@ int ieee80211_key_link(struct ieee80211_key *key,
*/
if (ieee80211_key_identical(sdata, old_key, key)) {
ret = -EALREADY;
- goto unlock;
+ goto out;
}
key->local = sdata->local;
@@ -940,7 +940,6 @@ int ieee80211_key_link(struct ieee80211_key *key,
out:
ieee80211_key_free_unused(key);
- unlock:
mutex_unlock(&sdata->local->key_mtx);
return ret;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index c3b83cb390d9..886ab689a8ae 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1298,7 +1298,7 @@ alloc_skb:
if (copy == 0) {
u64 snd_una = READ_ONCE(msk->snd_una);
- if (snd_una != msk->snd_nxt) {
+ if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) {
tcp_remove_empty_skb(ssk);
return 0;
}
@@ -1306,11 +1306,6 @@ alloc_skb:
zero_window_probe = true;
data_seq = snd_una - 1;
copy = 1;
-
- /* all mptcp-level data is acked, no skbs should be present into the
- * ssk write queue
- */
- WARN_ON_ONCE(reuse_skb);
}
copy = min_t(size_t, copy, info->limit - info->sent);
@@ -1339,7 +1334,6 @@ alloc_skb:
if (reuse_skb) {
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
mpext->data_len += copy;
- WARN_ON_ONCE(zero_window_probe);
goto out;
}
@@ -2354,6 +2348,26 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
#define MPTCP_CF_PUSH BIT(1)
#define MPTCP_CF_FASTCLOSE BIT(2)
+/* be sure to send a reset only if the caller asked for it, also
+ * clean completely the subflow status when the subflow reaches
+ * TCP_CLOSE state
+ */
+static void __mptcp_subflow_disconnect(struct sock *ssk,
+ struct mptcp_subflow_context *subflow,
+ unsigned int flags)
+{
+ if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+ (flags & MPTCP_CF_FASTCLOSE)) {
+ /* The MPTCP code never wait on the subflow sockets, TCP-level
+ * disconnect should never fail
+ */
+ WARN_ON_ONCE(tcp_disconnect(ssk, 0));
+ mptcp_subflow_ctx_reset(subflow);
+ } else {
+ tcp_shutdown(ssk, SEND_SHUTDOWN);
+ }
+}
+
/* subflow sockets can be either outgoing (connect) or incoming
* (accept).
*
@@ -2391,7 +2405,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) {
- /* be sure to force the tcp_disconnect() path,
+ /* be sure to force the tcp_close path
* to generate the egress reset
*/
ssk->sk_lingertime = 0;
@@ -2401,11 +2415,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
if (!dispose_it) {
- /* The MPTCP code never wait on the subflow sockets, TCP-level
- * disconnect should never fail
- */
- WARN_ON_ONCE(tcp_disconnect(ssk, 0));
- mptcp_subflow_ctx_reset(subflow);
+ __mptcp_subflow_disconnect(ssk, subflow, flags);
release_sock(ssk);
goto out;
@@ -3098,12 +3108,6 @@ static int mptcp_disconnect(struct sock *sk, int flags)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- /* Deny disconnect if other threads are blocked in sk_wait_event()
- * or inet_wait_for_connect().
- */
- if (sk->sk_wait_pending)
- return -EBUSY;
-
/* We are on the fastopen error path. We can't call straight into the
* subflows cleanup code due to lock nesting (we are already under
* msk->firstsocket lock).
@@ -3173,7 +3177,6 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk);
#endif
- nsk->sk_wait_pending = 0;
__mptcp_init_sock(nsk);
msk = mptcp_sk(nsk);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a72b6aeefb1b..29c651804cb2 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3166,7 +3166,7 @@ int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla,
if (err < 0)
return err;
- if (!tb[NFTA_EXPR_DATA])
+ if (!tb[NFTA_EXPR_DATA] || !tb[NFTA_EXPR_NAME])
return -EINVAL;
type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]);
@@ -5556,7 +5556,6 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
- u64 timeout = 0;
nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM);
if (nest == NULL)
@@ -5592,15 +5591,11 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
htonl(*nft_set_ext_flags(ext))))
goto nla_put_failure;
- if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
- timeout = *nft_set_ext_timeout(ext);
- if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
- nf_jiffies64_to_msecs(timeout),
- NFTA_SET_ELEM_PAD))
- goto nla_put_failure;
- } else if (set->flags & NFT_SET_TIMEOUT) {
- timeout = READ_ONCE(set->timeout);
- }
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
+ nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
+ nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)),
+ NFTA_SET_ELEM_PAD))
+ goto nla_put_failure;
if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
u64 expires, now = get_jiffies_64();
@@ -5615,9 +5610,6 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
nf_jiffies64_to_msecs(expires),
NFTA_SET_ELEM_PAD))
goto nla_put_failure;
-
- if (reset)
- *nft_set_ext_expiration(ext) = now + timeout;
}
if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) {
@@ -7615,6 +7607,16 @@ nla_put_failure:
return -1;
}
+static void audit_log_obj_reset(const struct nft_table *table,
+ unsigned int base_seq, unsigned int nentries)
+{
+ char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq);
+
+ audit_log_nfcfg(buf, table->family, nentries,
+ AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC);
+ kfree(buf);
+}
+
struct nft_obj_filter {
char *table;
u32 type;
@@ -7629,8 +7631,10 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
struct nftables_pernet *nft_net;
+ unsigned int entries = 0;
struct nft_object *obj;
bool reset = false;
+ int rc = 0;
if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
reset = true;
@@ -7643,6 +7647,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
if (family != NFPROTO_UNSPEC && family != table->family)
continue;
+ entries = 0;
list_for_each_entry_rcu(obj, &table->objects, list) {
if (!nft_is_active(net, obj))
goto cont;
@@ -7658,34 +7663,27 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
filter->type != NFT_OBJECT_UNSPEC &&
obj->ops->type->type != filter->type)
goto cont;
- if (reset) {
- char *buf = kasprintf(GFP_ATOMIC,
- "%s:%u",
- table->name,
- nft_net->base_seq);
-
- audit_log_nfcfg(buf,
- family,
- obj->handle,
- AUDIT_NFT_OP_OBJ_RESET,
- GFP_ATOMIC);
- kfree(buf);
- }
- if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- NFT_MSG_NEWOBJ,
- NLM_F_MULTI | NLM_F_APPEND,
- table->family, table,
- obj, reset) < 0)
- goto done;
+ rc = nf_tables_fill_obj_info(skb, net,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NFT_MSG_NEWOBJ,
+ NLM_F_MULTI | NLM_F_APPEND,
+ table->family, table,
+ obj, reset);
+ if (rc < 0)
+ break;
+ entries++;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
idx++;
}
+ if (reset && entries)
+ audit_log_obj_reset(table, nft_net->base_seq, entries);
+ if (rc < 0)
+ break;
}
-done:
rcu_read_unlock();
cb->args[0] = idx;
@@ -7790,7 +7788,7 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
audit_log_nfcfg(buf,
family,
- obj->handle,
+ 1,
AUDIT_NFT_OP_OBJ_RESET,
GFP_ATOMIC);
kfree(buf);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 53c9e76473ba..f03f4d4d7d88 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -698,8 +698,8 @@ nfulnl_log_packet(struct net *net,
unsigned int plen = 0;
struct nfnl_log_net *log = nfnl_log_pernet(net);
const struct nfnl_ct_hook *nfnl_ct = NULL;
+ enum ip_conntrack_info ctinfo = 0;
struct nf_conn *ct = NULL;
- enum ip_conntrack_info ctinfo;
if (li_user && li_user->type == NF_LOG_TYPE_ULOG)
li = li_user;
diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c
index 28e2873ba24e..928312d01eb1 100644
--- a/net/netfilter/nft_inner.c
+++ b/net/netfilter/nft_inner.c
@@ -298,6 +298,7 @@ static int nft_inner_init(const struct nft_ctx *ctx,
int err;
if (!tb[NFTA_INNER_FLAGS] ||
+ !tb[NFTA_INNER_NUM] ||
!tb[NFTA_INNER_HDRSIZE] ||
!tb[NFTA_INNER_TYPE] ||
!tb[NFTA_INNER_EXPR])
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 120f6d395b98..0a689c8e0295 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -179,7 +179,7 @@ void nft_payload_eval(const struct nft_expr *expr,
switch (priv->base) {
case NFT_PAYLOAD_LL_HEADER:
- if (!skb_mac_header_was_set(skb))
+ if (!skb_mac_header_was_set(skb) || skb_mac_header_len(skb) == 0)
goto err;
if (skb_vlan_tag_present(skb) &&
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index 25a75591583e..2e164a319945 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -147,7 +147,7 @@ struct nft_pipapo_match {
unsigned long * __percpu *scratch;
size_t bsize_max;
struct rcu_head rcu;
- struct nft_pipapo_field f[];
+ struct nft_pipapo_field f[] __counted_by(field_count);
};
/**
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 2660ceab3759..e34662f4a71e 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -568,6 +568,8 @@ static void *nft_rbtree_deactivate(const struct net *net,
nft_rbtree_interval_end(this)) {
parent = parent->rb_right;
continue;
+ } else if (nft_set_elem_expired(&rbe->ext)) {
+ break;
} else if (!nft_set_elem_active(&rbe->ext, genmask)) {
parent = parent->rb_left;
continue;
diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c
index 0935527d1d12..b68150c971d0 100644
--- a/net/nfc/nci/spi.c
+++ b/net/nfc/nci/spi.c
@@ -151,6 +151,8 @@ static int send_acknowledge(struct nci_spi *nspi, u8 acknowledge)
int ret;
skb = nci_skb_alloc(nspi->ndev, 0, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
/* add the NCI SPI header to the start of the buffer */
hdr = skb_push(skb, NCI_SPI_HDR_LEN);
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 08630896b6c8..14cc8fe8584b 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -1180,7 +1180,6 @@ static int rfkill_fop_open(struct inode *inode, struct file *file)
init_waitqueue_head(&data->read_wait);
mutex_lock(&rfkill_global_mutex);
- mutex_lock(&data->mtx);
/*
* start getting events from elsewhere but hold mtx to get
* startup events added first
@@ -1192,10 +1191,11 @@ static int rfkill_fop_open(struct inode *inode, struct file *file)
goto free;
rfkill_sync(rfkill);
rfkill_fill_event(&ev->ev, rfkill, RFKILL_OP_ADD);
+ mutex_lock(&data->mtx);
list_add_tail(&ev->list, &data->events);
+ mutex_unlock(&data->mtx);
}
list_add(&data->list, &rfkill_fds);
- mutex_unlock(&data->mtx);
mutex_unlock(&rfkill_global_mutex);
file->private_data = data;
@@ -1203,7 +1203,6 @@ static int rfkill_fop_open(struct inode *inode, struct file *file)
return stream_open(inode, file);
free:
- mutex_unlock(&data->mtx);
mutex_unlock(&rfkill_global_mutex);
mutex_destroy(&data->mtx);
list_for_each_entry_safe(ev, tmp, &data->events, list)
diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index e9d1b2f2ff0a..5a81505fba9a 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -108,13 +108,13 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
rfkill->clk = devm_clk_get(&pdev->dev, NULL);
- gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW);
+ gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_ASIS);
if (IS_ERR(gpio))
return PTR_ERR(gpio);
rfkill->reset_gpio = gpio;
- gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_OUT_LOW);
+ gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_ASIS);
if (IS_ERR(gpio))
return PTR_ERR(gpio);
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 3554085bc2be..880c5f16b29c 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -902,6 +902,14 @@ hfsc_change_usc(struct hfsc_class *cl, struct tc_service_curve *usc,
cl->cl_flags |= HFSC_USC;
}
+static void
+hfsc_upgrade_rt(struct hfsc_class *cl)
+{
+ cl->cl_fsc = cl->cl_rsc;
+ rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total);
+ cl->cl_flags |= HFSC_FSC;
+}
+
static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = {
[TCA_HFSC_RSC] = { .len = sizeof(struct tc_service_curve) },
[TCA_HFSC_FSC] = { .len = sizeof(struct tc_service_curve) },
@@ -1011,10 +1019,6 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
if (parent == NULL)
return -ENOENT;
}
- if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) {
- NL_SET_ERR_MSG(extack, "Invalid parent - parent class must have FSC");
- return -EINVAL;
- }
if (classid == 0 || TC_H_MAJ(classid ^ sch->handle) != 0)
return -EINVAL;
@@ -1065,6 +1069,12 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
cl->cf_tree = RB_ROOT;
sch_tree_lock(sch);
+ /* Check if the inner class is a misconfigured 'rt' */
+ if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) {
+ NL_SET_ERR_MSG(extack,
+ "Forced curve change on parent 'rt' to 'sc'");
+ hfsc_upgrade_rt(parent);
+ }
qdisc_class_hash_insert(&q->clhash, &cl->cl_common);
list_add_tail(&cl->siblings, &parent->children);
if (parent->level == 0)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index bacdd971615e..35ddebae8894 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1201,6 +1201,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
(struct smc_clc_msg_accept_confirm_v2 *)aclc;
struct smc_clc_first_contact_ext *fce =
smc_get_clc_first_contact_ext(clc_v2, false);
+ struct net *net = sock_net(&smc->sk);
int rc;
if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1)
@@ -1210,7 +1211,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
memcpy(ini->smcrv2.nexthop_mac, &aclc->r0.lcl.mac, ETH_ALEN);
ini->smcrv2.uses_gateway = false;
} else {
- if (smc_ib_find_route(smc->clcsock->sk->sk_rcv_saddr,
+ if (smc_ib_find_route(net, smc->clcsock->sk->sk_rcv_saddr,
smc_ib_gid_to_ipv4(aclc->r0.lcl.gid),
ini->smcrv2.nexthop_mac,
&ini->smcrv2.uses_gateway))
@@ -2361,7 +2362,7 @@ static int smc_listen_find_device(struct smc_sock *new_smc,
smc_find_ism_store_rc(rc, ini);
return (!rc) ? 0 : ini->rc;
}
- return SMC_CLC_DECL_NOSMCDEV;
+ return prfx_rc;
}
/* listen worker: finish RDMA setup */
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 9b66d6aeeb1a..89981dbe46c9 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -193,7 +193,7 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
}
-int smc_ib_find_route(__be32 saddr, __be32 daddr,
+int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr,
u8 nexthop_mac[], u8 *uses_gateway)
{
struct neighbour *neigh = NULL;
@@ -205,7 +205,7 @@ int smc_ib_find_route(__be32 saddr, __be32 daddr,
if (daddr == cpu_to_be32(INADDR_NONE))
goto out;
- rt = ip_route_output_flow(&init_net, &fl4, NULL);
+ rt = ip_route_output_flow(net, &fl4, NULL);
if (IS_ERR(rt))
goto out;
if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET)
@@ -235,6 +235,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev,
if (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP &&
smc_ib_gid_to_ipv4((u8 *)&attr->gid) != cpu_to_be32(INADDR_NONE)) {
struct in_device *in_dev = __in_dev_get_rcu(ndev);
+ struct net *net = dev_net(ndev);
const struct in_ifaddr *ifa;
bool subnet_match = false;
@@ -248,7 +249,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev,
}
if (!subnet_match)
goto out;
- if (smcrv2->daddr && smc_ib_find_route(smcrv2->saddr,
+ if (smcrv2->daddr && smc_ib_find_route(net, smcrv2->saddr,
smcrv2->daddr,
smcrv2->nexthop_mac,
&smcrv2->uses_gateway))
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 4df5f8c8a0a1..ef8ac2b7546d 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -112,7 +112,7 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk,
int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
unsigned short vlan_id, u8 gid[], u8 *sgid_index,
struct smc_init_info_smcrv2 *smcrv2);
-int smc_ib_find_route(__be32 saddr, __be32 daddr,
+int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr,
u8 nexthop_mac[], u8 *uses_gateway);
bool smc_ib_is_valid_local_systemid(void);
int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 02f583ff9239..002483e60c19 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -139,8 +139,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx)
int wait_on_pending_writer(struct sock *sk, long *timeo)
{
- int rc = 0;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ int ret, rc = 0;
add_wait_queue(sk_sleep(sk), &wait);
while (1) {
@@ -154,9 +154,13 @@ int wait_on_pending_writer(struct sock *sk, long *timeo)
break;
}
- if (sk_wait_event(sk, timeo,
- !READ_ONCE(sk->sk_write_pending), &wait))
+ ret = sk_wait_event(sk, timeo,
+ !READ_ONCE(sk->sk_write_pending), &wait);
+ if (ret) {
+ if (ret < 0)
+ rc = ret;
break;
+ }
}
remove_wait_queue(sk_sleep(sk), &wait);
return rc;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index d1fc295b83b5..e9d1e83a859d 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1291,6 +1291,7 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock,
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ int ret = 0;
long timeo;
timeo = sock_rcvtimeo(sk, nonblock);
@@ -1302,6 +1303,9 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock,
if (sk->sk_err)
return sock_error(sk);
+ if (ret < 0)
+ return ret;
+
if (!skb_queue_empty(&sk->sk_receive_queue)) {
tls_strp_check_rcv(&ctx->strp);
if (tls_strp_msg_ready(ctx))
@@ -1320,10 +1324,10 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock,
released = true;
add_wait_queue(sk_sleep(sk), &wait);
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
- sk_wait_event(sk, &timeo,
- tls_strp_msg_ready(ctx) ||
- !sk_psock_queue_empty(psock),
- &wait);
+ ret = sk_wait_event(sk, &timeo,
+ tls_strp_msg_ready(ctx) ||
+ !sk_psock_queue_empty(psock),
+ &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
remove_wait_queue(sk_sleep(sk), &wait);
@@ -1852,6 +1856,7 @@ static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx,
bool nonblock)
{
long timeo;
+ int ret;
timeo = sock_rcvtimeo(sk, nonblock);
@@ -1861,14 +1866,16 @@ static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx,
ctx->reader_contended = 1;
add_wait_queue(&ctx->wq, &wait);
- sk_wait_event(sk, &timeo,
- !READ_ONCE(ctx->reader_present), &wait);
+ ret = sk_wait_event(sk, &timeo,
+ !READ_ONCE(ctx->reader_present), &wait);
remove_wait_queue(&ctx->wq, &wait);
if (timeo <= 0)
return -EAGAIN;
if (signal_pending(current))
return sock_intr_errno(timeo);
+ if (ret < 0)
+ return ret;
}
WRITE_ONCE(ctx->reader_present, 1);
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 64e861617110..acec41c1809a 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1622,7 +1622,7 @@ void wiphy_work_queue(struct wiphy *wiphy, struct wiphy_work *work)
list_add_tail(&work->entry, &rdev->wiphy_work_list);
spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags);
- schedule_work(&rdev->wiphy_work);
+ queue_work(system_unbound_wq, &rdev->wiphy_work);
}
EXPORT_SYMBOL_GPL(wiphy_work_queue);
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index b86474084690..e21cc71095bb 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -380,8 +380,8 @@ static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
skb->dev = dev;
if (err) {
- dev->stats.rx_errors++;
- dev->stats.rx_dropped++;
+ DEV_STATS_INC(dev, rx_errors);
+ DEV_STATS_INC(dev, rx_dropped);
return 0;
}
@@ -426,7 +426,6 @@ static int
xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
{
struct xfrm_if *xi = netdev_priv(dev);
- struct net_device_stats *stats = &xi->dev->stats;
struct dst_entry *dst = skb_dst(skb);
unsigned int length = skb->len;
struct net_device *tdev;
@@ -473,7 +472,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
tdev = dst->dev;
if (tdev == dev) {
- stats->collisions++;
+ DEV_STATS_INC(dev, collisions);
net_warn_ratelimited("%s: Local routing loop detected!\n",
dev->name);
goto tx_err_dst_release;
@@ -512,13 +511,13 @@ xmit:
if (net_xmit_eval(err) == 0) {
dev_sw_netstats_tx_add(dev, 1, length);
} else {
- stats->tx_errors++;
- stats->tx_aborted_errors++;
+ DEV_STATS_INC(dev, tx_errors);
+ DEV_STATS_INC(dev, tx_aborted_errors);
}
return 0;
tx_err_link_failure:
- stats->tx_carrier_errors++;
+ DEV_STATS_INC(dev, tx_carrier_errors);
dst_link_failure(skb);
tx_err_dst_release:
dst_release(dst);
@@ -528,7 +527,6 @@ tx_err_dst_release:
static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct xfrm_if *xi = netdev_priv(dev);
- struct net_device_stats *stats = &xi->dev->stats;
struct dst_entry *dst = skb_dst(skb);
struct flowi fl;
int ret;
@@ -545,7 +543,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6);
if (dst->error) {
dst_release(dst);
- stats->tx_carrier_errors++;
+ DEV_STATS_INC(dev, tx_carrier_errors);
goto tx_err;
}
skb_dst_set(skb, dst);
@@ -561,7 +559,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4);
if (IS_ERR(rt)) {
- stats->tx_carrier_errors++;
+ DEV_STATS_INC(dev, tx_carrier_errors);
goto tx_err;
}
skb_dst_set(skb, &rt->dst);
@@ -580,8 +578,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
tx_err:
- stats->tx_errors++;
- stats->tx_dropped++;
+ DEV_STATS_INC(dev, tx_errors);
+ DEV_STATS_INC(dev, tx_dropped);
kfree_skb(skb);
return NETDEV_TX_OK;
}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index d6b405782b63..d24b4d4f620e 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -851,7 +851,7 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net,
struct hlist_node *newpos = NULL;
bool matches_s, matches_d;
- if (!policy->bydst_reinsert)
+ if (policy->walk.dead || !policy->bydst_reinsert)
continue;
WARN_ON_ONCE(policy->family != family);
@@ -1256,8 +1256,11 @@ static void xfrm_hash_rebuild(struct work_struct *work)
struct xfrm_pol_inexact_bin *bin;
u8 dbits, sbits;
+ if (policy->walk.dead)
+ continue;
+
dir = xfrm_policy_id2dir(policy->index);
- if (policy->walk.dead || dir >= XFRM_POLICY_MAX)
+ if (dir >= XFRM_POLICY_MAX)
continue;
if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
@@ -1372,8 +1375,6 @@ EXPORT_SYMBOL(xfrm_policy_hash_rebuild);
* of an absolute inpredictability of ordering of rules. This will not pass. */
static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
{
- static u32 idx_generator;
-
for (;;) {
struct hlist_head *list;
struct xfrm_policy *p;
@@ -1381,8 +1382,8 @@ static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
int found;
if (!index) {
- idx = (idx_generator | dir);
- idx_generator += 8;
+ idx = (net->xfrm.idx_generator | dir);
+ net->xfrm.idx_generator += 8;
} else {
idx = index;
index = 0;
@@ -1823,9 +1824,11 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
again:
list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+ if (pol->walk.dead)
+ continue;
+
dir = xfrm_policy_id2dir(pol->index);
- if (pol->walk.dead ||
- dir >= XFRM_POLICY_MAX ||
+ if (dir >= XFRM_POLICY_MAX ||
pol->type != type)
continue;
@@ -1862,9 +1865,11 @@ int xfrm_dev_policy_flush(struct net *net, struct net_device *dev,
again:
list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+ if (pol->walk.dead)
+ continue;
+
dir = xfrm_policy_id2dir(pol->index);
- if (pol->walk.dead ||
- dir >= XFRM_POLICY_MAX ||
+ if (dir >= XFRM_POLICY_MAX ||
pol->xdo.dev != dev)
continue;
@@ -3215,7 +3220,7 @@ no_transform:
}
for (i = 0; i < num_pols; i++)
- pols[i]->curlft.use_time = ktime_get_real_seconds();
+ WRITE_ONCE(pols[i]->curlft.use_time, ktime_get_real_seconds());
if (num_xfrms < 0) {
/* Prohibit the flow */