summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorJae Hyun Yoo <jae.hyun.yoo@linux.intel.com>2021-10-01 21:38:40 +0300
committerJae Hyun Yoo <jae.hyun.yoo@linux.intel.com>2021-10-01 21:40:21 +0300
commit9c881021a269af242594e2dfc79f1c4701404887 (patch)
treec8ec14f412d7ea35009b2dee08770082ddbb5c6e /net
parente9479d98b87227b8b7502c4c1e778887b23799f1 (diff)
parentcf06e1ab1c3ed354da5873e646f2164fea147c88 (diff)
downloadlinux-dev-5.10-intel.tar.xz
Merge branch 'dev-5.10' into dev-5.10-inteldev-5.10-intel
Pull 5.10.67 stable from OpenBMC upstream. Signed-off-by: Jae Hyun Yoo <jae.hyun.yoo@linux.intel.com>
Diffstat (limited to 'net')
-rw-r--r--net/6lowpan/debugfs.c3
-rw-r--r--net/9p/trans_xen.c4
-rw-r--r--net/bluetooth/cmtp/cmtp.h2
-rw-r--r--net/bluetooth/hci_core.c6
-rw-r--r--net/bluetooth/hci_event.c108
-rw-r--r--net/bluetooth/hidp/core.c2
-rw-r--r--net/bluetooth/mgmt.c2
-rw-r--r--net/bluetooth/sco.c85
-rw-r--r--net/bpf/test_run.c6
-rw-r--r--net/core/devlink.c36
-rw-r--r--net/core/flow_dissector.c12
-rw-r--r--net/core/flow_offload.c89
-rw-r--r--net/core/rtnetlink.c3
-rw-r--r--net/dccp/dccp.h6
-rw-r--r--net/ethtool/ioctl.c136
-rw-r--r--net/ipv4/igmp.c2
-rw-r--r--net/ipv4/ip_gre.c2
-rw-r--r--net/ipv4/ip_output.c5
-rw-r--r--net/ipv4/route.c60
-rw-r--r--net/ipv4/tcp_fastopen.c3
-rw-r--r--net/ipv4/tcp_ipv4.c5
-rw-r--r--net/ipv6/route.c25
-rw-r--r--net/mac80211/iface.c11
-rw-r--r--net/mac80211/tx.c4
-rw-r--r--net/netfilter/nf_conntrack_core.c71
-rw-r--r--net/netfilter/nf_flow_table_offload.c1
-rw-r--r--net/netfilter/nf_tables_api.c89
-rw-r--r--net/netfilter/nf_tables_offload.c1
-rw-r--r--net/netfilter/nft_set_hash.c10
-rw-r--r--net/netlabel/netlabel_cipso_v4.c12
-rw-r--r--net/netlink/af_netlink.c4
-rw-r--r--net/openvswitch/vport.c1
-rw-r--r--net/qrtr/qrtr.c2
-rw-r--r--net/rds/ib_frmr.c4
-rw-r--r--net/sched/cls_api.c1
-rw-r--r--net/sched/sch_cake.c2
-rw-r--r--net/sched/sch_cbq.c2
-rw-r--r--net/sched/sch_ets.c7
-rw-r--r--net/sched/sch_taprio.c4
-rw-r--r--net/socket.c131
-rw-r--r--net/sunrpc/auth_gss/svcauth_gss.c2
-rw-r--r--net/sunrpc/xprt.c8
-rw-r--r--net/sunrpc/xprtrdma/transport.c11
-rw-r--r--net/sunrpc/xprtsock.c7
-rw-r--r--net/tipc/socket.c38
-rw-r--r--net/xfrm/xfrm_ipcomp.c2
46 files changed, 633 insertions, 394 deletions
diff --git a/net/6lowpan/debugfs.c b/net/6lowpan/debugfs.c
index 1c140af06d52..600b9563bfc5 100644
--- a/net/6lowpan/debugfs.c
+++ b/net/6lowpan/debugfs.c
@@ -170,7 +170,8 @@ static void lowpan_dev_debugfs_ctx_init(struct net_device *dev,
struct dentry *root;
char buf[32];
- WARN_ON_ONCE(id > LOWPAN_IPHC_CTX_TABLE_SIZE);
+ if (WARN_ON_ONCE(id >= LOWPAN_IPHC_CTX_TABLE_SIZE))
+ return;
sprintf(buf, "%d", id);
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index f4fea28e05da..3ec1a51a6944 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -138,7 +138,7 @@ static bool p9_xen_write_todo(struct xen_9pfs_dataring *ring, RING_IDX size)
static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
{
- struct xen_9pfs_front_priv *priv = NULL;
+ struct xen_9pfs_front_priv *priv;
RING_IDX cons, prod, masked_cons, masked_prod;
unsigned long flags;
u32 size = p9_req->tc.size;
@@ -151,7 +151,7 @@ static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
break;
}
read_unlock(&xen_9pfs_lock);
- if (!priv || priv->client != client)
+ if (list_entry_is_head(priv, &xen_9pfs_devs, list))
return -EINVAL;
num = p9_req->tc.tag % priv->num_rings;
diff --git a/net/bluetooth/cmtp/cmtp.h b/net/bluetooth/cmtp/cmtp.h
index c32638dddbf9..f6b9dc4e408f 100644
--- a/net/bluetooth/cmtp/cmtp.h
+++ b/net/bluetooth/cmtp/cmtp.h
@@ -26,7 +26,7 @@
#include <linux/types.h>
#include <net/bluetooth/bluetooth.h>
-#define BTNAMSIZ 18
+#define BTNAMSIZ 21
/* CMTP ioctl defines */
#define CMTPCONNADD _IOW('C', 200, int)
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 65d3f5409963..2ad66f64879f 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1336,6 +1336,12 @@ int hci_inquiry(void __user *arg)
goto done;
}
+ /* Restrict maximum inquiry length to 60 seconds */
+ if (ir.length > 60) {
+ err = -EINVAL;
+ goto done;
+ }
+
hci_dev_lock(hdev);
if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX ||
inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) {
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index e59ae24a8f17..9f52145bb7b7 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4329,6 +4329,21 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev,
switch (ev->status) {
case 0x00:
+ /* The synchronous connection complete event should only be
+ * sent once per new connection. Receiving a successful
+ * complete event when the connection status is already
+ * BT_CONNECTED means that the device is misbehaving and sent
+ * multiple complete event packets for the same new connection.
+ *
+ * Registering the device more than once can corrupt kernel
+ * memory, hence upon detecting this invalid event, we report
+ * an error and ignore the packet.
+ */
+ if (conn->state == BT_CONNECTED) {
+ bt_dev_err(hdev, "Ignoring connect complete event for existing connection");
+ goto unlock;
+ }
+
conn->handle = __le16_to_cpu(ev->handle);
conn->state = BT_CONNECTED;
conn->type = ev->link_type;
@@ -5055,9 +5070,64 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev,
}
#endif
+static void le_conn_update_addr(struct hci_conn *conn, bdaddr_t *bdaddr,
+ u8 bdaddr_type, bdaddr_t *local_rpa)
+{
+ if (conn->out) {
+ conn->dst_type = bdaddr_type;
+ conn->resp_addr_type = bdaddr_type;
+ bacpy(&conn->resp_addr, bdaddr);
+
+ /* Check if the controller has set a Local RPA then it must be
+ * used instead or hdev->rpa.
+ */
+ if (local_rpa && bacmp(local_rpa, BDADDR_ANY)) {
+ conn->init_addr_type = ADDR_LE_DEV_RANDOM;
+ bacpy(&conn->init_addr, local_rpa);
+ } else if (hci_dev_test_flag(conn->hdev, HCI_PRIVACY)) {
+ conn->init_addr_type = ADDR_LE_DEV_RANDOM;
+ bacpy(&conn->init_addr, &conn->hdev->rpa);
+ } else {
+ hci_copy_identity_address(conn->hdev, &conn->init_addr,
+ &conn->init_addr_type);
+ }
+ } else {
+ conn->resp_addr_type = conn->hdev->adv_addr_type;
+ /* Check if the controller has set a Local RPA then it must be
+ * used instead or hdev->rpa.
+ */
+ if (local_rpa && bacmp(local_rpa, BDADDR_ANY)) {
+ conn->resp_addr_type = ADDR_LE_DEV_RANDOM;
+ bacpy(&conn->resp_addr, local_rpa);
+ } else if (conn->hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) {
+ /* In case of ext adv, resp_addr will be updated in
+ * Adv Terminated event.
+ */
+ if (!ext_adv_capable(conn->hdev))
+ bacpy(&conn->resp_addr,
+ &conn->hdev->random_addr);
+ } else {
+ bacpy(&conn->resp_addr, &conn->hdev->bdaddr);
+ }
+
+ conn->init_addr_type = bdaddr_type;
+ bacpy(&conn->init_addr, bdaddr);
+
+ /* For incoming connections, set the default minimum
+ * and maximum connection interval. They will be used
+ * to check if the parameters are in range and if not
+ * trigger the connection update procedure.
+ */
+ conn->le_conn_min_interval = conn->hdev->le_conn_min_interval;
+ conn->le_conn_max_interval = conn->hdev->le_conn_max_interval;
+ }
+}
+
static void le_conn_complete_evt(struct hci_dev *hdev, u8 status,
- bdaddr_t *bdaddr, u8 bdaddr_type, u8 role, u16 handle,
- u16 interval, u16 latency, u16 supervision_timeout)
+ bdaddr_t *bdaddr, u8 bdaddr_type,
+ bdaddr_t *local_rpa, u8 role, u16 handle,
+ u16 interval, u16 latency,
+ u16 supervision_timeout)
{
struct hci_conn_params *params;
struct hci_conn *conn;
@@ -5105,32 +5175,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status,
cancel_delayed_work(&conn->le_conn_timeout);
}
- if (!conn->out) {
- /* Set the responder (our side) address type based on
- * the advertising address type.
- */
- conn->resp_addr_type = hdev->adv_addr_type;
- if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) {
- /* In case of ext adv, resp_addr will be updated in
- * Adv Terminated event.
- */
- if (!ext_adv_capable(hdev))
- bacpy(&conn->resp_addr, &hdev->random_addr);
- } else {
- bacpy(&conn->resp_addr, &hdev->bdaddr);
- }
-
- conn->init_addr_type = bdaddr_type;
- bacpy(&conn->init_addr, bdaddr);
-
- /* For incoming connections, set the default minimum
- * and maximum connection interval. They will be used
- * to check if the parameters are in range and if not
- * trigger the connection update procedure.
- */
- conn->le_conn_min_interval = hdev->le_conn_min_interval;
- conn->le_conn_max_interval = hdev->le_conn_max_interval;
- }
+ le_conn_update_addr(conn, bdaddr, bdaddr_type, local_rpa);
/* Lookup the identity address from the stored connection
* address and address type.
@@ -5224,7 +5269,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type,
- ev->role, le16_to_cpu(ev->handle),
+ NULL, ev->role, le16_to_cpu(ev->handle),
le16_to_cpu(ev->interval),
le16_to_cpu(ev->latency),
le16_to_cpu(ev->supervision_timeout));
@@ -5238,7 +5283,7 @@ static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev,
BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type,
- ev->role, le16_to_cpu(ev->handle),
+ &ev->local_rpa, ev->role, le16_to_cpu(ev->handle),
le16_to_cpu(ev->interval),
le16_to_cpu(ev->latency),
le16_to_cpu(ev->supervision_timeout));
@@ -5274,7 +5319,8 @@ static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb)
if (conn) {
struct adv_info *adv_instance;
- if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM)
+ if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM ||
+ bacmp(&conn->resp_addr, BDADDR_ANY))
return;
if (!hdev->cur_adv_instance) {
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 3b4fa27a44e6..0db48c812662 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -1290,7 +1290,7 @@ static int hidp_session_thread(void *arg)
/* cleanup runtime environment */
remove_wait_queue(sk_sleep(session->intr_sock->sk), &intr_wait);
- remove_wait_queue(sk_sleep(session->intr_sock->sk), &ctrl_wait);
+ remove_wait_queue(sk_sleep(session->ctrl_sock->sk), &ctrl_wait);
wake_up_interruptible(&session->report_queue);
hidp_del_timer(session);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 31a585fe0c7c..08f67f91d427 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -7464,7 +7464,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
* advertising.
*/
if (hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY))
- return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
+ return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
MGMT_STATUS_NOT_SUPPORTED);
if (cp->instance < 1 || cp->instance > hdev->le_num_of_adv_sets)
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 22a110f37abc..7c24a9acbc45 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -48,6 +48,8 @@ struct sco_conn {
spinlock_t lock;
struct sock *sk;
+ struct delayed_work timeout_work;
+
unsigned int mtu;
};
@@ -74,9 +76,20 @@ struct sco_pinfo {
#define SCO_CONN_TIMEOUT (HZ * 40)
#define SCO_DISCONN_TIMEOUT (HZ * 2)
-static void sco_sock_timeout(struct timer_list *t)
+static void sco_sock_timeout(struct work_struct *work)
{
- struct sock *sk = from_timer(sk, t, sk_timer);
+ struct sco_conn *conn = container_of(work, struct sco_conn,
+ timeout_work.work);
+ struct sock *sk;
+
+ sco_conn_lock(conn);
+ sk = conn->sk;
+ if (sk)
+ sock_hold(sk);
+ sco_conn_unlock(conn);
+
+ if (!sk)
+ return;
BT_DBG("sock %p state %d", sk, sk->sk_state);
@@ -85,20 +98,26 @@ static void sco_sock_timeout(struct timer_list *t)
sk->sk_state_change(sk);
bh_unlock_sock(sk);
- sco_sock_kill(sk);
sock_put(sk);
}
static void sco_sock_set_timer(struct sock *sk, long timeout)
{
+ if (!sco_pi(sk)->conn)
+ return;
+
BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout);
- sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout);
+ cancel_delayed_work(&sco_pi(sk)->conn->timeout_work);
+ schedule_delayed_work(&sco_pi(sk)->conn->timeout_work, timeout);
}
static void sco_sock_clear_timer(struct sock *sk)
{
+ if (!sco_pi(sk)->conn)
+ return;
+
BT_DBG("sock %p state %d", sk, sk->sk_state);
- sk_stop_timer(sk, &sk->sk_timer);
+ cancel_delayed_work(&sco_pi(sk)->conn->timeout_work);
}
/* ---- SCO connections ---- */
@@ -177,8 +196,10 @@ static void sco_conn_del(struct hci_conn *hcon, int err)
sco_sock_clear_timer(sk);
sco_chan_del(sk, err);
bh_unlock_sock(sk);
- sco_sock_kill(sk);
sock_put(sk);
+
+ /* Ensure no more work items will run before freeing conn. */
+ cancel_delayed_work_sync(&conn->timeout_work);
}
hcon->sco_data = NULL;
@@ -193,6 +214,8 @@ static void __sco_chan_add(struct sco_conn *conn, struct sock *sk,
sco_pi(sk)->conn = conn;
conn->sk = sk;
+ INIT_DELAYED_WORK(&conn->timeout_work, sco_sock_timeout);
+
if (parent)
bt_accept_enqueue(parent, sk, true);
}
@@ -212,44 +235,32 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk,
return err;
}
-static int sco_connect(struct sock *sk)
+static int sco_connect(struct hci_dev *hdev, struct sock *sk)
{
struct sco_conn *conn;
struct hci_conn *hcon;
- struct hci_dev *hdev;
int err, type;
BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst);
- hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR);
- if (!hdev)
- return -EHOSTUNREACH;
-
- hci_dev_lock(hdev);
-
if (lmp_esco_capable(hdev) && !disable_esco)
type = ESCO_LINK;
else
type = SCO_LINK;
if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT &&
- (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) {
- err = -EOPNOTSUPP;
- goto done;
- }
+ (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev)))
+ return -EOPNOTSUPP;
hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst,
sco_pi(sk)->setting);
- if (IS_ERR(hcon)) {
- err = PTR_ERR(hcon);
- goto done;
- }
+ if (IS_ERR(hcon))
+ return PTR_ERR(hcon);
conn = sco_conn_add(hcon);
if (!conn) {
hci_conn_drop(hcon);
- err = -ENOMEM;
- goto done;
+ return -ENOMEM;
}
/* Update source addr of the socket */
@@ -257,7 +268,7 @@ static int sco_connect(struct sock *sk)
err = sco_chan_add(conn, sk, NULL);
if (err)
- goto done;
+ return err;
if (hcon->state == BT_CONNECTED) {
sco_sock_clear_timer(sk);
@@ -267,9 +278,6 @@ static int sco_connect(struct sock *sk)
sco_sock_set_timer(sk, sk->sk_sndtimeo);
}
-done:
- hci_dev_unlock(hdev);
- hci_dev_put(hdev);
return err;
}
@@ -394,8 +402,7 @@ static void sco_sock_cleanup_listen(struct sock *parent)
*/
static void sco_sock_kill(struct sock *sk)
{
- if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket ||
- sock_flag(sk, SOCK_DEAD))
+ if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket)
return;
BT_DBG("sk %p state %d", sk, sk->sk_state);
@@ -447,7 +454,6 @@ static void sco_sock_close(struct sock *sk)
lock_sock(sk);
__sco_sock_close(sk);
release_sock(sk);
- sco_sock_kill(sk);
}
static void sco_skb_put_cmsg(struct sk_buff *skb, struct msghdr *msg,
@@ -500,8 +506,6 @@ static struct sock *sco_sock_alloc(struct net *net, struct socket *sock,
sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT;
- timer_setup(&sk->sk_timer, sco_sock_timeout, 0);
-
bt_sock_link(&sco_sk_list, sk);
return sk;
}
@@ -566,6 +570,7 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen
{
struct sockaddr_sco *sa = (struct sockaddr_sco *) addr;
struct sock *sk = sock->sk;
+ struct hci_dev *hdev;
int err;
BT_DBG("sk %p", sk);
@@ -580,12 +585,19 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen
if (sk->sk_type != SOCK_SEQPACKET)
return -EINVAL;
+ hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR);
+ if (!hdev)
+ return -EHOSTUNREACH;
+ hci_dev_lock(hdev);
+
lock_sock(sk);
/* Set destination address and psm */
bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr);
- err = sco_connect(sk);
+ err = sco_connect(hdev, sk);
+ hci_dev_unlock(hdev);
+ hci_dev_put(hdev);
if (err)
goto done;
@@ -773,6 +785,11 @@ static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting)
cp.max_latency = cpu_to_le16(0xffff);
cp.retrans_effort = 0xff;
break;
+ default:
+ /* use CVSD settings as fallback */
+ cp.max_latency = cpu_to_le16(0xffff);
+ cp.retrans_effort = 0xff;
+ break;
}
hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ,
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index e7cbd1b4a5e5..72d424a5a142 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -42,13 +42,17 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
migrate_disable();
time_start = ktime_get_ns();
for (i = 0; i < repeat; i++) {
- bpf_cgroup_storage_set(storage);
+ ret = bpf_cgroup_storage_set(storage);
+ if (ret)
+ break;
if (xdp)
*retval = bpf_prog_run_xdp(prog, ctx);
else
*retval = BPF_PROG_RUN(prog, ctx);
+ bpf_cgroup_storage_unset();
+
if (signal_pending(current)) {
ret = -EINTR;
break;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 90badb6f7227..96cf4bc1f958 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3079,10 +3079,12 @@ static void devlink_param_notify(struct devlink *devlink,
struct devlink_param_item *param_item,
enum devlink_command cmd);
-static void devlink_reload_netns_change(struct devlink *devlink,
- struct net *dest_net)
+static void devlink_ns_change_notify(struct devlink *devlink,
+ struct net *dest_net, struct net *curr_net,
+ bool new)
{
struct devlink_param_item *param_item;
+ enum devlink_command cmd;
/* Userspace needs to be notified about devlink objects
* removed from original and entering new network namespace.
@@ -3090,17 +3092,18 @@ static void devlink_reload_netns_change(struct devlink *devlink,
* reload process so the notifications are generated separatelly.
*/
- list_for_each_entry(param_item, &devlink->param_list, list)
- devlink_param_notify(devlink, 0, param_item,
- DEVLINK_CMD_PARAM_DEL);
- devlink_notify(devlink, DEVLINK_CMD_DEL);
+ if (!dest_net || net_eq(dest_net, curr_net))
+ return;
- __devlink_net_set(devlink, dest_net);
+ if (new)
+ devlink_notify(devlink, DEVLINK_CMD_NEW);
- devlink_notify(devlink, DEVLINK_CMD_NEW);
+ cmd = new ? DEVLINK_CMD_PARAM_NEW : DEVLINK_CMD_PARAM_DEL;
list_for_each_entry(param_item, &devlink->param_list, list)
- devlink_param_notify(devlink, 0, param_item,
- DEVLINK_CMD_PARAM_NEW);
+ devlink_param_notify(devlink, 0, param_item, cmd);
+
+ if (!new)
+ devlink_notify(devlink, DEVLINK_CMD_DEL);
}
static bool devlink_reload_supported(const struct devlink_ops *ops)
@@ -3180,6 +3183,7 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net,
u32 *actions_performed, struct netlink_ext_ack *extack)
{
u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE];
+ struct net *curr_net;
int err;
if (!devlink->reload_enabled)
@@ -3187,18 +3191,22 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net,
memcpy(remote_reload_stats, devlink->stats.remote_reload_stats,
sizeof(remote_reload_stats));
+
+ curr_net = devlink_net(devlink);
+ devlink_ns_change_notify(devlink, dest_net, curr_net, false);
err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack);
if (err)
return err;
- if (dest_net && !net_eq(dest_net, devlink_net(devlink)))
- devlink_reload_netns_change(devlink, dest_net);
+ if (dest_net && !net_eq(dest_net, curr_net))
+ __devlink_net_set(devlink, dest_net);
err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack);
devlink_reload_failed_set(devlink, !!err);
if (err)
return err;
+ devlink_ns_change_notify(devlink, dest_net, curr_net, true);
WARN_ON(!(*actions_performed & BIT(action)));
/* Catch driver on updating the remote action within devlink reload */
WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats,
@@ -3395,7 +3403,7 @@ out_free_msg:
void devlink_flash_update_begin_notify(struct devlink *devlink)
{
- struct devlink_flash_notify params = { 0 };
+ struct devlink_flash_notify params = {};
__devlink_flash_update_notify(devlink,
DEVLINK_CMD_FLASH_UPDATE,
@@ -3405,7 +3413,7 @@ EXPORT_SYMBOL_GPL(devlink_flash_update_begin_notify);
void devlink_flash_update_end_notify(struct devlink *devlink)
{
- struct devlink_flash_notify params = { 0 };
+ struct devlink_flash_notify params = {};
__devlink_flash_update_notify(devlink,
DEVLINK_CMD_FLASH_UPDATE_END,
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index c52e5ea654e9..813c709c61cf 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1047,8 +1047,10 @@ proto_again:
FLOW_DISSECTOR_KEY_IPV4_ADDRS,
target_container);
- memcpy(&key_addrs->v4addrs, &iph->saddr,
- sizeof(key_addrs->v4addrs));
+ memcpy(&key_addrs->v4addrs.src, &iph->saddr,
+ sizeof(key_addrs->v4addrs.src));
+ memcpy(&key_addrs->v4addrs.dst, &iph->daddr,
+ sizeof(key_addrs->v4addrs.dst));
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
}
@@ -1092,8 +1094,10 @@ proto_again:
FLOW_DISSECTOR_KEY_IPV6_ADDRS,
target_container);
- memcpy(&key_addrs->v6addrs, &iph->saddr,
- sizeof(key_addrs->v6addrs));
+ memcpy(&key_addrs->v6addrs.src, &iph->saddr,
+ sizeof(key_addrs->v6addrs.src));
+ memcpy(&key_addrs->v6addrs.dst, &iph->daddr,
+ sizeof(key_addrs->v6addrs.dst));
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
}
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index 715b67f6c62f..e3f0d5906811 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -321,6 +321,7 @@ EXPORT_SYMBOL(flow_block_cb_setup_simple);
static DEFINE_MUTEX(flow_indr_block_lock);
static LIST_HEAD(flow_block_indr_list);
static LIST_HEAD(flow_block_indr_dev_list);
+static LIST_HEAD(flow_indir_dev_list);
struct flow_indr_dev {
struct list_head list;
@@ -346,6 +347,33 @@ static struct flow_indr_dev *flow_indr_dev_alloc(flow_indr_block_bind_cb_t *cb,
return indr_dev;
}
+struct flow_indir_dev_info {
+ void *data;
+ struct net_device *dev;
+ struct Qdisc *sch;
+ enum tc_setup_type type;
+ void (*cleanup)(struct flow_block_cb *block_cb);
+ struct list_head list;
+ enum flow_block_command command;
+ enum flow_block_binder_type binder_type;
+ struct list_head *cb_list;
+};
+
+static void existing_qdiscs_register(flow_indr_block_bind_cb_t *cb, void *cb_priv)
+{
+ struct flow_block_offload bo;
+ struct flow_indir_dev_info *cur;
+
+ list_for_each_entry(cur, &flow_indir_dev_list, list) {
+ memset(&bo, 0, sizeof(bo));
+ bo.command = cur->command;
+ bo.binder_type = cur->binder_type;
+ INIT_LIST_HEAD(&bo.cb_list);
+ cb(cur->dev, cur->sch, cb_priv, cur->type, &bo, cur->data, cur->cleanup);
+ list_splice(&bo.cb_list, cur->cb_list);
+ }
+}
+
int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv)
{
struct flow_indr_dev *indr_dev;
@@ -367,6 +395,7 @@ int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv)
}
list_add(&indr_dev->list, &flow_block_indr_dev_list);
+ existing_qdiscs_register(cb, cb_priv);
mutex_unlock(&flow_indr_block_lock);
return 0;
@@ -463,7 +492,59 @@ out:
}
EXPORT_SYMBOL(flow_indr_block_cb_alloc);
-int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch,
+static struct flow_indir_dev_info *find_indir_dev(void *data)
+{
+ struct flow_indir_dev_info *cur;
+
+ list_for_each_entry(cur, &flow_indir_dev_list, list) {
+ if (cur->data == data)
+ return cur;
+ }
+ return NULL;
+}
+
+static int indir_dev_add(void *data, struct net_device *dev, struct Qdisc *sch,
+ enum tc_setup_type type, void (*cleanup)(struct flow_block_cb *block_cb),
+ struct flow_block_offload *bo)
+{
+ struct flow_indir_dev_info *info;
+
+ info = find_indir_dev(data);
+ if (info)
+ return -EEXIST;
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (!info)
+ return -ENOMEM;
+
+ info->data = data;
+ info->dev = dev;
+ info->sch = sch;
+ info->type = type;
+ info->cleanup = cleanup;
+ info->command = bo->command;
+ info->binder_type = bo->binder_type;
+ info->cb_list = bo->cb_list_head;
+
+ list_add(&info->list, &flow_indir_dev_list);
+ return 0;
+}
+
+static int indir_dev_remove(void *data)
+{
+ struct flow_indir_dev_info *info;
+
+ info = find_indir_dev(data);
+ if (!info)
+ return -ENOENT;
+
+ list_del(&info->list);
+
+ kfree(info);
+ return 0;
+}
+
+int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch,
enum tc_setup_type type, void *data,
struct flow_block_offload *bo,
void (*cleanup)(struct flow_block_cb *block_cb))
@@ -471,6 +552,12 @@ int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch,
struct flow_indr_dev *this;
mutex_lock(&flow_indr_block_lock);
+
+ if (bo->command == FLOW_BLOCK_BIND)
+ indir_dev_add(data, dev, sch, type, cleanup, bo);
+ else if (bo->command == FLOW_BLOCK_UNBIND)
+ indir_dev_remove(data);
+
list_for_each_entry(this, &flow_block_indr_dev_list, list)
this->cb(dev, sch, this->cb_priv, type, bo, data, cleanup);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index dd4659246405..7266571d5c7e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2601,6 +2601,7 @@ static int do_setlink(const struct sk_buff *skb,
return err;
if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_TARGET_NETNSID]) {
+ const char *pat = ifname && ifname[0] ? ifname : NULL;
struct net *net = rtnl_link_get_net_capable(skb, dev_net(dev),
tb, CAP_NET_ADMIN);
if (IS_ERR(net)) {
@@ -2608,7 +2609,7 @@ static int do_setlink(const struct sk_buff *skb,
goto errout;
}
- err = dev_change_net_namespace(dev, net, ifname);
+ err = dev_change_net_namespace(dev, net, pat);
put_net(net);
if (err)
goto errout;
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 9cc9d1ee6cdb..c5c1d2b8045e 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -41,9 +41,9 @@ extern bool dccp_debug;
#define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a)
#define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a)
#else
-#define dccp_pr_debug(format, a...)
-#define dccp_pr_debug_cat(format, a...)
-#define dccp_debug(format, a...)
+#define dccp_pr_debug(format, a...) do {} while (0)
+#define dccp_pr_debug_cat(format, a...) do {} while (0)
+#define dccp_debug(format, a...) do {} while (0)
#endif
extern struct inet_hashinfo dccp_hashinfo;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 68ff19af195c..97b402b2d6fb 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -7,6 +7,7 @@
* the information ethtool needs.
*/
+#include <linux/compat.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/capability.h>
@@ -807,6 +808,120 @@ out:
return ret;
}
+static noinline_for_stack int
+ethtool_rxnfc_copy_from_compat(struct ethtool_rxnfc *rxnfc,
+ const struct compat_ethtool_rxnfc __user *useraddr,
+ size_t size)
+{
+ struct compat_ethtool_rxnfc crxnfc = {};
+
+ /* We expect there to be holes between fs.m_ext and
+ * fs.ring_cookie and at the end of fs, but nowhere else.
+ * On non-x86, no conversion should be needed.
+ */
+ BUILD_BUG_ON(!IS_ENABLED(CONFIG_X86_64) &&
+ sizeof(struct compat_ethtool_rxnfc) !=
+ sizeof(struct ethtool_rxnfc));
+ BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) +
+ sizeof(useraddr->fs.m_ext) !=
+ offsetof(struct ethtool_rxnfc, fs.m_ext) +
+ sizeof(rxnfc->fs.m_ext));
+ BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.location) -
+ offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) !=
+ offsetof(struct ethtool_rxnfc, fs.location) -
+ offsetof(struct ethtool_rxnfc, fs.ring_cookie));
+
+ if (copy_from_user(&crxnfc, useraddr, min(size, sizeof(crxnfc))))
+ return -EFAULT;
+
+ *rxnfc = (struct ethtool_rxnfc) {
+ .cmd = crxnfc.cmd,
+ .flow_type = crxnfc.flow_type,
+ .data = crxnfc.data,
+ .fs = {
+ .flow_type = crxnfc.fs.flow_type,
+ .h_u = crxnfc.fs.h_u,
+ .h_ext = crxnfc.fs.h_ext,
+ .m_u = crxnfc.fs.m_u,
+ .m_ext = crxnfc.fs.m_ext,
+ .ring_cookie = crxnfc.fs.ring_cookie,
+ .location = crxnfc.fs.location,
+ },
+ .rule_cnt = crxnfc.rule_cnt,
+ };
+
+ return 0;
+}
+
+static int ethtool_rxnfc_copy_from_user(struct ethtool_rxnfc *rxnfc,
+ const void __user *useraddr,
+ size_t size)
+{
+ if (compat_need_64bit_alignment_fixup())
+ return ethtool_rxnfc_copy_from_compat(rxnfc, useraddr, size);
+
+ if (copy_from_user(rxnfc, useraddr, size))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int ethtool_rxnfc_copy_to_compat(void __user *useraddr,
+ const struct ethtool_rxnfc *rxnfc,
+ size_t size, const u32 *rule_buf)
+{
+ struct compat_ethtool_rxnfc crxnfc;
+
+ memset(&crxnfc, 0, sizeof(crxnfc));
+ crxnfc = (struct compat_ethtool_rxnfc) {
+ .cmd = rxnfc->cmd,
+ .flow_type = rxnfc->flow_type,
+ .data = rxnfc->data,
+ .fs = {
+ .flow_type = rxnfc->fs.flow_type,
+ .h_u = rxnfc->fs.h_u,
+ .h_ext = rxnfc->fs.h_ext,
+ .m_u = rxnfc->fs.m_u,
+ .m_ext = rxnfc->fs.m_ext,
+ .ring_cookie = rxnfc->fs.ring_cookie,
+ .location = rxnfc->fs.location,
+ },
+ .rule_cnt = rxnfc->rule_cnt,
+ };
+
+ if (copy_to_user(useraddr, &crxnfc, min(size, sizeof(crxnfc))))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int ethtool_rxnfc_copy_to_user(void __user *useraddr,
+ const struct ethtool_rxnfc *rxnfc,
+ size_t size, const u32 *rule_buf)
+{
+ int ret;
+
+ if (compat_need_64bit_alignment_fixup()) {
+ ret = ethtool_rxnfc_copy_to_compat(useraddr, rxnfc, size,
+ rule_buf);
+ useraddr += offsetof(struct compat_ethtool_rxnfc, rule_locs);
+ } else {
+ ret = copy_to_user(useraddr, &rxnfc, size);
+ useraddr += offsetof(struct ethtool_rxnfc, rule_locs);
+ }
+
+ if (ret)
+ return -EFAULT;
+
+ if (rule_buf) {
+ if (copy_to_user(useraddr, rule_buf,
+ rxnfc->rule_cnt * sizeof(u32)))
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
u32 cmd, void __user *useraddr)
{
@@ -825,7 +940,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
info_size = (offsetof(struct ethtool_rxnfc, data) +
sizeof(info.data));
- if (copy_from_user(&info, useraddr, info_size))
+ if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
return -EFAULT;
rc = dev->ethtool_ops->set_rxnfc(dev, &info);
@@ -833,7 +948,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
return rc;
if (cmd == ETHTOOL_SRXCLSRLINS &&
- copy_to_user(useraddr, &info, info_size))
+ ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, NULL))
return -EFAULT;
return 0;
@@ -859,7 +974,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
info_size = (offsetof(struct ethtool_rxnfc, data) +
sizeof(info.data));
- if (copy_from_user(&info, useraddr, info_size))
+ if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
return -EFAULT;
/* If FLOW_RSS was requested then user-space must be using the
@@ -867,7 +982,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
*/
if (cmd == ETHTOOL_GRXFH && info.flow_type & FLOW_RSS) {
info_size = sizeof(info);
- if (copy_from_user(&info, useraddr, info_size))
+ if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
return -EFAULT;
/* Since malicious users may modify the original data,
* we need to check whether FLOW_RSS is still requested.
@@ -893,18 +1008,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
if (ret < 0)
goto err_out;
- ret = -EFAULT;
- if (copy_to_user(useraddr, &info, info_size))
- goto err_out;
-
- if (rule_buf) {
- useraddr += offsetof(struct ethtool_rxnfc, rule_locs);
- if (copy_to_user(useraddr, rule_buf,
- info.rule_cnt * sizeof(u32)))
- goto err_out;
- }
- ret = 0;
-
+ ret = ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, rule_buf);
err_out:
kfree(rule_buf);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 00576bae183d..0c321996c6eb 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2720,6 +2720,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u
rv = 1;
} else if (im) {
if (src_addr) {
+ spin_lock_bh(&im->lock);
for (psf = im->sources; psf; psf = psf->sf_next) {
if (psf->sf_inaddr == src_addr)
break;
@@ -2730,6 +2731,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u
im->sfcount[MCAST_EXCLUDE];
else
rv = im->sfcount[MCAST_EXCLUDE] != 0;
+ spin_unlock_bh(&im->lock);
} else
rv = 1; /* unspecified source; tentatively allow */
}
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index e70291748889..a0829495b211 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -468,6 +468,8 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
static int gre_handle_offloads(struct sk_buff *skb, bool csum)
{
+ if (csum && skb_checksum_start(skb) < skb->data)
+ return -EINVAL;
return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE);
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 560d5dc43562..10d4cde31c6b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -445,8 +445,9 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
{
BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) !=
offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr));
- memcpy(&iph->saddr, &fl4->saddr,
- sizeof(fl4->saddr) + sizeof(fl4->daddr));
+
+ iph->saddr = fl4->saddr;
+ iph->daddr = fl4->daddr;
}
/* Note: skb->sk can be different from sk, in case of tunnels */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e15c1d8b7c8d..ce787c386793 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -610,28 +610,35 @@ static void fnhe_flush_routes(struct fib_nh_exception *fnhe)
}
}
-static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
+static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash)
{
- struct fib_nh_exception *fnhe, *oldest;
+ struct fib_nh_exception __rcu **fnhe_p, **oldest_p;
+ struct fib_nh_exception *fnhe, *oldest = NULL;
- oldest = rcu_dereference(hash->chain);
- for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe;
- fnhe = rcu_dereference(fnhe->fnhe_next)) {
- if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp))
+ for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) {
+ fnhe = rcu_dereference_protected(*fnhe_p,
+ lockdep_is_held(&fnhe_lock));
+ if (!fnhe)
+ break;
+ if (!oldest ||
+ time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) {
oldest = fnhe;
+ oldest_p = fnhe_p;
+ }
}
fnhe_flush_routes(oldest);
- return oldest;
+ *oldest_p = oldest->fnhe_next;
+ kfree_rcu(oldest, rcu);
}
-static inline u32 fnhe_hashfun(__be32 daddr)
+static u32 fnhe_hashfun(__be32 daddr)
{
- static u32 fnhe_hashrnd __read_mostly;
- u32 hval;
+ static siphash_key_t fnhe_hash_key __read_mostly;
+ u64 hval;
- net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd));
- hval = jhash_1word((__force u32)daddr, fnhe_hashrnd);
- return hash_32(hval, FNHE_HASH_SHIFT);
+ net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key));
+ hval = siphash_1u32((__force u32)daddr, &fnhe_hash_key);
+ return hash_64(hval, FNHE_HASH_SHIFT);
}
static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe)
@@ -700,16 +707,21 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
if (rt)
fill_route_from_fnhe(rt, fnhe);
} else {
- if (depth > FNHE_RECLAIM_DEPTH)
- fnhe = fnhe_oldest(hash);
- else {
- fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC);
- if (!fnhe)
- goto out_unlock;
-
- fnhe->fnhe_next = hash->chain;
- rcu_assign_pointer(hash->chain, fnhe);
+ /* Randomize max depth to avoid some side channels attacks. */
+ int max_depth = FNHE_RECLAIM_DEPTH +
+ prandom_u32_max(FNHE_RECLAIM_DEPTH);
+
+ while (depth > max_depth) {
+ fnhe_remove_oldest(hash);
+ depth--;
}
+
+ fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC);
+ if (!fnhe)
+ goto out_unlock;
+
+ fnhe->fnhe_next = hash->chain;
+
fnhe->fnhe_genid = genid;
fnhe->fnhe_daddr = daddr;
fnhe->fnhe_gw = gw;
@@ -717,6 +729,8 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
fnhe->fnhe_mtu_locked = lock;
fnhe->fnhe_expires = max(1UL, expires);
+ rcu_assign_pointer(hash->chain, fnhe);
+
/* Exception created; mark the cached routes for the nexthop
* stale, so anyone caching it rechecks if this exception
* applies to them.
@@ -3064,7 +3078,7 @@ static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst,
udph = skb_put_zero(skb, sizeof(struct udphdr));
udph->source = sport;
udph->dest = dport;
- udph->len = sizeof(struct udphdr);
+ udph->len = htons(sizeof(struct udphdr));
udph->check = 0;
break;
}
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index d49709ba8e16..107111984384 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -379,8 +379,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
return NULL;
}
- if (syn_data &&
- tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD))
+ if (tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD))
goto fastopen;
if (foc->len == 0) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 04e259a04443..71395e745bc5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2417,6 +2417,7 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
static void *tcp_seek_last_pos(struct seq_file *seq)
{
struct tcp_iter_state *st = seq->private;
+ int bucket = st->bucket;
int offset = st->offset;
int orig_num = st->num;
void *rc = NULL;
@@ -2427,7 +2428,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
break;
st->state = TCP_SEQ_STATE_LISTENING;
rc = listening_get_next(seq, NULL);
- while (offset-- && rc)
+ while (offset-- && rc && bucket == st->bucket)
rc = listening_get_next(seq, rc);
if (rc)
break;
@@ -2438,7 +2439,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
if (st->bucket > tcp_hashinfo.ehash_mask)
break;
rc = established_get_first(seq);
- while (offset-- && rc)
+ while (offset-- && rc && bucket == st->bucket)
rc = established_get_next(seq, rc);
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 62db3c98424b..168a7b4d957a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -41,6 +41,7 @@
#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <linux/jhash.h>
+#include <linux/siphash.h>
#include <net/net_namespace.h>
#include <net/snmp.h>
#include <net/ipv6.h>
@@ -1482,17 +1483,24 @@ static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket)
static u32 rt6_exception_hash(const struct in6_addr *dst,
const struct in6_addr *src)
{
- static u32 seed __read_mostly;
- u32 val;
+ static siphash_key_t rt6_exception_key __read_mostly;
+ struct {
+ struct in6_addr dst;
+ struct in6_addr src;
+ } __aligned(SIPHASH_ALIGNMENT) combined = {
+ .dst = *dst,
+ };
+ u64 val;
- net_get_random_once(&seed, sizeof(seed));
- val = jhash2((const u32 *)dst, sizeof(*dst)/sizeof(u32), seed);
+ net_get_random_once(&rt6_exception_key, sizeof(rt6_exception_key));
#ifdef CONFIG_IPV6_SUBTREES
if (src)
- val = jhash2((const u32 *)src, sizeof(*src)/sizeof(u32), val);
+ combined.src = *src;
#endif
- return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT);
+ val = siphash(&combined, sizeof(combined), &rt6_exception_key);
+
+ return hash_64(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT);
}
/* Helper function to find the cached rt in the hash table
@@ -1647,6 +1655,7 @@ static int rt6_insert_exception(struct rt6_info *nrt,
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
struct fib6_nh *nh = res->nh;
+ int max_depth;
int err = 0;
spin_lock_bh(&rt6_exception_lock);
@@ -1701,7 +1710,9 @@ static int rt6_insert_exception(struct rt6_info *nrt,
bucket->depth++;
net->ipv6.rt6_stats->fib_rt_cache++;
- if (bucket->depth > FIB6_MAX_DEPTH)
+ /* Randomize max depth to avoid some side channels attacks. */
+ max_depth = FIB6_MAX_DEPTH + prandom_u32_max(FIB6_MAX_DEPTH);
+ while (bucket->depth > max_depth)
rt6_exception_remove_oldest(bucket);
out:
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 30589b4c09da..3a15ef8dd322 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -2000,9 +2000,16 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
netdev_set_default_ethtool_ops(ndev, &ieee80211_ethtool_ops);
- /* MTU range: 256 - 2304 */
+ /* MTU range is normally 256 - 2304, where the upper limit is
+ * the maximum MSDU size. Monitor interfaces send and receive
+ * MPDU and A-MSDU frames which may be much larger so we do
+ * not impose an upper limit in that case.
+ */
ndev->min_mtu = 256;
- ndev->max_mtu = local->hw.max_mtu;
+ if (type == NL80211_IFTYPE_MONITOR)
+ ndev->max_mtu = 0;
+ else
+ ndev->max_mtu = local->hw.max_mtu;
ret = register_netdevice(ndev);
if (ret) {
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 20b3581a1c43..673ad3cf2c3a 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3229,7 +3229,9 @@ static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata,
if (info->control.flags & IEEE80211_TX_CTRL_AMSDU)
return true;
- if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr)))
+ if (!ieee80211_amsdu_realloc_pad(local, skb,
+ sizeof(*amsdu_hdr) +
+ local->hw.extra_tx_headroom))
return false;
data = skb_push(skb, sizeof(*amsdu_hdr));
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f9f2af26ccb3..54430a34d2f6 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -66,22 +66,17 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash);
struct conntrack_gc_work {
struct delayed_work dwork;
- u32 last_bucket;
+ u32 next_bucket;
bool exiting;
bool early_drop;
- long next_gc_run;
};
static __read_mostly struct kmem_cache *nf_conntrack_cachep;
static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);
static __read_mostly bool nf_conntrack_locks_all;
-/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */
-#define GC_MAX_BUCKETS_DIV 128u
-/* upper bound of full table scan */
-#define GC_MAX_SCAN_JIFFIES (16u * HZ)
-/* desired ratio of entries found to be expired */
-#define GC_EVICT_RATIO 50u
+#define GC_SCAN_INTERVAL (120u * HZ)
+#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10)
static struct conntrack_gc_work conntrack_gc_work;
@@ -1352,17 +1347,13 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct)
static void gc_worker(struct work_struct *work)
{
- unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u);
- unsigned int i, goal, buckets = 0, expired_count = 0;
- unsigned int nf_conntrack_max95 = 0;
+ unsigned long end_time = jiffies + GC_SCAN_MAX_DURATION;
+ unsigned int i, hashsz, nf_conntrack_max95 = 0;
+ unsigned long next_run = GC_SCAN_INTERVAL;
struct conntrack_gc_work *gc_work;
- unsigned int ratio, scanned = 0;
- unsigned long next_run;
-
gc_work = container_of(work, struct conntrack_gc_work, dwork.work);
- goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV;
- i = gc_work->last_bucket;
+ i = gc_work->next_bucket;
if (gc_work->early_drop)
nf_conntrack_max95 = nf_conntrack_max / 100u * 95u;
@@ -1370,22 +1361,21 @@ static void gc_worker(struct work_struct *work)
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_head *ct_hash;
struct hlist_nulls_node *n;
- unsigned int hashsz;
struct nf_conn *tmp;
- i++;
rcu_read_lock();
nf_conntrack_get_ht(&ct_hash, &hashsz);
- if (i >= hashsz)
- i = 0;
+ if (i >= hashsz) {
+ rcu_read_unlock();
+ break;
+ }
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) {
struct net *net;
tmp = nf_ct_tuplehash_to_ctrack(h);
- scanned++;
if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) {
nf_ct_offload_timeout(tmp);
continue;
@@ -1393,7 +1383,6 @@ static void gc_worker(struct work_struct *work)
if (nf_ct_is_expired(tmp)) {
nf_ct_gc_expired(tmp);
- expired_count++;
continue;
}
@@ -1425,7 +1414,14 @@ static void gc_worker(struct work_struct *work)
*/
rcu_read_unlock();
cond_resched();
- } while (++buckets < goal);
+ i++;
+
+ if (time_after(jiffies, end_time) && i < hashsz) {
+ gc_work->next_bucket = i;
+ next_run = 0;
+ break;
+ }
+ } while (i < hashsz);
if (gc_work->exiting)
return;
@@ -1436,40 +1432,17 @@ static void gc_worker(struct work_struct *work)
*
* This worker is only here to reap expired entries when system went
* idle after a busy period.
- *
- * The heuristics below are supposed to balance conflicting goals:
- *
- * 1. Minimize time until we notice a stale entry
- * 2. Maximize scan intervals to not waste cycles
- *
- * Normally, expire ratio will be close to 0.
- *
- * As soon as a sizeable fraction of the entries have expired
- * increase scan frequency.
*/
- ratio = scanned ? expired_count * 100 / scanned : 0;
- if (ratio > GC_EVICT_RATIO) {
- gc_work->next_gc_run = min_interval;
- } else {
- unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV;
-
- BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0);
-
- gc_work->next_gc_run += min_interval;
- if (gc_work->next_gc_run > max)
- gc_work->next_gc_run = max;
+ if (next_run) {
+ gc_work->early_drop = false;
+ gc_work->next_bucket = 0;
}
-
- next_run = gc_work->next_gc_run;
- gc_work->last_bucket = i;
- gc_work->early_drop = false;
queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run);
}
static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
{
INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker);
- gc_work->next_gc_run = HZ;
gc_work->exiting = false;
}
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 92047cea3c17..a6b654b028dd 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -940,6 +940,7 @@ static void nf_flow_table_block_offload_init(struct flow_block_offload *bo,
bo->command = cmd;
bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
bo->extack = extack;
+ bo->cb_list_head = &flowtable->flow_block.cb_list;
INIT_LIST_HEAD(&bo->cb_list);
}
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index e34d05cc5754..2b5f97e1d40b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4115,6 +4115,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
struct nft_table *table;
struct nft_set *set;
struct nft_ctx ctx;
+ size_t alloc_size;
char *name;
u64 size;
u64 timeout;
@@ -4263,8 +4264,10 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
size = 0;
if (ops->privsize != NULL)
size = ops->privsize(nla, &desc);
-
- set = kvzalloc(sizeof(*set) + size + udlen, GFP_KERNEL);
+ alloc_size = sizeof(*set) + size + udlen;
+ if (alloc_size < size)
+ return -ENOMEM;
+ set = kvzalloc(alloc_size, GFP_KERNEL);
if (!set)
return -ENOMEM;
@@ -4277,15 +4280,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
err = nf_tables_set_alloc_name(&ctx, set, name);
kfree(name);
if (err < 0)
- goto err_set_alloc_name;
-
- if (nla[NFTA_SET_EXPR]) {
- expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]);
- if (IS_ERR(expr)) {
- err = PTR_ERR(expr);
- goto err_set_alloc_name;
- }
- }
+ goto err_set_name;
udata = NULL;
if (udlen) {
@@ -4296,21 +4291,19 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
INIT_LIST_HEAD(&set->bindings);
set->table = table;
write_pnet(&set->net, net);
- set->ops = ops;
+ set->ops = ops;
set->ktype = ktype;
- set->klen = desc.klen;
+ set->klen = desc.klen;
set->dtype = dtype;
set->objtype = objtype;
- set->dlen = desc.dlen;
- set->expr = expr;
+ set->dlen = desc.dlen;
set->flags = flags;
- set->size = desc.size;
+ set->size = desc.size;
set->policy = policy;
- set->udlen = udlen;
- set->udata = udata;
+ set->udlen = udlen;
+ set->udata = udata;
set->timeout = timeout;
set->gc_int = gc_int;
- set->handle = nf_tables_alloc_handle(table);
set->field_count = desc.field_count;
for (i = 0; i < desc.field_count; i++)
@@ -4320,20 +4313,32 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
if (err < 0)
goto err_set_init;
+ if (nla[NFTA_SET_EXPR]) {
+ expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]);
+ if (IS_ERR(expr)) {
+ err = PTR_ERR(expr);
+ goto err_set_expr_alloc;
+ }
+
+ set->expr = expr;
+ }
+
+ set->handle = nf_tables_alloc_handle(table);
+
err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
if (err < 0)
- goto err_set_trans;
+ goto err_set_expr_alloc;
list_add_tail_rcu(&set->list, &table->sets);
table->use++;
return 0;
-err_set_trans:
+err_set_expr_alloc:
+ if (set->expr)
+ nft_expr_destroy(&ctx, set->expr);
+
ops->destroy(set);
err_set_init:
- if (expr)
- nft_expr_destroy(&ctx, expr);
-err_set_alloc_name:
kfree(set->name);
err_set_name:
kvfree(set);
@@ -5145,6 +5150,24 @@ static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx,
kfree(elem);
}
+static int nft_set_elem_expr_setup(struct nft_ctx *ctx,
+ const struct nft_set_ext *ext,
+ struct nft_expr *expr)
+{
+ struct nft_expr *elem_expr = nft_set_ext_expr(ext);
+ int err;
+
+ if (expr == NULL)
+ return 0;
+
+ err = nft_expr_clone(elem_expr, expr);
+ if (err < 0)
+ return -ENOMEM;
+
+ nft_expr_destroy(ctx, expr);
+ return 0;
+}
+
static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
const struct nlattr *attr, u32 nlmsg_flags)
{
@@ -5347,15 +5370,17 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
*nft_set_ext_obj(ext) = obj;
obj->use++;
}
- if (expr) {
- memcpy(nft_set_ext_expr(ext), expr, expr->ops->size);
- kfree(expr);
- expr = NULL;
- }
+
+ err = nft_set_elem_expr_setup(ctx, ext, expr);
+ if (err < 0)
+ goto err_elem_expr;
+ expr = NULL;
trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
- if (trans == NULL)
- goto err_trans;
+ if (trans == NULL) {
+ err = -ENOMEM;
+ goto err_elem_expr;
+ }
ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK;
err = set->ops->insert(ctx->net, set, &elem, &ext2);
@@ -5399,7 +5424,7 @@ err_set_full:
set->ops->remove(ctx->net, set, &elem);
err_element_clash:
kfree(trans);
-err_trans:
+err_elem_expr:
if (obj)
obj->use--;
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 9ce776175214..e5fcbb0e4b8e 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -323,6 +323,7 @@ static void nft_flow_block_offload_init(struct flow_block_offload *bo,
bo->command = cmd;
bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
bo->extack = extack;
+ bo->cb_list_head = &basechain->flow_block.cb_list;
INIT_LIST_HEAD(&bo->cb_list);
}
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index d7083bcb20e8..858c8d4d659a 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -604,7 +604,7 @@ static u64 nft_hash_privsize(const struct nlattr * const nla[],
const struct nft_set_desc *desc)
{
return sizeof(struct nft_hash) +
- nft_hash_buckets(desc->size) * sizeof(struct hlist_head);
+ (u64)nft_hash_buckets(desc->size) * sizeof(struct hlist_head);
}
static int nft_hash_init(const struct nft_set *set,
@@ -644,8 +644,8 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
return false;
est->size = sizeof(struct nft_hash) +
- nft_hash_buckets(desc->size) * sizeof(struct hlist_head) +
- desc->size * sizeof(struct nft_hash_elem);
+ (u64)nft_hash_buckets(desc->size) * sizeof(struct hlist_head) +
+ (u64)desc->size * sizeof(struct nft_hash_elem);
est->lookup = NFT_SET_CLASS_O_1;
est->space = NFT_SET_CLASS_O_N;
@@ -662,8 +662,8 @@ static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features
return false;
est->size = sizeof(struct nft_hash) +
- nft_hash_buckets(desc->size) * sizeof(struct hlist_head) +
- desc->size * sizeof(struct nft_hash_elem);
+ (u64)nft_hash_buckets(desc->size) * sizeof(struct hlist_head) +
+ (u64)desc->size * sizeof(struct nft_hash_elem);
est->lookup = NFT_SET_CLASS_O_1;
est->space = NFT_SET_CLASS_O_N;
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index 4f50a64315cf..f3f1df1b0f8e 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -144,8 +144,8 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
return -ENOMEM;
doi_def->map.std = kzalloc(sizeof(*doi_def->map.std), GFP_KERNEL);
if (doi_def->map.std == NULL) {
- ret_val = -ENOMEM;
- goto add_std_failure;
+ kfree(doi_def);
+ return -ENOMEM;
}
doi_def->type = CIPSO_V4_MAP_TRANS;
@@ -187,14 +187,14 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
}
doi_def->map.std->lvl.local = kcalloc(doi_def->map.std->lvl.local_size,
sizeof(u32),
- GFP_KERNEL);
+ GFP_KERNEL | __GFP_NOWARN);
if (doi_def->map.std->lvl.local == NULL) {
ret_val = -ENOMEM;
goto add_std_failure;
}
doi_def->map.std->lvl.cipso = kcalloc(doi_def->map.std->lvl.cipso_size,
sizeof(u32),
- GFP_KERNEL);
+ GFP_KERNEL | __GFP_NOWARN);
if (doi_def->map.std->lvl.cipso == NULL) {
ret_val = -ENOMEM;
goto add_std_failure;
@@ -263,7 +263,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
doi_def->map.std->cat.local = kcalloc(
doi_def->map.std->cat.local_size,
sizeof(u32),
- GFP_KERNEL);
+ GFP_KERNEL | __GFP_NOWARN);
if (doi_def->map.std->cat.local == NULL) {
ret_val = -ENOMEM;
goto add_std_failure;
@@ -271,7 +271,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
doi_def->map.std->cat.cipso = kcalloc(
doi_def->map.std->cat.cipso_size,
sizeof(u32),
- GFP_KERNEL);
+ GFP_KERNEL | __GFP_NOWARN);
if (doi_def->map.std->cat.cipso == NULL) {
ret_val = -ENOMEM;
goto add_std_failure;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index e527f5686e2b..8434da3c0487 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2537,13 +2537,15 @@ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid,
/* errors reported via destination sk->sk_err, but propagate
* delivery errors if NETLINK_BROADCAST_ERROR flag is set */
err = nlmsg_multicast(sk, skb, exclude_portid, group, flags);
+ if (err == -ESRCH)
+ err = 0;
}
if (report) {
int err2;
err2 = nlmsg_unicast(sk, skb, portid);
- if (!err || err == -ESRCH)
+ if (!err)
err = err2;
}
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 82d801f063b7..1c05d4bef331 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -503,6 +503,7 @@ void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto)
}
skb->dev = vport->dev;
+ skb->tstamp = 0;
vport->ops->send(skb);
return;
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 6826558483f9..56cffbfa000b 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -486,7 +486,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
goto err;
}
- if (len != ALIGN(size, 4) + hdrlen)
+ if (!size || len != ALIGN(size, 4) + hdrlen)
goto err;
if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA &&
diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c
index 9b6ffff72f2d..28c1b0022178 100644
--- a/net/rds/ib_frmr.c
+++ b/net/rds/ib_frmr.c
@@ -131,9 +131,9 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr)
cpu_relax();
}
- ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_len,
+ ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len,
&off, PAGE_SIZE);
- if (unlikely(ret != ibmr->sg_len))
+ if (unlikely(ret != ibmr->sg_dma_len))
return ret < 0 ? ret : -EINVAL;
if (cmpxchg(&frmr->fr_state,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 31ac76a9189e..8073657a0fd2 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -634,6 +634,7 @@ static void tcf_block_offload_init(struct flow_block_offload *bo,
bo->block_shared = shared;
bo->extack = extack;
bo->sch = sch;
+ bo->cb_list_head = &flow_block->cb_list;
INIT_LIST_HEAD(&bo->cb_list);
}
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 5c15968b5155..c2c37ffd94f2 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -720,7 +720,7 @@ static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb,
skip_hash:
if (flow_override)
flow_hash = flow_override - 1;
- else if (use_skbhash)
+ else if (use_skbhash && (flow_mode & CAKE_FLOW_FLOWS))
flow_hash = skb->hash;
if (host_override) {
dsthost_hash = host_override - 1;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 53d45e029c36..4a78fcf5d4f9 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1614,7 +1614,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack);
if (err) {
kfree(cl);
- return err;
+ goto failure;
}
if (tca[TCA_RATE]) {
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index c1e84d1eeaba..c76701ac35ab 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -660,6 +660,13 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
sch_tree_lock(sch);
q->nbands = nbands;
+ for (i = nstrict; i < q->nstrict; i++) {
+ INIT_LIST_HEAD(&q->classes[i].alist);
+ if (q->classes[i].qdisc->q.qlen) {
+ list_add_tail(&q->classes[i].alist, &q->active);
+ q->classes[i].deficit = quanta[i];
+ }
+ }
q->nstrict = nstrict;
memcpy(q->prio2band, priomap, sizeof(priomap));
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 00853065dfa0..cb5e5220da55 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1502,7 +1502,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
taprio_set_picos_per_byte(dev, q);
if (mqprio) {
- netdev_set_num_tc(dev, mqprio->num_tc);
+ err = netdev_set_num_tc(dev, mqprio->num_tc);
+ if (err)
+ goto free_sched;
for (i = 0; i < mqprio->num_tc; i++)
netdev_set_tc_queue(dev, i,
mqprio->count[i],
diff --git a/net/socket.c b/net/socket.c
index 002d5952ae5d..d52c265ad449 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1062,7 +1062,7 @@ static long sock_do_ioctl(struct net *net, struct socket *sock,
rtnl_unlock();
if (!err && copy_to_user(argp, &ifc, sizeof(struct ifconf)))
err = -EFAULT;
- } else {
+ } else if (is_socket_ioctl_cmd(cmd)) {
struct ifreq ifr;
bool need_copyout;
if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
@@ -1071,6 +1071,8 @@ static long sock_do_ioctl(struct net *net, struct socket *sock,
if (!err && need_copyout)
if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
return -EFAULT;
+ } else {
+ err = -ENOTTY;
}
return err;
}
@@ -3110,128 +3112,6 @@ static int compat_dev_ifconf(struct net *net, struct compat_ifconf __user *uifc3
return 0;
}
-static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32)
-{
- struct compat_ethtool_rxnfc __user *compat_rxnfc;
- bool convert_in = false, convert_out = false;
- size_t buf_size = 0;
- struct ethtool_rxnfc __user *rxnfc = NULL;
- struct ifreq ifr;
- u32 rule_cnt = 0, actual_rule_cnt;
- u32 ethcmd;
- u32 data;
- int ret;
-
- if (get_user(data, &ifr32->ifr_ifru.ifru_data))
- return -EFAULT;
-
- compat_rxnfc = compat_ptr(data);
-
- if (get_user(ethcmd, &compat_rxnfc->cmd))
- return -EFAULT;
-
- /* Most ethtool structures are defined without padding.
- * Unfortunately struct ethtool_rxnfc is an exception.
- */
- switch (ethcmd) {
- default:
- break;
- case ETHTOOL_GRXCLSRLALL:
- /* Buffer size is variable */
- if (get_user(rule_cnt, &compat_rxnfc->rule_cnt))
- return -EFAULT;
- if (rule_cnt > KMALLOC_MAX_SIZE / sizeof(u32))
- return -ENOMEM;
- buf_size += rule_cnt * sizeof(u32);
- fallthrough;
- case ETHTOOL_GRXRINGS:
- case ETHTOOL_GRXCLSRLCNT:
- case ETHTOOL_GRXCLSRULE:
- case ETHTOOL_SRXCLSRLINS:
- convert_out = true;
- fallthrough;
- case ETHTOOL_SRXCLSRLDEL:
- buf_size += sizeof(struct ethtool_rxnfc);
- convert_in = true;
- rxnfc = compat_alloc_user_space(buf_size);
- break;
- }
-
- if (copy_from_user(&ifr.ifr_name, &ifr32->ifr_name, IFNAMSIZ))
- return -EFAULT;
-
- ifr.ifr_data = convert_in ? rxnfc : (void __user *)compat_rxnfc;
-
- if (convert_in) {
- /* We expect there to be holes between fs.m_ext and
- * fs.ring_cookie and at the end of fs, but nowhere else.
- */
- BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) +
- sizeof(compat_rxnfc->fs.m_ext) !=
- offsetof(struct ethtool_rxnfc, fs.m_ext) +
- sizeof(rxnfc->fs.m_ext));
- BUILD_BUG_ON(
- offsetof(struct compat_ethtool_rxnfc, fs.location) -
- offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) !=
- offsetof(struct ethtool_rxnfc, fs.location) -
- offsetof(struct ethtool_rxnfc, fs.ring_cookie));
-
- if (copy_in_user(rxnfc, compat_rxnfc,
- (void __user *)(&rxnfc->fs.m_ext + 1) -
- (void __user *)rxnfc) ||
- copy_in_user(&rxnfc->fs.ring_cookie,
- &compat_rxnfc->fs.ring_cookie,
- (void __user *)(&rxnfc->fs.location + 1) -
- (void __user *)&rxnfc->fs.ring_cookie))
- return -EFAULT;
- if (ethcmd == ETHTOOL_GRXCLSRLALL) {
- if (put_user(rule_cnt, &rxnfc->rule_cnt))
- return -EFAULT;
- } else if (copy_in_user(&rxnfc->rule_cnt,
- &compat_rxnfc->rule_cnt,
- sizeof(rxnfc->rule_cnt)))
- return -EFAULT;
- }
-
- ret = dev_ioctl(net, SIOCETHTOOL, &ifr, NULL);
- if (ret)
- return ret;
-
- if (convert_out) {
- if (copy_in_user(compat_rxnfc, rxnfc,
- (const void __user *)(&rxnfc->fs.m_ext + 1) -
- (const void __user *)rxnfc) ||
- copy_in_user(&compat_rxnfc->fs.ring_cookie,
- &rxnfc->fs.ring_cookie,
- (const void __user *)(&rxnfc->fs.location + 1) -
- (const void __user *)&rxnfc->fs.ring_cookie) ||
- copy_in_user(&compat_rxnfc->rule_cnt, &rxnfc->rule_cnt,
- sizeof(rxnfc->rule_cnt)))
- return -EFAULT;
-
- if (ethcmd == ETHTOOL_GRXCLSRLALL) {
- /* As an optimisation, we only copy the actual
- * number of rules that the underlying
- * function returned. Since Mallory might
- * change the rule count in user memory, we
- * check that it is less than the rule count
- * originally given (as the user buffer size),
- * which has been range-checked.
- */
- if (get_user(actual_rule_cnt, &rxnfc->rule_cnt))
- return -EFAULT;
- if (actual_rule_cnt < rule_cnt)
- rule_cnt = actual_rule_cnt;
- if (copy_in_user(&compat_rxnfc->rule_locs[0],
- &rxnfc->rule_locs[0],
- rule_cnt * sizeof(u32)))
- return -EFAULT;
- }
- }
-
- return 0;
-}
-
static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32)
{
compat_uptr_t uptr32;
@@ -3264,6 +3144,8 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd,
struct ifreq ifreq;
u32 data32;
+ if (!is_socket_ioctl_cmd(cmd))
+ return -ENOTTY;
if (copy_from_user(ifreq.ifr_name, u_ifreq32->ifr_name, IFNAMSIZ))
return -EFAULT;
if (get_user(data32, &u_ifreq32->ifr_data))
@@ -3386,8 +3268,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
return old_bridge_ioctl(argp);
case SIOCGIFCONF:
return compat_dev_ifconf(net, argp);
- case SIOCETHTOOL:
- return ethtool_ioctl(net, argp);
case SIOCWANDEV:
return compat_siocwandev(net, argp);
case SIOCGIFMAP:
@@ -3400,6 +3280,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD,
!COMPAT_USE_64BIT_TIME);
+ case SIOCETHTOOL:
case SIOCBONDSLAVEINFOQUERY:
case SIOCBONDINFOQUERY:
case SIOCSHWTSTAMP:
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 6dff64374bfe..e22f2d65457d 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1980,7 +1980,7 @@ gss_svc_init_net(struct net *net)
goto out2;
return 0;
out2:
- destroy_use_gss_proxy_proc_entry(net);
+ rsi_cache_destroy_net(net);
out1:
rsc_cache_destroy_net(net);
return rv;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 9a50764be916..8201531ce5d9 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -746,9 +746,9 @@ void xprt_force_disconnect(struct rpc_xprt *xprt)
/* Try to schedule an autoclose RPC call */
if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
queue_work(xprtiod_workqueue, &xprt->task_cleanup);
- else if (xprt->snd_task)
+ else if (xprt->snd_task && !test_bit(XPRT_SND_IS_COOKIE, &xprt->state))
rpc_wake_up_queued_task_set_status(&xprt->pending,
- xprt->snd_task, -ENOTCONN);
+ xprt->snd_task, -ENOTCONN);
spin_unlock(&xprt->transport_lock);
}
EXPORT_SYMBOL_GPL(xprt_force_disconnect);
@@ -837,12 +837,14 @@ bool xprt_lock_connect(struct rpc_xprt *xprt,
goto out;
if (xprt->snd_task != task)
goto out;
+ set_bit(XPRT_SND_IS_COOKIE, &xprt->state);
xprt->snd_task = cookie;
ret = true;
out:
spin_unlock(&xprt->transport_lock);
return ret;
}
+EXPORT_SYMBOL_GPL(xprt_lock_connect);
void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie)
{
@@ -852,12 +854,14 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie)
if (!test_bit(XPRT_LOCKED, &xprt->state))
goto out;
xprt->snd_task =NULL;
+ clear_bit(XPRT_SND_IS_COOKIE, &xprt->state);
xprt->ops->release_xprt(xprt, NULL);
xprt_schedule_autodisconnect(xprt);
out:
spin_unlock(&xprt->transport_lock);
wake_up_bit(&xprt->state, XPRT_LOCKED);
}
+EXPORT_SYMBOL_GPL(xprt_unlock_connect);
/**
* xprt_connect - schedule a transport connect operation
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index c26db0a37996..8e2368a0c2a2 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -249,12 +249,9 @@ xprt_rdma_connect_worker(struct work_struct *work)
xprt->stat.connect_start;
xprt_set_connected(xprt);
rc = -EAGAIN;
- } else {
- /* Force a call to xprt_rdma_close to clean up */
- spin_lock(&xprt->transport_lock);
- set_bit(XPRT_CLOSE_WAIT, &xprt->state);
- spin_unlock(&xprt->transport_lock);
- }
+ } else
+ rpcrdma_xprt_disconnect(r_xprt);
+ xprt_unlock_connect(xprt, r_xprt);
xprt_wake_pending_tasks(xprt, rc);
}
@@ -487,6 +484,8 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
struct rpcrdma_ep *ep = r_xprt->rx_ep;
unsigned long delay;
+ WARN_ON_ONCE(!xprt_lock_connect(xprt, task, r_xprt));
+
delay = 0;
if (ep && ep->re_connect_status != 0) {
delay = xprt_reconnect_delay(xprt);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 9c0f71e82d97..16c7758e7bf3 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1639,6 +1639,13 @@ static int xs_get_srcport(struct sock_xprt *transport)
return port;
}
+unsigned short get_srcport(struct rpc_xprt *xprt)
+{
+ struct sock_xprt *sock = container_of(xprt, struct sock_xprt, xprt);
+ return xs_sock_getport(sock->sock);
+}
+EXPORT_SYMBOL(get_srcport);
+
static unsigned short xs_next_srcport(struct sock_xprt *transport, unsigned short port)
{
if (transport->srcport != 0)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 4f9bd95b4eee..963047c57c27 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1511,7 +1511,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
if (unlikely(syn && !rc)) {
tipc_set_sk_state(sk, TIPC_CONNECTING);
- if (timeout) {
+ if (dlen && timeout) {
timeout = msecs_to_jiffies(timeout);
tipc_wait_for_connect(sock, &timeout);
}
@@ -1887,6 +1887,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
bool connected = !tipc_sk_type_connectionless(sk);
struct tipc_sock *tsk = tipc_sk(sk);
int rc, err, hlen, dlen, copy;
+ struct tipc_skb_cb *skb_cb;
struct sk_buff_head xmitq;
struct tipc_msg *hdr;
struct sk_buff *skb;
@@ -1910,6 +1911,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
if (unlikely(rc))
goto exit;
skb = skb_peek(&sk->sk_receive_queue);
+ skb_cb = TIPC_SKB_CB(skb);
hdr = buf_msg(skb);
dlen = msg_data_sz(hdr);
hlen = msg_hdr_sz(hdr);
@@ -1929,18 +1931,33 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
/* Capture data if non-error msg, otherwise just set return value */
if (likely(!err)) {
- copy = min_t(int, dlen, buflen);
- if (unlikely(copy != dlen))
- m->msg_flags |= MSG_TRUNC;
- rc = skb_copy_datagram_msg(skb, hlen, m, copy);
+ int offset = skb_cb->bytes_read;
+
+ copy = min_t(int, dlen - offset, buflen);
+ rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy);
+ if (unlikely(rc))
+ goto exit;
+ if (unlikely(offset + copy < dlen)) {
+ if (flags & MSG_EOR) {
+ if (!(flags & MSG_PEEK))
+ skb_cb->bytes_read = offset + copy;
+ } else {
+ m->msg_flags |= MSG_TRUNC;
+ skb_cb->bytes_read = 0;
+ }
+ } else {
+ if (flags & MSG_EOR)
+ m->msg_flags |= MSG_EOR;
+ skb_cb->bytes_read = 0;
+ }
} else {
copy = 0;
rc = 0;
- if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control)
+ if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control) {
rc = -ECONNRESET;
+ goto exit;
+ }
}
- if (unlikely(rc))
- goto exit;
/* Mark message as group event if applicable */
if (unlikely(grp_evt)) {
@@ -1963,9 +1980,10 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
tipc_node_distr_xmit(sock_net(sk), &xmitq);
}
- tsk_advance_rx_queue(sk);
+ if (!skb_cb->bytes_read)
+ tsk_advance_rx_queue(sk);
- if (likely(!connected))
+ if (likely(!connected) || skb_cb->bytes_read)
goto exit;
/* Send connection flow control advertisement when applicable */
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index 4d422447aadc..0814320472f1 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -250,7 +250,7 @@ static void ipcomp_free_tfms(struct crypto_comp * __percpu *tfms)
break;
}
- WARN_ON(!pos);
+ WARN_ON(list_entry_is_head(pos, &ipcomp_tfms_list, list));
if (--pos->users)
return;