summaryrefslogtreecommitdiff
path: root/include/net
diff options
context:
space:
mode:
Diffstat (limited to 'include/net')
-rw-r--r--include/net/addrconf.h29
-rw-r--r--include/net/ax25.h10
-rw-r--r--include/net/bluetooth/hci.h1
-rw-r--r--include/net/bluetooth/hci_core.h14
-rw-r--r--include/net/bluetooth/hci_sync.h1
-rw-r--r--include/net/bluetooth/l2cap.h3
-rw-r--r--include/net/busy_poll.h8
-rw-r--r--include/net/cfg80211.h75
-rw-r--r--include/net/devlink.h25
-rw-r--r--include/net/dropreason-core.h88
-rw-r--r--include/net/dsa.h6
-rw-r--r--include/net/dst.h11
-rw-r--r--include/net/genetlink.h6
-rw-r--r--include/net/gro.h3
-rw-r--r--include/net/inet_connection_sock.h2
-rw-r--r--include/net/inet_sock.h8
-rw-r--r--include/net/inet_timewait_sock.h4
-rw-r--r--include/net/inetpeer.h12
-rw-r--r--include/net/ip.h15
-rw-r--r--include/net/ipv6.h2
-rw-r--r--include/net/iucv/iucv.h30
-rw-r--r--include/net/l3mdev.h2
-rw-r--r--include/net/mac80211.h56
-rw-r--r--include/net/macsec.h4
-rw-r--r--include/net/net_namespace.h15
-rw-r--r--include/net/netdev_queues.h10
-rw-r--r--include/net/netfilter/nf_conntrack.h18
-rw-r--r--include/net/netfilter/nf_conntrack_ecache.h12
-rw-r--r--include/net/netfilter/nf_flow_table.h1
-rw-r--r--include/net/netfilter/nf_tables.h17
-rw-r--r--include/net/netfilter/nf_tproxy.h4
-rw-r--r--include/net/netlink.h44
-rw-r--r--include/net/netmem.h78
-rw-r--r--include/net/netns/ipv4.h1
-rw-r--r--include/net/page_pool/helpers.h84
-rw-r--r--include/net/page_pool/types.h12
-rw-r--r--include/net/pkt_cls.h17
-rw-r--r--include/net/route.h51
-rw-r--r--include/net/sch_generic.h15
-rw-r--r--include/net/scm.h12
-rw-r--r--include/net/sock.h35
-rw-r--r--include/net/strparser.h2
-rw-r--r--include/net/tcp.h24
-rw-r--r--include/net/tls.h3
-rw-r--r--include/net/vxlan.h1
-rw-r--r--include/net/xdp.h194
-rw-r--r--include/net/xdp_sock_drv.h43
-rw-r--r--include/net/xfrm.h60
-rw-r--r--include/net/xsk_buff_pool.h4
49 files changed, 915 insertions, 257 deletions
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 363dd63babe7..9e5e95988b9e 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -88,6 +88,23 @@ struct ifa6_config {
u16 scope;
};
+enum addr_type_t {
+ UNICAST_ADDR,
+ MULTICAST_ADDR,
+ ANYCAST_ADDR,
+};
+
+struct inet6_fill_args {
+ u32 portid;
+ u32 seq;
+ int event;
+ unsigned int flags;
+ int netnsid;
+ int ifindex;
+ enum addr_type_t type;
+ bool force_rt_scope_universe;
+};
+
int addrconf_init(void);
void addrconf_cleanup(void);
@@ -330,6 +347,11 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev)
return rcu_dereference_rtnl(dev->ip6_ptr);
}
+static inline struct inet6_dev *__in6_dev_get_rtnl_net(const struct net_device *dev)
+{
+ return rtnl_net_dereference(dev_net(dev), dev->ip6_ptr);
+}
+
/**
* __in6_dev_stats_get - get inet6_dev pointer for stats
* @dev: network device
@@ -525,4 +547,11 @@ int if6_proc_init(void);
void if6_proc_exit(void);
#endif
+int inet6_fill_ifmcaddr(struct sk_buff *skb,
+ const struct ifmcaddr6 *ifmca,
+ struct inet6_fill_args *args);
+
+int inet6_fill_ifacaddr(struct sk_buff *skb,
+ const struct ifacaddr6 *ifaca,
+ struct inet6_fill_args *args);
#endif
diff --git a/include/net/ax25.h b/include/net/ax25.h
index cb622d84cd0c..4ee141aae0a2 100644
--- a/include/net/ax25.h
+++ b/include/net/ax25.h
@@ -231,6 +231,7 @@ typedef struct ax25_dev {
#endif
refcount_t refcount;
bool device_up;
+ struct rcu_head rcu;
} ax25_dev;
typedef struct ax25_cb {
@@ -290,9 +291,8 @@ static inline void ax25_dev_hold(ax25_dev *ax25_dev)
static inline void ax25_dev_put(ax25_dev *ax25_dev)
{
- if (refcount_dec_and_test(&ax25_dev->refcount)) {
- kfree(ax25_dev);
- }
+ if (refcount_dec_and_test(&ax25_dev->refcount))
+ kfree_rcu(ax25_dev, rcu);
}
static inline __be16 ax25_type_trans(struct sk_buff *skb, struct net_device *dev)
{
@@ -335,9 +335,9 @@ void ax25_digi_invert(const ax25_digi *, ax25_digi *);
extern spinlock_t ax25_dev_lock;
#if IS_ENABLED(CONFIG_AX25)
-static inline ax25_dev *ax25_dev_ax25dev(struct net_device *dev)
+static inline ax25_dev *ax25_dev_ax25dev(const struct net_device *dev)
{
- return dev->ax25_ptr;
+ return rcu_dereference_rtnl(dev->ax25_ptr);
}
#endif
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 6203bd8663b7..0d51970d809f 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -438,7 +438,6 @@ enum {
HCI_FORCE_BREDR_SMP,
HCI_FORCE_STATIC_ADDR,
HCI_LL_RPA_RESOLUTION,
- HCI_ENABLE_LL_PRIVACY,
HCI_CMD_PENDING,
HCI_FORCE_NO_MITM,
HCI_QUALITY_REPORT,
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index ca22ead85dbe..f756fac95488 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -157,8 +157,9 @@ struct bdaddr_list_with_irk {
/* Bitmask of connection flags */
enum hci_conn_flags {
- HCI_CONN_FLAG_REMOTE_WAKEUP = 1,
- HCI_CONN_FLAG_DEVICE_PRIVACY = 2,
+ HCI_CONN_FLAG_REMOTE_WAKEUP = BIT(0),
+ HCI_CONN_FLAG_DEVICE_PRIVACY = BIT(1),
+ HCI_CONN_FLAG_ADDRESS_RESOLUTION = BIT(2),
};
typedef u8 hci_conn_flags_t;
@@ -632,7 +633,6 @@ struct hci_dev {
int (*post_init)(struct hci_dev *hdev);
int (*set_diag)(struct hci_dev *hdev, bool enable);
int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr);
- void (*cmd_timeout)(struct hci_dev *hdev);
void (*reset)(struct hci_dev *hdev);
bool (*wakeup)(struct hci_dev *hdev);
int (*set_quality_report)(struct hci_dev *hdev, bool enable);
@@ -1759,8 +1759,6 @@ int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr,
int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type);
int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr,
u8 type);
-int hci_bdaddr_list_del_with_flags(struct list_head *list, bdaddr_t *bdaddr,
- u8 type);
void hci_bdaddr_list_clear(struct list_head *list);
struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev,
@@ -1919,11 +1917,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
#define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY)
-/* Use LL Privacy based address resolution if supported */
-#define use_ll_privacy(dev) (ll_privacy_capable(dev) && \
- hci_dev_test_flag(dev, HCI_ENABLE_LL_PRIVACY))
-
-#define privacy_mode_capable(dev) (use_ll_privacy(dev) && \
+#define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \
(hdev->commands[39] & 0x04))
#define read_key_size_capable(dev) \
diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index f3052cb252ef..7e2cf0cca939 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -140,7 +140,6 @@ int hci_update_scan(struct hci_dev *hdev);
int hci_write_le_host_supported_sync(struct hci_dev *hdev, u8 le, u8 simul);
int hci_remove_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance,
struct sock *sk);
-int hci_remove_ext_adv_instance(struct hci_dev *hdev, u8 instance);
struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, bool ext,
struct sock *sk);
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index d9c767cf773d..9189354c568f 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -668,7 +668,7 @@ struct l2cap_conn {
struct l2cap_chan *smp;
struct list_head chan_l;
- struct mutex chan_lock;
+ struct mutex lock;
struct kref ref;
struct list_head users;
};
@@ -970,6 +970,7 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err);
void l2cap_send_conn_req(struct l2cap_chan *chan);
struct l2cap_conn *l2cap_conn_get(struct l2cap_conn *conn);
+struct l2cap_conn *l2cap_conn_hold_unless_zero(struct l2cap_conn *conn);
void l2cap_conn_put(struct l2cap_conn *conn);
int l2cap_register_user(struct l2cap_conn *conn, struct l2cap_user *user);
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index c858270141bc..c39a426ebf52 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -174,12 +174,4 @@ static inline void sk_mark_napi_id_once(struct sock *sk,
#endif
}
-static inline void sk_mark_napi_id_once_xdp(struct sock *sk,
- const struct xdp_buff *xdp)
-{
-#ifdef CONFIG_NET_RX_BUSY_POLL
- __sk_mark_napi_id_once(sk, xdp->rxq->napi_id);
-#endif
-}
-
#endif /* _LINUX_NET_BUSY_POLL_H */
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 27acf1292a5c..363d7dd2255a 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3023,6 +3023,10 @@ static inline const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 id)
*
* @bss: The BSS to authenticate with, the callee must obtain a reference
* to it if it needs to keep it.
+ * @supported_selectors: List of selectors that should be assumed to be
+ * supported by the station.
+ * SAE_H2E must be assumed supported if set to %NULL.
+ * @supported_selectors_len: Length of supported_selectors in octets.
* @auth_type: Authentication type (algorithm)
* @ie: Extra IEs to add to Authentication frame or %NULL
* @ie_len: Length of ie buffer in octets
@@ -3045,6 +3049,8 @@ struct cfg80211_auth_request {
struct cfg80211_bss *bss;
const u8 *ie;
size_t ie_len;
+ const u8 *supported_selectors;
+ u8 supported_selectors_len;
enum nl80211_auth_type auth_type;
const u8 *key;
u8 key_len;
@@ -3124,6 +3130,10 @@ enum cfg80211_assoc_req_flags {
* included in the Current AP address field of the Reassociation Request
* frame.
* @flags: See &enum cfg80211_assoc_req_flags
+ * @supported_selectors: supported selectors in IEEE 802.11 format
+ * (or %NULL for no change).
+ * If %NULL, then support for SAE_H2E should be assumed.
+ * @supported_selectors_len: Length of supported_selectors in octets.
* @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask
* will be used in ht_capa. Un-supported values will be ignored.
* @ht_capa_mask: The bits of ht_capa which are to be used.
@@ -3150,6 +3160,8 @@ struct cfg80211_assoc_request {
struct cfg80211_crypto_settings crypto;
bool use_mfp;
u32 flags;
+ const u8 *supported_selectors;
+ u8 supported_selectors_len;
struct ieee80211_ht_cap ht_capa;
struct ieee80211_ht_cap ht_capa_mask;
struct ieee80211_vht_cap vht_capa, vht_capa_mask;
@@ -4582,8 +4594,18 @@ struct mgmt_frame_regs {
*
* @set_hw_timestamp: Enable/disable HW timestamping of TM/FTM frames.
* @set_ttlm: set the TID to link mapping.
+ * @set_epcs: Enable/Disable EPCS for station mode.
* @get_radio_mask: get bitmask of radios in use.
* (invoked with the wiphy mutex held)
+ * @assoc_ml_reconf: Request a non-AP MLO connection to perform ML
+ * reconfiguration, i.e., add and/or remove links to/from the
+ * association using ML reconfiguration action frames. Successfully added
+ * links will be added to the set of valid links. Successfully removed
+ * links will be removed from the set of valid links. The driver must
+ * indicate removed links by calling cfg80211_links_removed() and added
+ * links by calling cfg80211_mlo_reconf_add_done(). When calling
+ * cfg80211_mlo_reconf_add_done() the bss pointer must be given for each
+ * link for which MLO reconfiguration 'add' operation was requested.
*/
struct cfg80211_ops {
int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -4733,7 +4755,7 @@ struct cfg80211_ops {
int (*set_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev,
enum nl80211_tx_power_setting type, int mbm);
int (*get_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev,
- int *dbm);
+ unsigned int link_id, int *dbm);
void (*rfkill_poll)(struct wiphy *wiphy);
@@ -4947,6 +4969,11 @@ struct cfg80211_ops {
int (*set_ttlm)(struct wiphy *wiphy, struct net_device *dev,
struct cfg80211_ttlm_params *params);
u32 (*get_radio_mask)(struct wiphy *wiphy, struct net_device *dev);
+ int (*assoc_ml_reconf)(struct wiphy *wiphy, struct net_device *dev,
+ struct cfg80211_assoc_link *add_links,
+ u16 rem_links);
+ int (*set_epcs)(struct wiphy *wiphy, struct net_device *dev,
+ bool val);
};
/*
@@ -5957,7 +5984,7 @@ int wiphy_register(struct wiphy *wiphy);
* @wiphy: the wiphy to check the locking on
* @p: The pointer to read, prior to dereferencing
*
- * Return the value of the specified RCU-protected pointer, but omit the
+ * Return: the value of the specified RCU-protected pointer, but omit the
* READ_ONCE(), because caller holds the wiphy mutex used for updates.
*/
#define wiphy_dereference(wiphy, p) \
@@ -6031,6 +6058,10 @@ static inline void wiphy_unlock(struct wiphy *wiphy)
mutex_unlock(&wiphy->mtx);
}
+DEFINE_GUARD(wiphy, struct wiphy *,
+ mutex_lock(&_T->mtx),
+ mutex_unlock(&_T->mtx))
+
struct wiphy_work;
typedef void (*wiphy_work_func_t)(struct wiphy *, struct wiphy_work *);
@@ -9701,6 +9732,39 @@ static inline int cfg80211_color_change_notify(struct net_device *dev,
void cfg80211_links_removed(struct net_device *dev, u16 link_mask);
/**
+ * struct cfg80211_mlo_reconf_done_data - MLO reconfiguration data
+ * @buf: MLO Reconfiguration Response frame (header + body)
+ * @len: length of the frame data
+ * @added_links: BIT mask of links successfully added to the association
+ * @links: per-link information indexed by link ID
+ * @links.bss: the BSS that MLO reconfiguration was requested for, ownership of
+ * the pointer moves to cfg80211 in the call to
+ * cfg80211_mlo_reconf_add_done().
+ *
+ * The BSS pointer must be set for each link for which 'add' operation was
+ * requested in the assoc_ml_reconf callback.
+ */
+struct cfg80211_mlo_reconf_done_data {
+ const u8 *buf;
+ size_t len;
+ u16 added_links;
+ struct {
+ struct cfg80211_bss *bss;
+ } links[IEEE80211_MLD_MAX_NUM_LINKS];
+};
+
+/**
+ * cfg80211_mlo_reconf_add_done - Notify about MLO reconfiguration result
+ * @dev: network device.
+ * @data: MLO reconfiguration done data, &struct cfg80211_mlo_reconf_done_data
+ *
+ * Inform cfg80211 and the userspace that processing of ML reconfiguration
+ * request to add links to the association is done.
+ */
+void cfg80211_mlo_reconf_add_done(struct net_device *dev,
+ struct cfg80211_mlo_reconf_done_data *data);
+
+/**
* cfg80211_schedule_channels_check - schedule regulatory check if needed
* @wdev: the wireless device to check
*
@@ -9710,6 +9774,13 @@ void cfg80211_links_removed(struct net_device *dev, u16 link_mask);
*/
void cfg80211_schedule_channels_check(struct wireless_dev *wdev);
+/**
+ * cfg80211_epcs_changed - Notify about a change in EPCS state
+ * @netdev: the wireless device whose EPCS state changed
+ * @enabled: set to true if EPCS was enabled, otherwise set to false.
+ */
+void cfg80211_epcs_changed(struct net_device *netdev, bool enabled);
+
#ifdef CONFIG_CFG80211_DEBUGFS
/**
* wiphy_locked_debugfs_read - do a locked read in debugfs
diff --git a/include/net/devlink.h b/include/net/devlink.h
index fbb9a2668e24..b8783126c1ed 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -35,7 +35,7 @@ struct devlink_port_phys_attrs {
/**
* struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes
* @controller: Associated controller number
- * @pf: Associated PCI PF number for this port.
+ * @pf: associated PCI function number for the devlink port instance
* @external: when set, indicates if a port is for an external controller
*/
struct devlink_port_pci_pf_attrs {
@@ -47,8 +47,9 @@ struct devlink_port_pci_pf_attrs {
/**
* struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes
* @controller: Associated controller number
- * @pf: Associated PCI PF number for this port.
- * @vf: Associated PCI VF for of the PCI PF for this port.
+ * @pf: associated PCI function number for the devlink port instance
+ * @vf: associated PCI VF number of a PF for the devlink port instance;
+ * VF number starts from 0 for the first PCI virtual function
* @external: when set, indicates if a port is for an external controller
*/
struct devlink_port_pci_vf_attrs {
@@ -61,8 +62,8 @@ struct devlink_port_pci_vf_attrs {
/**
* struct devlink_port_pci_sf_attrs - devlink port's PCI SF attributes
* @controller: Associated controller number
- * @sf: Associated PCI SF for of the PCI PF for this port.
- * @pf: Associated PCI PF number for this port.
+ * @sf: associated SF number of a PF for the devlink port instance
+ * @pf: associated PCI function number for the devlink port instance
* @external: when set, indicates if a port is for an external controller
*/
struct devlink_port_pci_sf_attrs {
@@ -1261,6 +1262,18 @@ enum devlink_trap_group_generic_id {
.min_burst = _min_burst, \
}
+#define devlink_fmsg_put(fmsg, name, value) ( \
+ _Generic((value), \
+ bool : devlink_fmsg_bool_pair_put, \
+ u8 : devlink_fmsg_u8_pair_put, \
+ u16 : devlink_fmsg_u32_pair_put, \
+ u32 : devlink_fmsg_u32_pair_put, \
+ u64 : devlink_fmsg_u64_pair_put, \
+ int : devlink_fmsg_u32_pair_put, \
+ char * : devlink_fmsg_string_pair_put, \
+ const char * : devlink_fmsg_string_pair_put) \
+ (fmsg, name, (value)))
+
enum {
/* device supports reload operations */
DEVLINK_F_RELOAD = 1UL << 0,
@@ -1522,6 +1535,7 @@ int devl_trylock(struct devlink *devlink);
void devl_unlock(struct devlink *devlink);
void devl_assert_locked(struct devlink *devlink);
bool devl_lock_is_held(struct devlink *devlink);
+DEFINE_GUARD(devl, struct devlink *, devl_lock(_T), devl_unlock(_T));
struct ib_device;
@@ -1994,6 +2008,7 @@ int devlink_compat_switch_id_get(struct net_device *dev,
int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port);
size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port);
+void devlink_fmsg_dump_skb(struct devlink_fmsg *fmsg, const struct sk_buff *skb);
#else
diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index 6c5a1ea209a2..32a34dfe8cc5 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -6,9 +6,13 @@
#define DEFINE_DROP_REASON(FN, FNe) \
FN(NOT_SPECIFIED) \
FN(NO_SOCKET) \
+ FN(SOCKET_CLOSE) \
+ FN(SOCKET_FILTER) \
+ FN(SOCKET_RCVBUFF) \
+ FN(UNIX_DISCONNECT) \
+ FN(UNIX_SKIP_OOB) \
FN(PKT_TOO_SMALL) \
FN(TCP_CSUM) \
- FN(SOCKET_FILTER) \
FN(UDP_CSUM) \
FN(NETFILTER_DROP) \
FN(OTHERHOST) \
@@ -18,7 +22,6 @@
FN(UNICAST_IN_L2_MULTICAST) \
FN(XFRM_POLICY) \
FN(IP_NOPROTO) \
- FN(SOCKET_RCVBUFF) \
FN(PROTO_MEM) \
FN(TCP_AUTH_HDR) \
FN(TCP_MD5NOTFOUND) \
@@ -36,6 +39,7 @@
FN(TCP_OVERWINDOW) \
FN(TCP_OFOMERGE) \
FN(TCP_RFC7323_PAWS) \
+ FN(TCP_RFC7323_PAWS_ACK) \
FN(TCP_OLD_SEQUENCE) \
FN(TCP_INVALID_SEQUENCE) \
FN(TCP_INVALID_ACK_SEQUENCE) \
@@ -58,6 +62,12 @@
FN(TC_EGRESS) \
FN(SECURITY_HOOK) \
FN(QDISC_DROP) \
+ FN(QDISC_OVERLIMIT) \
+ FN(QDISC_CONGESTED) \
+ FN(CAKE_FLOOD) \
+ FN(FQ_BAND_LIMIT) \
+ FN(FQ_HORIZON_LIMIT) \
+ FN(FQ_FLOW_LIMIT) \
FN(CPU_BACKLOG) \
FN(XDP) \
FN(TC_INGRESS) \
@@ -100,11 +110,13 @@
FN(VXLAN_VNI_NOT_FOUND) \
FN(MAC_INVALID_SOURCE) \
FN(VXLAN_ENTRY_EXISTS) \
- FN(VXLAN_NO_REMOTE) \
+ FN(NO_TX_TARGET) \
FN(IP_TUNNEL_ECN) \
FN(TUNNEL_TXINFO) \
FN(LOCAL_MAC) \
FN(ARP_PVLAN_DISABLE) \
+ FN(MAC_IEEE_MAC_CONTROL) \
+ FN(BRIDGE_INGRESS_STP_STATE) \
FNe(MAX)
/**
@@ -129,12 +141,27 @@ enum skb_drop_reason {
* 3) no valid child socket during 3WHS process
*/
SKB_DROP_REASON_NO_SOCKET,
+ /** @SKB_DROP_REASON_SOCKET_CLOSE: socket is close()d */
+ SKB_DROP_REASON_SOCKET_CLOSE,
+ /** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */
+ SKB_DROP_REASON_SOCKET_FILTER,
+ /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */
+ SKB_DROP_REASON_SOCKET_RCVBUFF,
+ /**
+ * @SKB_DROP_REASON_UNIX_DISCONNECT: recv queue is purged when SOCK_DGRAM
+ * or SOCK_SEQPACKET socket re-connect()s to another socket or notices
+ * during send() that the peer has been close()d.
+ */
+ SKB_DROP_REASON_UNIX_DISCONNECT,
+ /**
+ * @SKB_DROP_REASON_UNIX_SKIP_OOB: Out-Of-Band data is skipped by
+ * recv() without MSG_OOB so dropped.
+ */
+ SKB_DROP_REASON_UNIX_SKIP_OOB,
/** @SKB_DROP_REASON_PKT_TOO_SMALL: packet size is too small */
SKB_DROP_REASON_PKT_TOO_SMALL,
/** @SKB_DROP_REASON_TCP_CSUM: TCP checksum error */
SKB_DROP_REASON_TCP_CSUM,
- /** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */
- SKB_DROP_REASON_SOCKET_FILTER,
/** @SKB_DROP_REASON_UDP_CSUM: UDP checksum error */
SKB_DROP_REASON_UDP_CSUM,
/** @SKB_DROP_REASON_NETFILTER_DROP: dropped by netfilter */
@@ -165,8 +192,6 @@ enum skb_drop_reason {
SKB_DROP_REASON_XFRM_POLICY,
/** @SKB_DROP_REASON_IP_NOPROTO: no support for IP protocol */
SKB_DROP_REASON_IP_NOPROTO,
- /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */
- SKB_DROP_REASON_SOCKET_RCVBUFF,
/**
* @SKB_DROP_REASON_PROTO_MEM: proto memory limitation, such as
* udp packet drop out of udp_memory_allocated.
@@ -251,6 +276,11 @@ enum skb_drop_reason {
* LINUX_MIB_PAWSESTABREJECTED, LINUX_MIB_PAWSACTIVEREJECTED
*/
SKB_DROP_REASON_TCP_RFC7323_PAWS,
+ /**
+ * @SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK: PAWS check, old ACK packet.
+ * Corresponds to LINUX_MIB_PAWS_OLD_ACK.
+ */
+ SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK,
/** @SKB_DROP_REASON_TCP_OLD_SEQUENCE: Old SEQ field (duplicate packet) */
SKB_DROP_REASON_TCP_OLD_SEQUENCE,
/** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */
@@ -312,6 +342,36 @@ enum skb_drop_reason {
*/
SKB_DROP_REASON_QDISC_DROP,
/**
+ * @SKB_DROP_REASON_QDISC_OVERLIMIT: dropped by qdisc when a qdisc
+ * instance exceeds its total buffer size limit.
+ */
+ SKB_DROP_REASON_QDISC_OVERLIMIT,
+ /**
+ * @SKB_DROP_REASON_QDISC_CONGESTED: dropped by a qdisc AQM algorithm
+ * due to congestion.
+ */
+ SKB_DROP_REASON_QDISC_CONGESTED,
+ /**
+ * @SKB_DROP_REASON_CAKE_FLOOD: dropped by the flood protection part of
+ * CAKE qdisc AQM algorithm (BLUE).
+ */
+ SKB_DROP_REASON_CAKE_FLOOD,
+ /**
+ * @SKB_DROP_REASON_FQ_BAND_LIMIT: dropped by fq qdisc when per band
+ * limit is reached.
+ */
+ SKB_DROP_REASON_FQ_BAND_LIMIT,
+ /**
+ * @SKB_DROP_REASON_FQ_HORIZON_LIMIT: dropped by fq qdisc when packet
+ * timestamp is too far in the future.
+ */
+ SKB_DROP_REASON_FQ_HORIZON_LIMIT,
+ /**
+ * @SKB_DROP_REASON_FQ_FLOW_LIMIT: dropped by fq qdisc when a flow
+ * exceeds its limits.
+ */
+ SKB_DROP_REASON_FQ_FLOW_LIMIT,
+ /**
* @SKB_DROP_REASON_CPU_BACKLOG: failed to enqueue the skb to the per CPU
* backlog queue. This can be caused by backlog queue full (see
* netdev_max_backlog in net.rst) or RPS flow limit
@@ -461,8 +521,8 @@ enum skb_drop_reason {
* entry or an entry pointing to a nexthop.
*/
SKB_DROP_REASON_VXLAN_ENTRY_EXISTS,
- /** @SKB_DROP_REASON_VXLAN_NO_REMOTE: no remote found for xmit */
- SKB_DROP_REASON_VXLAN_NO_REMOTE,
+ /** @SKB_DROP_REASON_NO_TX_TARGET: no target found for xmit */
+ SKB_DROP_REASON_NO_TX_TARGET,
/**
* @SKB_DROP_REASON_IP_TUNNEL_ECN: skb is dropped according to
* RFC 6040 4.2, see __INET_ECN_decapsulate() for detail.
@@ -485,6 +545,16 @@ enum skb_drop_reason {
*/
SKB_DROP_REASON_ARP_PVLAN_DISABLE,
/**
+ * @SKB_DROP_REASON_MAC_IEEE_MAC_CONTROL: the destination MAC address
+ * is an IEEE MAC Control address.
+ */
+ SKB_DROP_REASON_MAC_IEEE_MAC_CONTROL,
+ /**
+ * @SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE: the STP state of the
+ * ingress bridge port does not allow frames to be forwarded.
+ */
+ SKB_DROP_REASON_BRIDGE_INGRESS_STP_STATE,
+ /**
* @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which
* shouldn't be used as a real 'reason' - only for tracing code gen
*/
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 72ae65e7246a..a0a9481c52c2 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -906,6 +906,8 @@ struct dsa_switch_ops {
void (*get_rmon_stats)(struct dsa_switch *ds, int port,
struct ethtool_rmon_stats *rmon_stats,
const struct ethtool_rmon_hist_range **ranges);
+ void (*get_ts_stats)(struct dsa_switch *ds, int port,
+ struct ethtool_ts_stats *ts_stats);
void (*get_stats64)(struct dsa_switch *ds, int port,
struct rtnl_link_stats64 *s);
void (*get_pause_stats)(struct dsa_switch *ds, int port,
@@ -988,10 +990,9 @@ struct dsa_switch_ops {
/*
* Port's MAC EEE settings
*/
+ bool (*support_eee)(struct dsa_switch *ds, int port);
int (*set_mac_eee)(struct dsa_switch *ds, int port,
struct ethtool_keee *e);
- int (*get_mac_eee)(struct dsa_switch *ds, int port,
- struct ethtool_keee *e);
/* EEPROM access */
int (*get_eeprom_len)(struct dsa_switch *ds);
@@ -1383,5 +1384,6 @@ static inline bool dsa_user_dev_check(const struct net_device *dev)
netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev);
void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up);
+bool dsa_supports_eee(struct dsa_switch *ds, int port);
#endif
diff --git a/include/net/dst.h b/include/net/dst.h
index 0f303cc60252..78c78cdce0e9 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -307,7 +307,7 @@ static inline bool dst_hold_safe(struct dst_entry *dst)
* @skb: buffer
*
* If dst is not yet refcounted and not destroyed, grab a ref on it.
- * Returns true if dst is refcounted.
+ * Returns: true if dst is refcounted.
*/
static inline bool skb_dst_force(struct sk_buff *skb)
{
@@ -440,6 +440,15 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout)
dst->expires = expires;
}
+static inline unsigned int dst_dev_overhead(struct dst_entry *dst,
+ struct sk_buff *skb)
+{
+ if (likely(dst))
+ return LL_RESERVED_SPACE(dst->dev);
+
+ return skb->mac_len;
+}
+
INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *,
struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *,
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index d096cc6352de..a03d56765832 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -354,7 +354,7 @@ __genlmsg_iput(struct sk_buff *skb, const struct genl_info *info, int flags)
* such requests) or a struct initialized by genl_info_init_ntf()
* when constructing notifications.
*
- * Returns pointer to new genetlink header.
+ * Returns: pointer to new genetlink header.
*/
static inline void *
genlmsg_iput(struct sk_buff *skb, const struct genl_info *info)
@@ -366,7 +366,7 @@ genlmsg_iput(struct sk_buff *skb, const struct genl_info *info)
* genlmsg_nlhdr - Obtain netlink header from user specified header
* @user_hdr: user header as returned from genlmsg_put()
*
- * Returns pointer to netlink header.
+ * Returns: pointer to netlink header.
*/
static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr)
{
@@ -435,7 +435,7 @@ static inline void genl_dump_check_consistent(struct netlink_callback *cb,
* @flags: netlink message flags
* @cmd: generic netlink command
*
- * Returns pointer to user specific header
+ * Returns: pointer to user specific header
*/
static inline void *genlmsg_put_reply(struct sk_buff *skb,
struct genl_info *info,
diff --git a/include/net/gro.h b/include/net/gro.h
index b9b58c1f8d19..7b548f91754b 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -11,6 +11,9 @@
#include <net/udp.h>
#include <net/hotdata.h>
+/* This should be increased if a protocol with a bigger head is added. */
+#define GRO_MAX_HEAD (MAX_HEADER + 128)
+
struct napi_gro_cb {
union {
struct {
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 3c82fad904d4..c7f42844c79a 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -282,7 +282,7 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
{
- return inet_csk_reqsk_queue_len(sk) >= READ_ONCE(sk->sk_max_ack_backlog);
+ return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog);
}
bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 56d8bc5593d3..1086256549fa 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -19,6 +19,7 @@
#include <linux/netdevice.h>
#include <net/flow.h>
+#include <net/inet_dscp.h>
#include <net/sock.h>
#include <net/request_sock.h>
#include <net/netns/hash.h>
@@ -172,7 +173,7 @@ struct inet_cork {
u8 tx_flags;
__u8 ttl;
__s16 tos;
- char priority;
+ u32 priority;
__u16 gso_size;
u32 ts_opt_id;
u64 transmit_time;
@@ -302,6 +303,11 @@ static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet)
return READ_ONCE(inet->inet_flags) & IP_CMSG_ALL;
}
+static inline dscp_t inet_sk_dscp(const struct inet_sock *inet)
+{
+ return inet_dsfield_to_dscp(READ_ONCE(inet->tos));
+}
+
#define inet_test_bit(nr, sk) \
test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags)
#define inet_set_bit(nr, sk) \
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 62c0a7e65d6b..67a313575780 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -74,6 +74,10 @@ struct inet_timewait_sock {
tw_tos : 8;
u32 tw_txhash;
u32 tw_priority;
+ /**
+ * @tw_reuse_stamp: Time of entry into %TCP_TIME_WAIT state in msec.
+ */
+ u32 tw_entry_stamp;
struct timer_list tw_timer;
struct inet_bind_bucket *tw_tb;
struct inet_bind2_bucket *tw_tb2;
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 74ff688568a0..f475757daafb 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -96,30 +96,28 @@ static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr)
/* can be called with or without local BH being disabled */
struct inet_peer *inet_getpeer(struct inet_peer_base *base,
- const struct inetpeer_addr *daddr,
- int create);
+ const struct inetpeer_addr *daddr);
static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base,
__be32 v4daddr,
- int vif, int create)
+ int vif)
{
struct inetpeer_addr daddr;
daddr.a4.addr = v4daddr;
daddr.a4.vif = vif;
daddr.family = AF_INET;
- return inet_getpeer(base, &daddr, create);
+ return inet_getpeer(base, &daddr);
}
static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
- const struct in6_addr *v6daddr,
- int create)
+ const struct in6_addr *v6daddr)
{
struct inetpeer_addr daddr;
daddr.a6 = *v6daddr;
daddr.family = AF_INET6;
- return inet_getpeer(base, &daddr, create);
+ return inet_getpeer(base, &daddr);
}
static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a,
diff --git a/include/net/ip.h b/include/net/ip.h
index 0e548c1f2a0e..ba7b43447775 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -81,7 +81,6 @@ struct ipcm_cookie {
__u8 protocol;
__u8 ttl;
__s16 tos;
- char priority;
__u16 gso_size;
};
@@ -96,6 +95,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
ipcm_init(ipcm);
ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark);
+ ipcm->sockc.priority = READ_ONCE(inet->sk.sk_priority);
ipcm->sockc.tsflags = READ_ONCE(inet->sk.sk_tsflags);
ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
ipcm->addr = inet->inet_saddr;
@@ -471,9 +471,12 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
bool forwarding)
{
const struct rtable *rt = dst_rtable(dst);
- struct net *net = dev_net(dst->dev);
- unsigned int mtu;
+ unsigned int mtu, res;
+ struct net *net;
+
+ rcu_read_lock();
+ net = dev_net_rcu(dst->dev);
if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) ||
ip_mtu_locked(dst) ||
!forwarding) {
@@ -497,7 +500,11 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
out:
mtu = min_t(unsigned int, mtu, IP_MAX_MTU);
- return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
+ res = mtu - lwtunnel_headroom(dst->lwtstate, mtu);
+
+ rcu_read_unlock();
+
+ return res;
}
static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 248bfb26e2af..f5c43ad1565e 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -471,7 +471,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
/* This helper is specialized for BIG TCP needs.
* It assumes the hop_jumbo_hdr will immediately follow the IPV6 header.
* It assumes headers are already in skb->head.
- * Returns 0, or IPPROTO_TCP if a BIG TCP packet is there.
+ * Returns: 0, or IPPROTO_TCP if a BIG TCP packet is there.
*/
static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb)
{
diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h
index dd9e93c12260..9804fa5d9c67 100644
--- a/include/net/iucv/iucv.h
+++ b/include/net/iucv/iucv.h
@@ -202,7 +202,7 @@ struct iucv_handler {
*
* Registers a driver with IUCV.
*
- * Returns 0 on success, -ENOMEM if the memory allocation for the pathid
+ * Returns: 0 on success, -ENOMEM if the memory allocation for the pathid
* table failed, or -EIO if IUCV_DECLARE_BUFFER failed on all cpus.
*/
int iucv_register(struct iucv_handler *handler, int smp);
@@ -224,7 +224,7 @@ void iucv_unregister(struct iucv_handler *handle, int smp);
*
* Allocate a new path structure for use with iucv_connect.
*
- * Returns NULL if the memory allocation failed or a pointer to the
+ * Returns: NULL if the memory allocation failed or a pointer to the
* path structure.
*/
static inline struct iucv_path *iucv_path_alloc(u16 msglim, u8 flags, gfp_t gfp)
@@ -260,7 +260,7 @@ static inline void iucv_path_free(struct iucv_path *path)
* This function is issued after the user received a connection pending
* external interrupt and now wishes to complete the IUCV communication path.
*
- * Returns the result of the CP IUCV call.
+ * Returns: the result of the CP IUCV call.
*/
int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler,
u8 *userdata, void *private);
@@ -278,7 +278,7 @@ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler,
* successfully, you are not able to use the path until you receive an IUCV
* Connection Complete external interrupt.
*
- * Returns the result of the CP IUCV call.
+ * Returns: the result of the CP IUCV call.
*/
int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler,
u8 *userid, u8 *system, u8 *userdata,
@@ -292,7 +292,7 @@ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler,
* This function temporarily suspends incoming messages on an IUCV path.
* You can later reactivate the path by invoking the iucv_resume function.
*
- * Returns the result from the CP IUCV call.
+ * Returns: the result from the CP IUCV call.
*/
int iucv_path_quiesce(struct iucv_path *path, u8 *userdata);
@@ -304,7 +304,7 @@ int iucv_path_quiesce(struct iucv_path *path, u8 *userdata);
* This function resumes incoming messages on an IUCV path that has
* been stopped with iucv_path_quiesce.
*
- * Returns the result from the CP IUCV call.
+ * Returns: the result from the CP IUCV call.
*/
int iucv_path_resume(struct iucv_path *path, u8 *userdata);
@@ -315,7 +315,7 @@ int iucv_path_resume(struct iucv_path *path, u8 *userdata);
*
* This function terminates an IUCV path.
*
- * Returns the result from the CP IUCV call.
+ * Returns: the result from the CP IUCV call.
*/
int iucv_path_sever(struct iucv_path *path, u8 *userdata);
@@ -327,7 +327,7 @@ int iucv_path_sever(struct iucv_path *path, u8 *userdata);
*
* Cancels a message you have sent.
*
- * Returns the result from the CP IUCV call.
+ * Returns: the result from the CP IUCV call.
*/
int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg,
u32 srccls);
@@ -347,7 +347,7 @@ int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg,
*
* Locking: local_bh_enable/local_bh_disable
*
- * Returns the result from the CP IUCV call.
+ * Returns: the result from the CP IUCV call.
*/
int iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
u8 flags, void *buffer, size_t size, size_t *residual);
@@ -367,7 +367,7 @@ int iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
*
* Locking: no locking.
*
- * Returns the result from the CP IUCV call.
+ * Returns: the result from the CP IUCV call.
*/
int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
u8 flags, void *buffer, size_t size,
@@ -382,7 +382,7 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
* are notified of a message and the time that you complete the message,
* the message may be rejected.
*
- * Returns the result from the CP IUCV call.
+ * Returns: the result from the CP IUCV call.
*/
int iucv_message_reject(struct iucv_path *path, struct iucv_message *msg);
@@ -399,7 +399,7 @@ int iucv_message_reject(struct iucv_path *path, struct iucv_message *msg);
* pathid, msgid, and trgcls. Prmmsg signifies the data is moved into
* the parameter list.
*
- * Returns the result from the CP IUCV call.
+ * Returns: the result from the CP IUCV call.
*/
int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg,
u8 flags, void *reply, size_t size);
@@ -419,7 +419,7 @@ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg,
*
* Locking: local_bh_enable/local_bh_disable
*
- * Returns the result from the CP IUCV call.
+ * Returns: the result from the CP IUCV call.
*/
int iucv_message_send(struct iucv_path *path, struct iucv_message *msg,
u8 flags, u32 srccls, void *buffer, size_t size);
@@ -439,7 +439,7 @@ int iucv_message_send(struct iucv_path *path, struct iucv_message *msg,
*
* Locking: no locking.
*
- * Returns the result from the CP IUCV call.
+ * Returns: the result from the CP IUCV call.
*/
int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg,
u8 flags, u32 srccls, void *buffer, size_t size);
@@ -461,7 +461,7 @@ int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg,
* reply to the message and a buffer is provided into which IUCV moves
* the reply to this message.
*
- * Returns the result from the CP IUCV call.
+ * Returns: the result from the CP IUCV call.
*/
int iucv_message_send2way(struct iucv_path *path, struct iucv_message *msg,
u8 flags, u32 srccls, void *buffer, size_t size,
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index 2d6141f28b53..f7fe796e8429 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -198,10 +198,12 @@ struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto)
if (netif_is_l3_slave(dev)) {
struct net_device *master;
+ rcu_read_lock();
master = netdev_master_upper_dev_get_rcu(dev);
if (master && master->l3mdev_ops->l3mdev_l3_out)
skb = master->l3mdev_ops->l3mdev_l3_out(master, sk,
skb, proto);
+ rcu_read_unlock();
}
return skb;
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index ab8dce1f2c27..c3ed2fcff8b7 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1855,6 +1855,9 @@ struct ieee80211_channel_switch {
* operation on this interface and request a channel context without
* the AP definition. Use this e.g. because the device is able to
* handle OFDMA (downlink and trigger for uplink) on a per-AP basis.
+ * @IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC: indicates that the AP sta should
+ * be removed only after setting the vif as unassociated, and not the
+ * opposite. Only relevant for STA vifs.
*/
enum ieee80211_vif_flags {
IEEE80211_VIF_BEACON_FILTER = BIT(0),
@@ -1863,6 +1866,7 @@ enum ieee80211_vif_flags {
IEEE80211_VIF_GET_NOA_UPDATE = BIT(3),
IEEE80211_VIF_EML_ACTIVE = BIT(4),
IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW = BIT(5),
+ IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC = BIT(6),
};
@@ -2216,7 +2220,7 @@ enum ieee80211_key_flags {
* @tx_pn: PN used for TX keys, may be used by the driver as well if it
* needs to do software PN assignment by itself (e.g. due to TSO)
* @flags: key flags, see &enum ieee80211_key_flags.
- * @keyidx: the key index (0-3)
+ * @keyidx: the key index (0-7)
* @keylen: key material length
* @key: key material. For ALG_TKIP the key is encoded as a 256-bit (32 byte)
* data block:
@@ -2225,7 +2229,7 @@ enum ieee80211_key_flags {
* - Temporal Authenticator Rx MIC Key (64 bits)
* @icv_len: The ICV length for this key type
* @iv_len: The IV length for this key type
- * @link_id: the link ID for MLO, or -1 for non-MLO or pairwise keys
+ * @link_id: the link ID, 0 for non-MLO, or -1 for pairwise keys
*/
struct ieee80211_key_conf {
atomic64_t tx_pn;
@@ -2336,6 +2340,8 @@ enum ieee80211_sta_rx_bandwidth {
IEEE80211_STA_RX_BW_320,
};
+#define IEEE80211_STA_RX_BW_MAX IEEE80211_STA_RX_BW_320
+
/**
* struct ieee80211_sta_rates - station rate selection table
*
@@ -4762,7 +4768,7 @@ struct ieee80211_ops {
u32 (*get_expected_throughput)(struct ieee80211_hw *hw,
struct ieee80211_sta *sta);
int (*get_txpower)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
- int *dbm);
+ unsigned int link_id, int *dbm);
int (*tdls_channel_switch)(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
@@ -7734,6 +7740,50 @@ ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width)
}
}
+/**
+ * ieee80211_prepare_rx_omi_bw - prepare for sending BW RX OMI
+ * @link_sta: the link STA the OMI is going to be sent to
+ * @bw: the bandwidth requested
+ *
+ * When the driver decides to do RX OMI to change bandwidth with a STA
+ * it calls this function to prepare, then sends the OMI, and finally
+ * calls ieee80211_finalize_rx_omi_bw().
+ *
+ * Note that the (link) STA rate control is updated accordingly as well,
+ * but the chanctx might not be updated if there are other users.
+ * If the intention is to reduce the listen bandwidth, the driver must
+ * ensure there are no TDLS stations nor other uses of the chanctx.
+ *
+ * Also note that in order to sequence correctly, narrowing bandwidth
+ * will only happen in ieee80211_finalize_rx_omi_bw(), whereas widening
+ * again (e.g. going back to normal) will happen here.
+ *
+ * Note that we treat this symmetrically, so if the driver calls this
+ * and tells the peer to only send with a lower bandwidth, we assume
+ * that the driver also wants to only send at that lower bandwidth, to
+ * allow narrowing of the chanctx request for this station/interface.
+ *
+ * Finally, the driver must ensure that if the function returned %true,
+ * ieee80211_finalize_rx_omi_bw() is also called, even for example in
+ * case of HW restart.
+ *
+ * Context: Must be called with wiphy mutex held, and will call back
+ * into the driver, so ensure no driver locks are held.
+ *
+ * Return: %true if changes are going to be made, %false otherwise
+ */
+bool ieee80211_prepare_rx_omi_bw(struct ieee80211_link_sta *link_sta,
+ enum ieee80211_sta_rx_bandwidth bw);
+
+/**
+ * ieee80211_finalize_rx_omi_bw - finalize BW RX OMI update
+ * @link_sta: the link STA the OMI was sent to
+ *
+ * See ieee80211_client_prepare_rx_omi_bw(). Context is the same here
+ * as well.
+ */
+void ieee80211_finalize_rx_omi_bw(struct ieee80211_link_sta *link_sta);
+
/* for older drivers - let's not document these ... */
int ieee80211_emulate_add_chanctx(struct ieee80211_hw *hw,
struct ieee80211_chanctx_conf *ctx);
diff --git a/include/net/macsec.h b/include/net/macsec.h
index de216cbc6b05..bc7de5b53e54 100644
--- a/include/net/macsec.h
+++ b/include/net/macsec.h
@@ -38,8 +38,8 @@ struct metadata_dst;
typedef union salt {
struct {
- u32 ssci;
- u64 pn;
+ ssci_t ssci;
+ __be64 pn;
} __packed;
u8 bytes[MACSEC_SALT_LEN];
} __packed salt_t;
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 5a2a0df8ad91..f467a66abc6b 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -210,6 +210,8 @@ void net_ns_barrier(void);
struct ns_common *get_net_ns(struct ns_common *ns);
struct net *get_net_ns_by_fd(int fd);
+extern struct task_struct *cleanup_net_task;
+
#else /* CONFIG_NET_NS */
#include <linux/sched.h>
#include <linux/nsproxy.h>
@@ -295,6 +297,7 @@ static inline int check_net(const struct net *net)
}
void net_drop_ns(void *);
+void net_passive_dec(struct net *net);
#else
@@ -324,8 +327,18 @@ static inline int check_net(const struct net *net)
}
#define net_drop_ns NULL
+
+static inline void net_passive_dec(struct net *net)
+{
+ refcount_dec(&net->passive);
+}
#endif
+static inline void net_passive_inc(struct net *net)
+{
+ refcount_inc(&net->passive);
+}
+
/* Returns true if the netns initialization is completed successfully */
static inline bool net_initialized(const struct net *net)
{
@@ -396,7 +409,7 @@ static inline struct net *read_pnet(const possible_net_t *pnet)
#endif
}
-static inline struct net *read_pnet_rcu(possible_net_t *pnet)
+static inline struct net *read_pnet_rcu(const possible_net_t *pnet)
{
#ifdef CONFIG_NET_NS
return rcu_dereference(pnet->net);
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index 5ca019d294ca..b02bb9f109d5 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -4,6 +4,16 @@
#include <linux/netdevice.h>
+/**
+ * struct netdev_config - queue-related configuration for a netdev
+ * @hds_thresh: HDS Threshold value.
+ * @hds_config: HDS value from userspace.
+ */
+struct netdev_config {
+ u32 hds_thresh;
+ u8 hds_config;
+};
+
/* See the netdev.yaml spec for definition of each statistic */
struct netdev_queue_stats_rx {
u64 bytes;
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index cba3ccf03fcc..3f02a45773e8 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -204,8 +204,7 @@ bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
struct nf_conntrack_tuple *tuple);
void __nf_ct_refresh_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
- const struct sk_buff *skb,
- u32 extra_jiffies, bool do_acct);
+ u32 extra_jiffies, unsigned int bytes);
/* Refresh conntrack for this many jiffies and do accounting */
static inline void nf_ct_refresh_acct(struct nf_conn *ct,
@@ -213,15 +212,14 @@ static inline void nf_ct_refresh_acct(struct nf_conn *ct,
const struct sk_buff *skb,
u32 extra_jiffies)
{
- __nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies, true);
+ __nf_ct_refresh_acct(ct, ctinfo, extra_jiffies, skb->len);
}
/* Refresh conntrack for this many jiffies */
static inline void nf_ct_refresh(struct nf_conn *ct,
- const struct sk_buff *skb,
u32 extra_jiffies)
{
- __nf_ct_refresh_acct(ct, 0, skb, extra_jiffies, false);
+ __nf_ct_refresh_acct(ct, 0, extra_jiffies, 0);
}
/* kill conntrack and do accounting */
@@ -314,16 +312,6 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct)
#define NF_CT_DAY (86400 * HZ)
-/* Set an arbitrary timeout large enough not to ever expire, this save
- * us a check for the IPS_OFFLOAD_BIT from the packet path via
- * nf_ct_is_expired().
- */
-static inline void nf_ct_offload_timeout(struct nf_conn *ct)
-{
- if (nf_ct_expires(ct) < NF_CT_DAY / 2)
- WRITE_ONCE(ct->timeout, nfct_time_stamp + NF_CT_DAY);
-}
-
struct kernel_param;
int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp);
diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index 0c1dac318e02..8dcf7c371ee9 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -12,6 +12,7 @@
#include <linux/netfilter/nf_conntrack_common.h>
#include <linux/netfilter/nf_conntrack_tuple_common.h>
#include <net/netfilter/nf_conntrack_extend.h>
+#include <asm/local64.h>
enum nf_ct_ecache_state {
NFCT_ECACHE_DESTROY_FAIL, /* tried but failed to send destroy event */
@@ -20,6 +21,9 @@ enum nf_ct_ecache_state {
struct nf_conntrack_ecache {
unsigned long cache; /* bitops want long */
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+ local64_t timestamp; /* event timestamp, in nanoseconds */
+#endif
u16 ctmask; /* bitmask of ct events to be delivered */
u16 expmask; /* bitmask of expect events to be delivered */
u32 missed; /* missed events */
@@ -108,6 +112,14 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct)
if (e == NULL)
return;
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+ /* renew only if this is the first cached event, so that the
+ * timestamp reflects the first, not the last, generated event.
+ */
+ if (local64_read(&e->timestamp) && READ_ONCE(e->cache) == 0)
+ local64_set(&e->timestamp, ktime_get_real_ns());
+#endif
+
set_bit(event, &e->cache);
#endif
}
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index b63d53bb9dd6..d711642e78b5 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -163,6 +163,7 @@ struct flow_offload_tuple_rhash {
enum nf_flow_flags {
NF_FLOW_SNAT,
NF_FLOW_DNAT,
+ NF_FLOW_CLOSING,
NF_FLOW_TEARDOWN,
NF_FLOW_HW,
NF_FLOW_HW_DYING,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 4afa64c81304..60d5dcdb289c 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -442,6 +442,9 @@ struct nft_set_ext;
* @remove: remove element from set
* @walk: iterate over all set elements
* @get: get set elements
+ * @ksize: kernel set size
+ * @usize: userspace set size
+ * @adjust_maxsize: delta to adjust maximum set size
* @commit: commit set elements
* @abort: abort set elements
* @privsize: function to return size of set private data
@@ -495,6 +498,9 @@ struct nft_set_ops {
const struct nft_set *set,
const struct nft_set_elem *elem,
unsigned int flags);
+ u32 (*ksize)(u32 size);
+ u32 (*usize)(u32 size);
+ u32 (*adjust_maxsize)(const struct nft_set *set);
void (*commit)(struct nft_set *set);
void (*abort)(const struct nft_set *set);
u64 (*privsize)(const struct nlattr * const nla[],
@@ -733,15 +739,18 @@ struct nft_set_ext_tmpl {
/**
* struct nft_set_ext - set extensions
*
- * @genmask: generation mask
+ * @genmask: generation mask, but also flags (see NFT_SET_ELEM_DEAD_BIT)
* @offset: offsets of individual extension types
* @data: beginning of extension data
+ *
+ * This structure must be aligned to word size, otherwise atomic bitops
+ * on genmask field can cause alignment failure on some archs.
*/
struct nft_set_ext {
u8 genmask;
u8 offset[NFT_SET_EXT_NUM];
char data[];
-};
+} __aligned(BITS_PER_LONG / 8);
static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl)
{
@@ -1192,6 +1201,8 @@ struct nft_hook {
struct list_head list;
struct nf_hook_ops ops;
struct rcu_head rcu;
+ char ifname[IFNAMSIZ];
+ u8 ifnamelen;
};
/**
@@ -1227,8 +1238,6 @@ static inline bool nft_is_base_chain(const struct nft_chain *chain)
return chain->flags & NFT_CHAIN_BASE;
}
-int __nft_release_basechain(struct nft_ctx *ctx);
-
unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv);
static inline bool nft_use_inc(u32 *use)
diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h
index 5adf6fda11e8..06985530517b 100644
--- a/include/net/netfilter/nf_tproxy.h
+++ b/include/net/netfilter/nf_tproxy.h
@@ -49,7 +49,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr);
*
* nf_tproxy_handle_time_wait4() consumes the socket reference passed in.
*
- * Returns the listener socket if there's one, the TIME_WAIT socket if
+ * Returns: the listener socket if there's one, the TIME_WAIT socket if
* no such listener is found, or NULL if the TCP header is incomplete.
*/
struct sock *
@@ -108,7 +108,7 @@ nf_tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr,
*
* nf_tproxy_handle_time_wait6() consumes the socket reference passed in.
*
- * Returns the listener socket if there's one, the TIME_WAIT socket if
+ * Returns: the listener socket if there's one, the TIME_WAIT socket if
* no such listener is found, or NULL if the TCP header is incomplete.
*/
struct sock *
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 39eaa6be6ca8..e015ffbed819 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -649,7 +649,7 @@ static inline int nlmsg_ok(const struct nlmsghdr *nlh, int remaining)
* @nlh: netlink message header
* @remaining: number of bytes remaining in message stream
*
- * Returns the next netlink message in the message stream and
+ * Returns: the next netlink message in the message stream and
* decrements remaining by the size of the current message.
*/
static inline struct nlmsghdr *
@@ -676,7 +676,7 @@ nlmsg_next(const struct nlmsghdr *nlh, int *remaining)
* exceeding maxtype will be rejected, policy must be specified, attributes
* will be validated in the strictest way possible.
*
- * Returns 0 on success or a negative error code.
+ * Returns: 0 on success or a negative error code.
*/
static inline int nla_parse(struct nlattr **tb, int maxtype,
const struct nlattr *head, int len,
@@ -701,7 +701,7 @@ static inline int nla_parse(struct nlattr **tb, int maxtype,
* exceeding maxtype will be ignored and attributes from the policy are not
* always strictly validated (only for new attributes).
*
- * Returns 0 on success or a negative error code.
+ * Returns: 0 on success or a negative error code.
*/
static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype,
const struct nlattr *head, int len,
@@ -726,7 +726,7 @@ static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype,
* exceeding maxtype will be rejected as well as trailing data, but the
* policy is not completely strictly validated (only for new attributes).
*
- * Returns 0 on success or a negative error code.
+ * Returns: 0 on success or a negative error code.
*/
static inline int nla_parse_deprecated_strict(struct nlattr **tb, int maxtype,
const struct nlattr *head,
@@ -833,7 +833,7 @@ nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen,
* @hdrlen: length of family specific header
* @attrtype: type of attribute to look for
*
- * Returns the first attribute which matches the specified type.
+ * Returns: the first attribute which matches the specified type.
*/
static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh,
int hdrlen, int attrtype)
@@ -854,7 +854,7 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh,
* specified policy. Validation is done in liberal mode.
* See documentation of struct nla_policy for more details.
*
- * Returns 0 on success or a negative error code.
+ * Returns: 0 on success or a negative error code.
*/
static inline int nla_validate_deprecated(const struct nlattr *head, int len,
int maxtype,
@@ -877,7 +877,7 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len,
* specified policy. Validation is done in strict mode.
* See documentation of struct nla_policy for more details.
*
- * Returns 0 on success or a negative error code.
+ * Returns: 0 on success or a negative error code.
*/
static inline int nla_validate(const struct nlattr *head, int len, int maxtype,
const struct nla_policy *policy,
@@ -914,7 +914,7 @@ static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh,
* nlmsg_report - need to report back to application?
* @nlh: netlink message header
*
- * Returns 1 if a report back to the application is requested.
+ * Returns: 1 if a report back to the application is requested.
*/
static inline int nlmsg_report(const struct nlmsghdr *nlh)
{
@@ -925,7 +925,7 @@ static inline int nlmsg_report(const struct nlmsghdr *nlh)
* nlmsg_seq - return the seq number of netlink message
* @nlh: netlink message header
*
- * Returns 0 if netlink message is NULL
+ * Returns: 0 if netlink message is NULL
*/
static inline u32 nlmsg_seq(const struct nlmsghdr *nlh)
{
@@ -952,7 +952,7 @@ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh)
* @payload: length of message payload
* @flags: message flags
*
- * Returns NULL if the tailroom of the skb is insufficient to store
+ * Returns: NULL if the tailroom of the skb is insufficient to store
* the message header and payload.
*/
static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq,
@@ -971,7 +971,7 @@ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 se
*
* Append data to an existing nlmsg, used when constructing a message
* with multiple fixed-format headers (which is rare).
- * Returns NULL if the tailroom of the skb is insufficient to store
+ * Returns: NULL if the tailroom of the skb is insufficient to store
* the extra payload.
*/
static inline void *nlmsg_append(struct sk_buff *skb, u32 size)
@@ -993,7 +993,7 @@ static inline void *nlmsg_append(struct sk_buff *skb, u32 size)
* @payload: length of message payload
* @flags: message flags
*
- * Returns NULL if the tailroom of the skb is insufficient to store
+ * Returns: NULL if the tailroom of the skb is insufficient to store
* the message header and payload.
*/
static inline struct nlmsghdr *nlmsg_put_answer(struct sk_buff *skb,
@@ -1050,7 +1050,7 @@ static inline void nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh)
* nlmsg_get_pos - return current position in netlink message
* @skb: socket buffer the message is stored in
*
- * Returns a pointer to the current tail of the message.
+ * Returns: a pointer to the current tail of the message.
*/
static inline void *nlmsg_get_pos(struct sk_buff *skb)
{
@@ -1276,7 +1276,7 @@ static inline int nla_ok(const struct nlattr *nla, int remaining)
* @nla: netlink attribute
* @remaining: number of bytes remaining in attribute stream
*
- * Returns the next netlink attribute in the attribute stream and
+ * Returns: the next netlink attribute in the attribute stream and
* decrements remaining by the size of the current attribute.
*/
static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
@@ -1292,7 +1292,7 @@ static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
* @nla: attribute containing the nested attributes
* @attrtype: type of attribute to look for
*
- * Returns the first attribute which matches the specified type.
+ * Returns: the first attribute which matches the specified type.
*/
static inline struct nlattr *
nla_find_nested(const struct nlattr *nla, int attrtype)
@@ -2091,7 +2091,7 @@ static inline int nla_get_flag(const struct nlattr *nla)
* nla_get_msecs - return payload of msecs attribute
* @nla: msecs netlink attribute
*
- * Returns the number of milliseconds in jiffies.
+ * Returns: the number of milliseconds in jiffies.
*/
static inline unsigned long nla_get_msecs(const struct nlattr *nla)
{
@@ -2183,7 +2183,7 @@ static inline void *nla_memdup_noprof(const struct nlattr *src, gfp_t gfp)
* marked their nest attributes with NLA_F_NESTED flag. New APIs should use
* nla_nest_start() which sets the flag.
*
- * Returns the container attribute or NULL on error
+ * Returns: the container attribute or NULL on error
*/
static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb,
int attrtype)
@@ -2204,7 +2204,7 @@ static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb,
* Unlike nla_nest_start_noflag(), mark the nest attribute with NLA_F_NESTED
* flag. This is the preferred function to use in new code.
*
- * Returns the container attribute or NULL on error
+ * Returns: the container attribute or NULL on error
*/
static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype)
{
@@ -2219,7 +2219,7 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype)
* Corrects the container attribute header to include the all
* appended attributes.
*
- * Returns the total data length of the skb.
+ * Returns: the total data length of the skb.
*/
static inline int nla_nest_end(struct sk_buff *skb, struct nlattr *start)
{
@@ -2252,7 +2252,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start)
* specified policy. Attributes with a type exceeding maxtype will be
* ignored. See documentation of struct nla_policy for more details.
*
- * Returns 0 on success or a negative error code.
+ * Returns: 0 on success or a negative error code.
*/
static inline int __nla_validate_nested(const struct nlattr *start, int maxtype,
const struct nla_policy *policy,
@@ -2285,7 +2285,7 @@ nla_validate_nested_deprecated(const struct nlattr *start, int maxtype,
* nla_need_padding_for_64bit - test 64-bit alignment of the next attribute
* @skb: socket buffer the message is stored in
*
- * Return true if padding is needed to align the next attribute (nla_data()) to
+ * Return: true if padding is needed to align the next attribute (nla_data()) to
* a 64-bit aligned area.
*/
static inline bool nla_need_padding_for_64bit(struct sk_buff *skb)
@@ -2312,7 +2312,7 @@ static inline bool nla_need_padding_for_64bit(struct sk_buff *skb)
* This will only be done in architectures which do not have
* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS defined.
*
- * Returns zero on success or a negative error code.
+ * Returns: zero on success or a negative error code.
*/
static inline int nla_align_64bit(struct sk_buff *skb, int padattr)
{
diff --git a/include/net/netmem.h b/include/net/netmem.h
index 8a6e20be4b9d..1b58faa4f20f 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -72,6 +72,22 @@ static inline bool netmem_is_net_iov(const netmem_ref netmem)
return (__force unsigned long)netmem & NET_IOV;
}
+/**
+ * __netmem_to_page - unsafely get pointer to the &page backing @netmem
+ * @netmem: netmem reference to convert
+ *
+ * Unsafe version of netmem_to_page(). When @netmem is always page-backed,
+ * e.g. when it's a header buffer, performs faster and generates smaller
+ * object code (no check for the LSB, no WARN). When @netmem points to IOV,
+ * provokes undefined behaviour.
+ *
+ * Return: pointer to the &page (garbage if @netmem is not page-backed).
+ */
+static inline struct page *__netmem_to_page(netmem_ref netmem)
+{
+ return (__force struct page *)netmem;
+}
+
/* This conversion fails (returns NULL) if the netmem_ref is not struct page
* backed.
*/
@@ -80,7 +96,7 @@ static inline struct page *netmem_to_page(netmem_ref netmem)
if (WARN_ON_ONCE(netmem_is_net_iov(netmem)))
return NULL;
- return (__force struct page *)netmem;
+ return __netmem_to_page(netmem);
}
static inline struct net_iov *netmem_to_net_iov(netmem_ref netmem)
@@ -103,6 +119,17 @@ static inline netmem_ref page_to_netmem(struct page *page)
return (__force netmem_ref)page;
}
+/**
+ * virt_to_netmem - convert virtual memory pointer to a netmem reference
+ * @data: host memory pointer to convert
+ *
+ * Return: netmem reference to the &page backing this virtual address.
+ */
+static inline netmem_ref virt_to_netmem(const void *data)
+{
+ return page_to_netmem(virt_to_page(data));
+}
+
static inline int netmem_ref_count(netmem_ref netmem)
{
/* The non-pp refcount of net_iov is always 1. On net_iov, we only
@@ -127,6 +154,22 @@ static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem)
return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV);
}
+/**
+ * __netmem_get_pp - unsafely get pointer to the &page_pool backing @netmem
+ * @netmem: netmem reference to get the pointer from
+ *
+ * Unsafe version of netmem_get_pp(). When @netmem is always page-backed,
+ * e.g. when it's a header buffer, performs faster and generates smaller
+ * object code (avoids clearing the LSB). When @netmem points to IOV,
+ * provokes invalid memory access.
+ *
+ * Return: pointer to the &page_pool (garbage if @netmem is not page-backed).
+ */
+static inline struct page_pool *__netmem_get_pp(netmem_ref netmem)
+{
+ return __netmem_to_page(netmem)->pp;
+}
+
static inline struct page_pool *netmem_get_pp(netmem_ref netmem)
{
return __netmem_clear_lsb(netmem)->pp;
@@ -158,12 +201,43 @@ static inline netmem_ref netmem_compound_head(netmem_ref netmem)
return page_to_netmem(compound_head(netmem_to_page(netmem)));
}
+/**
+ * __netmem_address - unsafely get pointer to the memory backing @netmem
+ * @netmem: netmem reference to get the pointer for
+ *
+ * Unsafe version of netmem_address(). When @netmem is always page-backed,
+ * e.g. when it's a header buffer, performs faster and generates smaller
+ * object code (no check for the LSB). When @netmem points to IOV, provokes
+ * undefined behaviour.
+ *
+ * Return: pointer to the memory (garbage if @netmem is not page-backed).
+ */
+static inline void *__netmem_address(netmem_ref netmem)
+{
+ return page_address(__netmem_to_page(netmem));
+}
+
static inline void *netmem_address(netmem_ref netmem)
{
if (netmem_is_net_iov(netmem))
return NULL;
- return page_address(netmem_to_page(netmem));
+ return __netmem_address(netmem);
+}
+
+/**
+ * netmem_is_pfmemalloc - check if @netmem was allocated under memory pressure
+ * @netmem: netmem reference to check
+ *
+ * Return: true if @netmem is page-backed and the page was allocated under
+ * memory pressure, false otherwise.
+ */
+static inline bool netmem_is_pfmemalloc(netmem_ref netmem)
+{
+ if (netmem_is_net_iov(netmem))
+ return false;
+
+ return page_is_pfmemalloc(netmem_to_page(netmem));
}
static inline unsigned long netmem_get_dma_addr(netmem_ref netmem)
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 3c014170e001..46452da35206 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -175,6 +175,7 @@ struct netns_ipv4 {
u8 sysctl_tcp_retries2;
u8 sysctl_tcp_orphan_retries;
u8 sysctl_tcp_tw_reuse;
+ unsigned int sysctl_tcp_tw_reuse_delay;
int sysctl_tcp_fin_timeout;
u8 sysctl_tcp_sack;
u8 sysctl_tcp_window_scaling;
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 793e6fd78bc5..582a3d00cbe2 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -104,8 +104,7 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool)
*
* Get a page fragment from the page allocator or page_pool caches.
*
- * Return:
- * Return allocated page fragment, otherwise return NULL.
+ * Return: allocated page fragment, otherwise return NULL.
*/
static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool,
unsigned int *offset,
@@ -116,22 +115,22 @@ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool,
return page_pool_alloc_frag(pool, offset, size, gfp);
}
-static inline struct page *page_pool_alloc(struct page_pool *pool,
- unsigned int *offset,
- unsigned int *size, gfp_t gfp)
+static inline netmem_ref page_pool_alloc_netmem(struct page_pool *pool,
+ unsigned int *offset,
+ unsigned int *size, gfp_t gfp)
{
unsigned int max_size = PAGE_SIZE << pool->p.order;
- struct page *page;
+ netmem_ref netmem;
if ((*size << 1) > max_size) {
*size = max_size;
*offset = 0;
- return page_pool_alloc_pages(pool, gfp);
+ return page_pool_alloc_netmems(pool, gfp);
}
- page = page_pool_alloc_frag(pool, offset, *size, gfp);
- if (unlikely(!page))
- return NULL;
+ netmem = page_pool_alloc_frag_netmem(pool, offset, *size, gfp);
+ if (unlikely(!netmem))
+ return 0;
/* There is very likely not enough space for another fragment, so append
* the remaining size to the current fragment to avoid truesize
@@ -142,7 +141,23 @@ static inline struct page *page_pool_alloc(struct page_pool *pool,
pool->frag_offset = max_size;
}
- return page;
+ return netmem;
+}
+
+static inline netmem_ref page_pool_dev_alloc_netmem(struct page_pool *pool,
+ unsigned int *offset,
+ unsigned int *size)
+{
+ gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
+
+ return page_pool_alloc_netmem(pool, offset, size, gfp);
+}
+
+static inline struct page *page_pool_alloc(struct page_pool *pool,
+ unsigned int *offset,
+ unsigned int *size, gfp_t gfp)
+{
+ return netmem_to_page(page_pool_alloc_netmem(pool, offset, size, gfp));
}
/**
@@ -155,8 +170,7 @@ static inline struct page *page_pool_alloc(struct page_pool *pool,
* depending on the requested size in order to allocate memory with least memory
* utilization and performance penalty.
*
- * Return:
- * Return allocated page or page fragment, otherwise return NULL.
+ * Return: allocated page or page fragment, otherwise return NULL.
*/
static inline struct page *page_pool_dev_alloc(struct page_pool *pool,
unsigned int *offset,
@@ -190,8 +204,7 @@ static inline void *page_pool_alloc_va(struct page_pool *pool,
* This is just a thin wrapper around the page_pool_alloc() API, and
* it returns va of the allocated page or page fragment.
*
- * Return:
- * Return the va for the allocated page or page fragment, otherwise return NULL.
+ * Return: the va for the allocated page or page fragment, otherwise return NULL.
*/
static inline void *page_pool_dev_alloc_va(struct page_pool *pool,
unsigned int *size)
@@ -294,7 +307,7 @@ static inline long page_pool_unref_page(struct page *page, long nr)
static inline void page_pool_ref_netmem(netmem_ref netmem)
{
- atomic_long_inc(&netmem_to_page(netmem)->pp_ref_count);
+ atomic_long_inc(netmem_get_pp_ref_count_ref(netmem));
}
static inline void page_pool_ref_page(struct page *page)
@@ -302,7 +315,7 @@ static inline void page_pool_ref_page(struct page *page)
page_pool_ref_netmem(page_to_netmem(page));
}
-static inline bool page_pool_is_last_ref(netmem_ref netmem)
+static inline bool page_pool_unref_and_test(netmem_ref netmem)
{
/* If page_pool_unref_page() returns 0, we were the last user */
return page_pool_unref_netmem(netmem, 1) == 0;
@@ -317,7 +330,7 @@ static inline void page_pool_put_netmem(struct page_pool *pool,
* allow registering MEM_TYPE_PAGE_POOL, but shield linker.
*/
#ifdef CONFIG_PAGE_POOL
- if (!page_pool_is_last_ref(netmem))
+ if (!page_pool_unref_and_test(netmem))
return;
page_pool_put_unrefed_netmem(pool, netmem, dma_sync_size, allow_direct);
@@ -418,7 +431,21 @@ static inline dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem)
*/
static inline dma_addr_t page_pool_get_dma_addr(const struct page *page)
{
- return page_pool_get_dma_addr_netmem(page_to_netmem((struct page *)page));
+ dma_addr_t ret = page->dma_addr;
+
+ if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA)
+ ret <<= PAGE_SHIFT;
+
+ return ret;
+}
+
+static inline void __page_pool_dma_sync_for_cpu(const struct page_pool *pool,
+ const dma_addr_t dma_addr,
+ u32 offset, u32 dma_sync_size)
+{
+ dma_sync_single_range_for_cpu(pool->p.dev, dma_addr,
+ offset + pool->p.offset, dma_sync_size,
+ page_pool_get_dma_dir(pool));
}
/**
@@ -437,10 +464,21 @@ static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool,
const struct page *page,
u32 offset, u32 dma_sync_size)
{
- dma_sync_single_range_for_cpu(pool->p.dev,
- page_pool_get_dma_addr(page),
- offset + pool->p.offset, dma_sync_size,
- page_pool_get_dma_dir(pool));
+ __page_pool_dma_sync_for_cpu(pool, page_pool_get_dma_addr(page), offset,
+ dma_sync_size);
+}
+
+static inline void
+page_pool_dma_sync_netmem_for_cpu(const struct page_pool *pool,
+ const netmem_ref netmem, u32 offset,
+ u32 dma_sync_size)
+{
+ if (!pool->dma_sync_for_cpu)
+ return;
+
+ __page_pool_dma_sync_for_cpu(pool,
+ page_pool_get_dma_addr_netmem(netmem),
+ offset, dma_sync_size);
}
static inline bool page_pool_put(struct page_pool *pool)
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index c022c410abe3..7f405672b089 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -164,7 +164,8 @@ struct page_pool {
bool has_init_callback:1; /* slow::init_callback is set */
bool dma_map:1; /* Perform DMA mapping */
- bool dma_sync:1; /* Perform DMA sync */
+ bool dma_sync:1; /* Perform DMA sync for device */
+ bool dma_sync_for_cpu:1; /* Perform DMA sync for cpu */
#ifdef CONFIG_PAGE_POOL_STATS
bool system:1; /* This is a global percpu pool */
#endif
@@ -236,13 +237,12 @@ struct page_pool {
struct {
struct hlist_node list;
u64 detach_time;
- u32 napi_id;
u32 id;
} user;
};
struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
-netmem_ref page_pool_alloc_netmem(struct page_pool *pool, gfp_t gfp);
+netmem_ref page_pool_alloc_netmems(struct page_pool *pool, gfp_t gfp);
struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset,
unsigned int size, gfp_t gfp);
netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool,
@@ -259,8 +259,7 @@ void page_pool_disable_direct_recycling(struct page_pool *pool);
void page_pool_destroy(struct page_pool *pool);
void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
const struct xdp_mem_info *mem);
-void page_pool_put_page_bulk(struct page_pool *pool, void **data,
- int count);
+void page_pool_put_netmem_bulk(netmem_ref *data, u32 count);
#else
static inline void page_pool_destroy(struct page_pool *pool)
{
@@ -272,8 +271,7 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool,
{
}
-static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
- int count)
+static inline void page_pool_put_netmem_bulk(netmem_ref *data, u32 count)
{
}
#endif
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index cf199af85c52..c64fd896b1f9 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -75,11 +75,11 @@ static inline bool tcf_block_non_null_shared(struct tcf_block *block)
}
#ifdef CONFIG_NET_CLS_ACT
-DECLARE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key);
+DECLARE_STATIC_KEY_FALSE(tcf_sw_enabled_key);
static inline bool tcf_block_bypass_sw(struct tcf_block *block)
{
- return block && block->bypass_wanted;
+ return block && !atomic_read(&block->useswcnt);
}
#endif
@@ -319,7 +319,7 @@ tcf_exts_hw_stats_update(const struct tcf_exts *exts,
* tcf_exts_has_actions - check if at least one action is present
* @exts: tc filter extensions handle
*
- * Returns true if at least one action is present.
+ * Returns: true if at least one action is present.
*/
static inline bool tcf_exts_has_actions(struct tcf_exts *exts)
{
@@ -501,7 +501,7 @@ int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *,
* through all ematches respecting their logic relations returning
* as soon as the result is obvious.
*
- * Returns 1 if the ematch tree as-one matches, no ematches are configured
+ * Returns: 1 if the ematch tree as-one matches, no ematches are configured
* or ematch is not enabled in the kernel, otherwise 0 is returned.
*/
static inline int tcf_em_tree_match(struct sk_buff *skb,
@@ -760,6 +760,15 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common,
cls_common->extack = extack;
}
+static inline void tcf_proto_update_usesw(struct tcf_proto *tp, u32 flags)
+{
+ if (tp->usesw)
+ return;
+ if (tc_skip_sw(flags) && tc_in_hw(flags))
+ return;
+ tp->usesw = true;
+}
+
#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb)
{
diff --git a/include/net/route.h b/include/net/route.h
index 84cb1e04f5cd..c605fd5ec0c0 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -28,6 +28,7 @@
#include <net/arp.h>
#include <net/ndisc.h>
#include <net/inet_dscp.h>
+#include <net/sock.h>
#include <linux/in_route.h>
#include <linux/rtnetlink.h>
#include <linux/rcupdate.h>
@@ -129,6 +130,33 @@ struct in_device;
int ip_rt_init(void);
void rt_cache_flush(struct net *net);
void rt_flush_dev(struct net_device *dev);
+
+static inline void inet_sk_init_flowi4(const struct inet_sock *inet,
+ struct flowi4 *fl4)
+{
+ const struct ip_options_rcu *ip4_opt;
+ const struct sock *sk;
+ __be32 daddr;
+
+ rcu_read_lock();
+ ip4_opt = rcu_dereference(inet->inet_opt);
+
+ /* Source routing option overrides the socket destination address */
+ if (ip4_opt && ip4_opt->opt.srr)
+ daddr = ip4_opt->opt.faddr;
+ else
+ daddr = inet->inet_daddr;
+ rcu_read_unlock();
+
+ sk = &inet->sk;
+ flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark),
+ ip_sock_rt_tos(sk), ip_sock_rt_scope(sk),
+ sk->sk_protocol, inet_sk_flowi_flags(sk), daddr,
+ inet->inet_saddr, inet->inet_dport,
+ inet->inet_sport, sk->sk_uid);
+ security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
+}
+
struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
const struct sk_buff *skb);
struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
@@ -185,20 +213,6 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi
return ip_route_output_flow(net, fl4, sk);
}
-static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 *fl4,
- __be32 daddr, __be32 saddr,
- __be32 gre_key, __u8 tos, int oif)
-{
- memset(fl4, 0, sizeof(*fl4));
- fl4->flowi4_oif = oif;
- fl4->daddr = daddr;
- fl4->saddr = saddr;
- fl4->flowi4_tos = tos;
- fl4->flowi4_proto = IPPROTO_GRE;
- fl4->fl4_gre_key = gre_key;
- return ip_route_output_key(net, fl4);
-}
-
enum skb_drop_reason
ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
dscp_t dscp, struct net_device *dev,
@@ -368,10 +382,15 @@ static inline int inet_iif(const struct sk_buff *skb)
static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
{
int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
- struct net *net = dev_net(dst->dev);
- if (hoplimit == 0)
+ if (hoplimit == 0) {
+ const struct net *net;
+
+ rcu_read_lock();
+ net = dev_net_rcu(dst->dev);
hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl);
+ rcu_read_unlock();
+ }
return hoplimit;
}
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 5d74fa7e694c..d48c657191cd 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -425,6 +425,7 @@ struct tcf_proto {
spinlock_t lock;
bool deleting;
bool counted;
+ bool usesw;
refcount_t refcnt;
struct rcu_head rcu;
struct hlist_node destroy_ht_node;
@@ -474,9 +475,7 @@ struct tcf_block {
struct flow_block flow_block;
struct list_head owner_list;
bool keep_dst;
- bool bypass_wanted;
- atomic_t filtercnt; /* Number of filters */
- atomic_t skipswcnt; /* Number of skip_sw filters */
+ atomic_t useswcnt;
atomic_t offloadcnt; /* Number of oddloaded filters */
unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */
unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */
@@ -852,7 +851,7 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
}
static inline void _bstats_update(struct gnet_stats_basic_sync *bstats,
- __u64 bytes, __u32 packets)
+ __u64 bytes, __u64 packets)
{
u64_stats_update_begin(&bstats->syncp);
u64_stats_add(&bstats->bytes, bytes);
@@ -1245,6 +1244,14 @@ static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch,
return NET_XMIT_DROP;
}
+static inline int qdisc_drop_reason(struct sk_buff *skb, struct Qdisc *sch,
+ struct sk_buff **to_free,
+ enum skb_drop_reason reason)
+{
+ tcf_set_drop_reason(skb, reason);
+ return qdisc_drop(skb, sch, to_free);
+}
+
static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
diff --git a/include/net/scm.h b/include/net/scm.h
index 0d35c7c77a74..22bb49589fde 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -105,16 +105,16 @@ static __inline__ int scm_send(struct socket *sock, struct msghdr *msg,
#ifdef CONFIG_SECURITY_NETWORK
static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm)
{
- char *secdata;
- u32 seclen;
+ struct lsm_context ctx;
int err;
if (test_bit(SOCK_PASSSEC, &sock->flags)) {
- err = security_secid_to_secctx(scm->secid, &secdata, &seclen);
+ err = security_secid_to_secctx(scm->secid, &ctx);
- if (!err) {
- put_cmsg(msg, SOL_SOCKET, SCM_SECURITY, seclen, secdata);
- security_release_secctx(secdata, seclen);
+ if (err >= 0) {
+ put_cmsg(msg, SOL_SOCKET, SCM_SECURITY, ctx.len,
+ ctx.context);
+ security_release_secctx(&ctx);
}
}
}
diff --git a/include/net/sock.h b/include/net/sock.h
index 7464e9f9f47c..8036b3b79cd8 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -953,6 +953,7 @@ enum sock_flags {
SOCK_XDP, /* XDP is attached */
SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */
SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */
+ SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */
};
#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -1527,7 +1528,7 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size)
}
static inline bool
-sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size)
+__sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc)
{
int delta;
@@ -1535,7 +1536,13 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size)
return true;
delta = size - sk->sk_forward_alloc;
return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) ||
- skb_pfmemalloc(skb);
+ pfmemalloc;
+}
+
+static inline bool
+sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size)
+{
+ return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb));
}
static inline int sk_unused_reserved_mem(const struct sock *sk)
@@ -1814,13 +1821,15 @@ struct sockcm_cookie {
u32 mark;
u32 tsflags;
u32 ts_opt_id;
+ u32 priority;
};
static inline void sockcm_init(struct sockcm_cookie *sockc,
const struct sock *sk)
{
*sockc = (struct sockcm_cookie) {
- .tsflags = READ_ONCE(sk->sk_tsflags)
+ .tsflags = READ_ONCE(sk->sk_tsflags),
+ .priority = READ_ONCE(sk->sk_priority),
};
}
@@ -2291,7 +2300,7 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq)
}
/**
- * sock_poll_wait - place memory barrier behind the poll_wait call.
+ * sock_poll_wait - wrapper for the poll_wait call.
* @filp: file
* @sock: socket to wait on
* @p: poll_table
@@ -2301,15 +2310,12 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq)
static inline void sock_poll_wait(struct file *filp, struct socket *sock,
poll_table *p)
{
- if (!poll_does_not_wait(p)) {
- poll_wait(filp, &sock->wq.wait, p);
- /* We need to be sure we are in sync with the
- * socket flags modification.
- *
- * This memory barrier is paired in the wq_has_sleeper.
- */
- smp_mb();
- }
+ /* Provides a barrier we need to be sure we are in sync
+ * with the socket flags modification.
+ *
+ * This memory barrier is paired in the wq_has_sleeper.
+ */
+ poll_wait(filp, &sock->wq.wait, p);
}
static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk)
@@ -2658,7 +2664,8 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
{
#define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \
(1UL << SOCK_RCVTSTAMP) | \
- (1UL << SOCK_RCVMARK))
+ (1UL << SOCK_RCVMARK) |\
+ (1UL << SOCK_RCVPRIORITY))
#define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \
SOF_TIMESTAMPING_RAW_HARDWARE)
diff --git a/include/net/strparser.h b/include/net/strparser.h
index 41e2ce9e9e10..0a83010b3a64 100644
--- a/include/net/strparser.h
+++ b/include/net/strparser.h
@@ -43,6 +43,8 @@ struct strparser;
struct strp_callbacks {
int (*parse_msg)(struct strparser *strp, struct sk_buff *skb);
void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb);
+ int (*read_sock)(struct strparser *strp, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor);
int (*read_sock_done)(struct strparser *strp, int err);
void (*abort_parser)(struct strparser *strp, int err);
void (*lock)(struct strparser *strp);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e9b37b76e894..2d08473a6dc0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -41,6 +41,7 @@
#include <net/inet_ecn.h>
#include <net/dst.h>
#include <net/mptcp.h>
+#include <net/xfrm.h>
#include <linux/seq_file.h>
#include <linux/memcontrol.h>
@@ -683,6 +684,19 @@ void tcp_fin(struct sock *sk);
void tcp_check_space(struct sock *sk);
void tcp_sack_compress_send_ack(struct sock *sk);
+static inline void tcp_cleanup_skb(struct sk_buff *skb)
+{
+ skb_dst_drop(skb);
+ secpath_reset(skb);
+}
+
+static inline void tcp_add_receive_queue(struct sock *sk, struct sk_buff *skb)
+{
+ DEBUG_NET_WARN_ON_ONCE(skb_dst(skb));
+ DEBUG_NET_WARN_ON_ONCE(secpath_exists(skb));
+ __skb_queue_tail(&sk->sk_receive_queue, skb);
+}
+
/* tcp_timer.c */
void tcp_init_xmit_timers(struct sock *);
static inline void tcp_clear_xmit_timers(struct sock *sk)
@@ -729,6 +743,9 @@ void tcp_get_info(struct sock *, struct tcp_info *);
/* Read 'sendfile()'-style from a TCP socket */
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
sk_read_actor_t recv_actor);
+int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor, bool noack,
+ u32 *copied_seq);
int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor);
struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off);
void tcp_read_done(struct sock *sk, size_t len);
@@ -1817,7 +1834,7 @@ int tcp_sigpool_hash_skb_data(struct tcp_sigpool *hp,
* @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash()
* @c: returned tcp_sigpool for usage (uninitialized on failure)
*
- * Returns 0 on success, error otherwise.
+ * Returns: 0 on success, error otherwise.
*/
int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c);
/**
@@ -2599,6 +2616,11 @@ struct sk_psock;
#ifdef CONFIG_BPF_SYSCALL
int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
+#ifdef CONFIG_BPF_STREAM_PARSER
+struct strparser;
+int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor);
+#endif /* CONFIG_BPF_STREAM_PARSER */
#endif /* CONFIG_BPF_SYSCALL */
#ifdef CONFIG_INET
diff --git a/include/net/tls.h b/include/net/tls.h
index 61fef2880114..857340338b69 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -59,6 +59,8 @@ struct tls_rec;
#define TLS_CRYPTO_INFO_READY(info) ((info)->cipher_type)
+#define TLS_HANDSHAKE_KEYUPDATE 24 /* rfc8446 B.3: Key update */
+
#define TLS_AAD_SPACE_SIZE 13
#define TLS_MAX_IV_SIZE 16
@@ -130,6 +132,7 @@ struct tls_sw_context_rx {
u8 async_capable:1;
u8 zc_capable:1;
u8 reader_contended:1;
+ bool key_update_pending;
struct tls_strparser strp;
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 33ba6fc151cf..2dd23ee2bacd 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -227,6 +227,7 @@ struct vxlan_config {
unsigned int addrmax;
bool no_share;
enum ifla_vxlan_df df;
+ struct vxlanhdr reserved_bits;
};
enum {
diff --git a/include/net/xdp.h b/include/net/xdp.h
index e6770dd40c91..4dafc5e021f1 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -11,6 +11,8 @@
#include <linux/netdevice.h>
#include <linux/skbuff.h> /* skb_shared_info */
+#include <net/page_pool/types.h>
+
/**
* DOC: XDP RX-queue information
*
@@ -62,7 +64,6 @@ struct xdp_rxq_info {
u32 queue_index;
u32 reg_state;
struct xdp_mem_info mem;
- unsigned int napi_id;
u32 frag_size;
} ____cacheline_aligned; /* perf critical, avoid false-sharing */
@@ -88,7 +89,7 @@ struct xdp_buff {
u32 flags; /* supported values defined in xdp_buff_flags */
};
-static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp)
+static __always_inline bool xdp_buff_has_frags(const struct xdp_buff *xdp)
{
return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS);
}
@@ -103,7 +104,8 @@ static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp)
xdp->flags &= ~XDP_FLAGS_HAS_FRAGS;
}
-static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp)
+static __always_inline bool
+xdp_buff_is_frag_pfmemalloc(const struct xdp_buff *xdp)
{
return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC);
}
@@ -144,15 +146,16 @@ xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start,
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
static inline struct skb_shared_info *
-xdp_get_shared_info_from_buff(struct xdp_buff *xdp)
+xdp_get_shared_info_from_buff(const struct xdp_buff *xdp)
{
return (struct skb_shared_info *)xdp_data_hard_end(xdp);
}
-static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp)
+static __always_inline unsigned int
+xdp_get_buff_len(const struct xdp_buff *xdp)
{
unsigned int len = xdp->data_end - xdp->data;
- struct skb_shared_info *sinfo;
+ const struct skb_shared_info *sinfo;
if (likely(!xdp_buff_has_frags(xdp)))
goto out;
@@ -163,26 +166,114 @@ out:
return len;
}
+void xdp_return_frag(netmem_ref netmem, const struct xdp_buff *xdp);
+
+/**
+ * __xdp_buff_add_frag - attach frag to &xdp_buff
+ * @xdp: XDP buffer to attach the frag to
+ * @netmem: network memory containing the frag
+ * @offset: offset at which the frag starts
+ * @size: size of the frag
+ * @truesize: total memory size occupied by the frag
+ * @try_coalesce: whether to try coalescing the frags (not valid for XSk)
+ *
+ * Attach frag to the XDP buffer. If it currently has no frags attached,
+ * initialize the related fields, otherwise check that the frag number
+ * didn't reach the limit of ``MAX_SKB_FRAGS``. If possible, try coalescing
+ * the frag with the previous one.
+ * The function doesn't check/update the pfmemalloc bit. Please use the
+ * non-underscored wrapper in drivers.
+ *
+ * Return: true on success, false if there's no space for the frag in
+ * the shared info struct.
+ */
+static inline bool __xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem,
+ u32 offset, u32 size, u32 truesize,
+ bool try_coalesce)
+{
+ struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+ skb_frag_t *prev;
+ u32 nr_frags;
+
+ if (!xdp_buff_has_frags(xdp)) {
+ xdp_buff_set_frags_flag(xdp);
+
+ nr_frags = 0;
+ sinfo->xdp_frags_size = 0;
+ sinfo->xdp_frags_truesize = 0;
+
+ goto fill;
+ }
+
+ nr_frags = sinfo->nr_frags;
+ prev = &sinfo->frags[nr_frags - 1];
+
+ if (try_coalesce && netmem == skb_frag_netmem(prev) &&
+ offset == skb_frag_off(prev) + skb_frag_size(prev)) {
+ skb_frag_size_add(prev, size);
+ /* Guaranteed to only decrement the refcount */
+ xdp_return_frag(netmem, xdp);
+ } else if (unlikely(nr_frags == MAX_SKB_FRAGS)) {
+ return false;
+ } else {
+fill:
+ __skb_fill_netmem_desc_noacc(sinfo, nr_frags++, netmem,
+ offset, size);
+ }
+
+ sinfo->nr_frags = nr_frags;
+ sinfo->xdp_frags_size += size;
+ sinfo->xdp_frags_truesize += truesize;
+
+ return true;
+}
+
+/**
+ * xdp_buff_add_frag - attach frag to &xdp_buff
+ * @xdp: XDP buffer to attach the frag to
+ * @netmem: network memory containing the frag
+ * @offset: offset at which the frag starts
+ * @size: size of the frag
+ * @truesize: total memory size occupied by the frag
+ *
+ * Version of __xdp_buff_add_frag() which takes care of the pfmemalloc bit.
+ *
+ * Return: true on success, false if there's no space for the frag in
+ * the shared info struct.
+ */
+static inline bool xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem,
+ u32 offset, u32 size, u32 truesize)
+{
+ if (!__xdp_buff_add_frag(xdp, netmem, offset, size, truesize, true))
+ return false;
+
+ if (unlikely(netmem_is_pfmemalloc(netmem)))
+ xdp_buff_set_frag_pfmemalloc(xdp);
+
+ return true;
+}
+
struct xdp_frame {
void *data;
- u16 len;
- u16 headroom;
+ u32 len;
+ u32 headroom;
u32 metasize; /* uses lower 8-bits */
/* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time,
- * while mem info is valid on remote CPU.
+ * while mem_type is valid on remote CPU.
*/
- struct xdp_mem_info mem;
+ enum xdp_mem_type mem_type:32;
struct net_device *dev_rx; /* used by cpumap */
u32 frame_sz;
u32 flags; /* supported values defined in xdp_buff_flags */
};
-static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame)
+static __always_inline bool xdp_frame_has_frags(const struct xdp_frame *frame)
{
return !!(frame->flags & XDP_FLAGS_HAS_FRAGS);
}
-static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame)
+static __always_inline bool
+xdp_frame_is_frag_pfmemalloc(const struct xdp_frame *frame)
{
return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC);
}
@@ -190,18 +281,16 @@ static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame
#define XDP_BULK_QUEUE_SIZE 16
struct xdp_frame_bulk {
int count;
- void *xa;
- void *q[XDP_BULK_QUEUE_SIZE];
+ netmem_ref q[XDP_BULK_QUEUE_SIZE];
};
static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq)
{
- /* bq->count will be zero'ed when bq->xa gets updated */
- bq->xa = NULL;
+ bq->count = 0;
}
static inline struct skb_shared_info *
-xdp_get_shared_info_from_frame(struct xdp_frame *frame)
+xdp_get_shared_info_from_frame(const struct xdp_frame *frame)
{
void *data_hard_start = frame->data - frame->headroom - sizeof(*frame);
@@ -227,7 +316,14 @@ xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags,
unsigned int size, unsigned int truesize,
bool pfmemalloc)
{
- skb_shinfo(skb)->nr_frags = nr_frags;
+ struct skb_shared_info *sinfo = skb_shinfo(skb);
+
+ sinfo->nr_frags = nr_frags;
+ /*
+ * ``destructor_arg`` is unionized with ``xdp_frags_{,true}size``,
+ * reset it after that these fields aren't used anymore.
+ */
+ sinfo->destructor_arg = NULL;
skb->len += size;
skb->data_len += size;
@@ -239,6 +335,8 @@ xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags,
void xdp_warn(const char *msg, const char *func, const int line);
#define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)
+struct sk_buff *xdp_build_skb_from_buff(const struct xdp_buff *xdp);
+struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp);
struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp);
struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
struct sk_buff *skb,
@@ -249,7 +347,8 @@ int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp);
struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf);
static inline
-void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
+void xdp_convert_frame_to_buff(const struct xdp_frame *frame,
+ struct xdp_buff *xdp)
{
xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame);
xdp->data = frame->data;
@@ -260,7 +359,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
}
static inline
-int xdp_update_frame_from_buff(struct xdp_buff *xdp,
+int xdp_update_frame_from_buff(const struct xdp_buff *xdp,
struct xdp_frame *xdp_frame)
{
int metasize, headroom;
@@ -302,24 +401,33 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0))
return NULL;
- /* rxq only valid until napi_schedule ends, convert to xdp_mem_info */
- xdp_frame->mem = xdp->rxq->mem;
+ /* rxq only valid until napi_schedule ends, convert to xdp_mem_type */
+ xdp_frame->mem_type = xdp->rxq->mem.type;
return xdp_frame;
}
-void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
- struct xdp_buff *xdp);
+void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type,
+ bool napi_direct, struct xdp_buff *xdp);
void xdp_return_frame(struct xdp_frame *xdpf);
void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
void xdp_return_buff(struct xdp_buff *xdp);
-void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq);
void xdp_return_frame_bulk(struct xdp_frame *xdpf,
struct xdp_frame_bulk *bq);
-static __always_inline unsigned int xdp_get_frame_len(struct xdp_frame *xdpf)
+static inline void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq)
+{
+ if (unlikely(!bq->count))
+ return;
+
+ page_pool_put_netmem_bulk(bq->q, bq->count);
+ bq->count = 0;
+}
+
+static __always_inline unsigned int
+xdp_get_frame_len(const struct xdp_frame *xdpf)
{
- struct skb_shared_info *sinfo;
+ const struct skb_shared_info *sinfo;
unsigned int len = xdpf->len;
if (likely(!xdp_frame_has_frags(xdpf)))
@@ -351,6 +459,38 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq);
int xdp_reg_mem_model(struct xdp_mem_info *mem,
enum xdp_mem_type type, void *allocator);
void xdp_unreg_mem_model(struct xdp_mem_info *mem);
+int xdp_reg_page_pool(struct page_pool *pool);
+void xdp_unreg_page_pool(const struct page_pool *pool);
+void xdp_rxq_info_attach_page_pool(struct xdp_rxq_info *xdp_rxq,
+ const struct page_pool *pool);
+
+/**
+ * xdp_rxq_info_attach_mem_model - attach registered mem info to RxQ info
+ * @xdp_rxq: XDP RxQ info to attach the memory info to
+ * @mem: already registered memory info
+ *
+ * If the driver registers its memory providers manually, it must use this
+ * function instead of xdp_rxq_info_reg_mem_model().
+ */
+static inline void
+xdp_rxq_info_attach_mem_model(struct xdp_rxq_info *xdp_rxq,
+ const struct xdp_mem_info *mem)
+{
+ xdp_rxq->mem = *mem;
+}
+
+/**
+ * xdp_rxq_info_detach_mem_model - detach registered mem info from RxQ info
+ * @xdp_rxq: XDP RxQ info to detach the memory info from
+ *
+ * If the driver registers its memory providers manually and then attaches it
+ * via xdp_rxq_info_attach_mem_model(), it must call this function before
+ * xdp_rxq_info_unreg().
+ */
+static inline void xdp_rxq_info_detach_mem_model(struct xdp_rxq_info *xdp_rxq)
+{
+ xdp_rxq->mem = (struct xdp_mem_info){ };
+}
/* Drivers not supporting XDP metadata can use this helper, which
* rejects any room expansion for metadata as a result.
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 40085afd9160..784cd34f5bba 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -59,15 +59,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
xp_fill_cb(pool, desc);
}
-static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
-{
-#ifdef CONFIG_NET_RX_BUSY_POLL
- return pool->heads[0].xdp.rxq->napi_id;
-#else
- return 0;
-#endif
-}
-
static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
unsigned long attrs)
{
@@ -101,7 +92,7 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
return xp_alloc(pool);
}
-static inline bool xsk_is_eop_desc(struct xdp_desc *desc)
+static inline bool xsk_is_eop_desc(const struct xdp_desc *desc)
{
return !xp_mb_desc(desc);
}
@@ -136,14 +127,24 @@ out:
xp_free(xskb);
}
-static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
+static inline bool xsk_buff_add_frag(struct xdp_buff *head,
+ struct xdp_buff *xdp)
{
- struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp);
+ const void *data = xdp->data;
+ struct xdp_buff_xsk *frag;
+
+ if (!__xdp_buff_add_frag(head, virt_to_netmem(data),
+ offset_in_page(data), xdp->data_end - data,
+ xdp->frame_sz, false))
+ return false;
+ frag = container_of(xdp, struct xdp_buff_xsk, xdp);
list_add_tail(&frag->list_node, &frag->pool->xskb_list);
+
+ return true;
}
-static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
+static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
{
struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
struct xdp_buff *ret = NULL;
@@ -200,7 +201,8 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
XDP_TXMD_FLAGS_CHECKSUM | \
0)
-static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta)
+static inline bool
+xsk_buff_valid_tx_metadata(const struct xsk_tx_metadata *meta)
{
return !(meta->flags & ~XDP_TXMD_FLAGS_VALID);
}
@@ -306,11 +308,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
{
}
-static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
-{
- return 0;
-}
-
static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
unsigned long attrs)
{
@@ -337,7 +334,7 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
return NULL;
}
-static inline bool xsk_is_eop_desc(struct xdp_desc *desc)
+static inline bool xsk_is_eop_desc(const struct xdp_desc *desc)
{
return false;
}
@@ -356,11 +353,13 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
{
}
-static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
+static inline bool xsk_buff_add_frag(struct xdp_buff *head,
+ struct xdp_buff *xdp)
{
+ return false;
}
-static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
+static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
{
return NULL;
}
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 32c09e85a64c..ed4b83696c77 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -38,6 +38,7 @@
#define XFRM_PROTO_COMP 108
#define XFRM_PROTO_IPIP 4
#define XFRM_PROTO_IPV6 41
+#define XFRM_PROTO_IPTFS IPPROTO_AGGFRAG
#define XFRM_PROTO_ROUTING IPPROTO_ROUTING
#define XFRM_PROTO_DSTOPTS IPPROTO_DSTOPTS
@@ -213,6 +214,7 @@ struct xfrm_state {
u16 family;
xfrm_address_t saddr;
int header_len;
+ int enc_hdr_len;
int trailer_len;
u32 extra_flags;
struct xfrm_mark smark;
@@ -303,6 +305,9 @@ struct xfrm_state {
* interpreted by xfrm_type methods. */
void *data;
u8 dir;
+
+ const struct xfrm_mode_cbs *mode_cbs;
+ void *mode_data;
};
static inline struct net *xs_net(struct xfrm_state *x)
@@ -460,6 +465,45 @@ struct xfrm_type_offload {
int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family);
void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
+/**
+ * struct xfrm_mode_cbs - XFRM mode callbacks
+ * @owner: module owner or NULL
+ * @init_state: Add/init mode specific state in `xfrm_state *x`
+ * @clone_state: Copy mode specific values from `orig` to new state `x`
+ * @destroy_state: Cleanup mode specific state from `xfrm_state *x`
+ * @user_init: Process mode specific netlink attributes from user
+ * @copy_to_user: Add netlink attributes to `attrs` based on state in `x`
+ * @sa_len: Return space required to store mode specific netlink attributes
+ * @get_inner_mtu: Return avail payload space after removing encap overhead
+ * @input: Process received packet from SA using mode
+ * @output: Output given packet using mode
+ * @prepare_output: Add mode specific encapsulation to packet in skb. On return
+ * `transport_header` should point at ESP header, `network_header` should
+ * point at outer IP header and `mac_header` should opint at the
+ * protocol/nexthdr field of the outer IP.
+ *
+ * One should examine and understand the specific uses of these callbacks in
+ * xfrm for further detail on how and when these functions are called. RTSL.
+ */
+struct xfrm_mode_cbs {
+ struct module *owner;
+ int (*init_state)(struct xfrm_state *x);
+ int (*clone_state)(struct xfrm_state *x, struct xfrm_state *orig);
+ void (*destroy_state)(struct xfrm_state *x);
+ int (*user_init)(struct net *net, struct xfrm_state *x,
+ struct nlattr **attrs,
+ struct netlink_ext_ack *extack);
+ int (*copy_to_user)(struct xfrm_state *x, struct sk_buff *skb);
+ unsigned int (*sa_len)(const struct xfrm_state *x);
+ u32 (*get_inner_mtu)(struct xfrm_state *x, int outer_mtu);
+ int (*input)(struct xfrm_state *x, struct sk_buff *skb);
+ int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
+ int (*prepare_output)(struct xfrm_state *x, struct sk_buff *skb);
+};
+
+int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs);
+void xfrm_unregister_mode_cbs(u8 mode);
+
static inline int xfrm_af2proto(unsigned int family)
{
switch(family) {
@@ -1224,9 +1268,19 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir,
if (xo) {
x = xfrm_input_state(skb);
- if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
- return (xo->flags & CRYPTO_DONE) &&
- (xo->status & CRYPTO_SUCCESS);
+ if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) {
+ bool check = (xo->flags & CRYPTO_DONE) &&
+ (xo->status & CRYPTO_SUCCESS);
+
+ /* The packets here are plain ones and secpath was
+ * needed to indicate that hardware already handled
+ * them and there is no need to do nothing in addition.
+ *
+ * Consume secpath which was set by drivers.
+ */
+ secpath_reset(skb);
+ return check;
+ }
}
return __xfrm_check_nopolicy(net, skb, dir) ||
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index bb03cee716b3..50779406bc2d 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -29,7 +29,7 @@ struct xdp_buff_xsk {
dma_addr_t frame_dma;
struct xsk_buff_pool *pool;
struct list_head list_node;
-};
+} __aligned_largest;
#define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
#define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t))
@@ -183,7 +183,7 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool,
!(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK);
}
-static inline bool xp_mb_desc(struct xdp_desc *desc)
+static inline bool xp_mb_desc(const struct xdp_desc *desc)
{
return desc->options & XDP_PKT_CONTD;
}