Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h
index a713780..c80539b 100644
--- a/include/net/6lowpan.h
+++ b/include/net/6lowpan.h
@@ -138,7 +138,7 @@
struct lowpan_iphc_ctx_table ctx;
/* must be last */
- u8 priv[0] __aligned(sizeof(void *));
+ u8 priv[] __aligned(sizeof(void *));
};
struct lowpan_802154_neigh {
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index acc60d8..dd5b5bd 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -73,7 +73,6 @@
* @wq: wait_queue for the client to block on for this request
* @tc: the request fcall structure
* @rc: the response fcall structure
- * @aux: transport specific data (provided for trans_fd migration)
* @req_list: link for higher level objects to chain requests
*/
struct p9_req_t {
@@ -83,7 +82,6 @@
wait_queue_head_t wq;
struct p9_fcall tc;
struct p9_fcall rc;
- void *aux;
struct list_head req_list;
};
@@ -200,6 +198,8 @@
int p9_client_remove(struct p9_fid *fid);
int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags);
int p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err);
+int p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to,
+ int *err);
int p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err);
int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset);
int p9dirent_read(struct p9_client *clnt, char *buf, int len,
diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h
index 98a2be2..3eb4261 100644
--- a/include/net/9p/transport.h
+++ b/include/net/9p/transport.h
@@ -25,7 +25,7 @@
* @request: member function to issue a request to the transport
* @cancel: member function to cancel a request (if it hasn't been sent)
* @cancelled: member function to notify that a cancelled request will not
- * not receive a reply
+ * receive a reply
*
* This is the basic API for a transport module which is registered by the
* transport module with the 9P core network module and used by the client
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 4dabe47..2c88b8a 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -23,7 +23,6 @@
struct tc_action {
const struct tc_action_ops *ops;
__u32 type; /* for backward compat(TCA_OLD_COMPAT) */
- __u32 order;
struct tcf_idrinfo *idrinfo;
u32 tcfa_index;
@@ -41,6 +40,10 @@
struct gnet_stats_queue __percpu *cpu_qstats;
struct tc_cookie __rcu *act_cookie;
struct tcf_chain __rcu *goto_chain;
+ u32 tcfa_flags;
+ u8 hw_stats;
+ u8 used_hw_stats;
+ bool used_hw_stats_valid;
};
#define tcf_index common.tcfa_index
#define tcf_refcnt common.tcfa_refcnt
@@ -52,6 +55,9 @@
#define tcf_rate_est common.tcfa_rate_est
#define tcf_lock common.tcfa_lock
+#define TCA_ACT_HW_STATS_ANY (TCA_ACT_HW_STATS_IMMEDIATE | \
+ TCA_ACT_HW_STATS_DELAYED)
+
/* Update lastuse only if needed, to avoid dirtying a cache line.
* We use a temp variable to avoid fetching jiffies twice.
*/
@@ -95,12 +101,12 @@
int (*init)(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **act, int ovr,
int bind, bool rtnl_held, struct tcf_proto *tp,
- struct netlink_ext_ack *extack);
+ u32 flags, struct netlink_ext_ack *extack);
int (*walk)(struct net *, struct sk_buff *,
struct netlink_callback *, int,
const struct tc_action_ops *,
struct netlink_ext_ack *);
- void (*stats_update)(struct tc_action *, u64, u32, u64, bool);
+ void (*stats_update)(struct tc_action *, u64, u64, u64, u64, bool);
size_t (*get_fill_size)(const struct tc_action *act);
struct net_device *(*get_dev)(const struct tc_action *a,
tc_action_priv_destructor *destructor);
@@ -155,17 +161,16 @@
int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index);
int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
struct tc_action **a, const struct tc_action_ops *ops,
- int bind, bool cpustats);
+ int bind, bool cpustats, u32 flags);
+int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
+ struct nlattr *est, struct tc_action **a,
+ const struct tc_action_ops *ops, int bind,
+ u32 flags);
void tcf_idr_insert_many(struct tc_action *actions[]);
void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
struct tc_action **a, int bind);
-int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
-
-static inline int tcf_idr_release(struct tc_action *a, bool bind)
-{
- return __tcf_idr_release(a, bind, false);
-}
+int tcf_idr_release(struct tc_action *a, bool bind);
int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
int tcf_unregister_action(struct tc_action_ops *a,
@@ -175,17 +180,58 @@
int nr_actions, struct tcf_result *res);
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
- struct tc_action *actions[], size_t *attr_size,
+ struct tc_action *actions[], int init_res[], size_t *attr_size,
bool rtnl_held, struct netlink_ext_ack *extack);
+struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla,
+ bool rtnl_held,
+ struct netlink_ext_ack *extack);
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
+ struct tc_action_ops *a_o, int *init_res,
bool rtnl_held,
struct netlink_ext_ack *extack);
int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind,
- int ref);
+ int ref, bool terse);
int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
+
+static inline void tcf_action_update_bstats(struct tc_action *a,
+ struct sk_buff *skb)
+{
+ if (likely(a->cpu_bstats)) {
+ bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), skb);
+ return;
+ }
+ spin_lock(&a->tcfa_lock);
+ bstats_update(&a->tcfa_bstats, skb);
+ spin_unlock(&a->tcfa_lock);
+}
+
+static inline void tcf_action_inc_drop_qstats(struct tc_action *a)
+{
+ if (likely(a->cpu_qstats)) {
+ qstats_drop_inc(this_cpu_ptr(a->cpu_qstats));
+ return;
+ }
+ spin_lock(&a->tcfa_lock);
+ qstats_drop_inc(&a->tcfa_qstats);
+ spin_unlock(&a->tcfa_lock);
+}
+
+static inline void tcf_action_inc_overlimit_qstats(struct tc_action *a)
+{
+ if (likely(a->cpu_qstats)) {
+ qstats_overlimit_inc(this_cpu_ptr(a->cpu_qstats));
+ return;
+ }
+ spin_lock(&a->tcfa_lock);
+ qstats_overlimit_inc(&a->tcfa_qstats);
+ spin_unlock(&a->tcfa_lock);
+}
+
+void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets,
+ u64 drops, bool hw);
int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
int tcf_action_check_ctrlact(int action, struct tcf_proto *tp,
@@ -196,13 +242,14 @@
#endif /* CONFIG_NET_CLS_ACT */
static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
- u64 packets, u64 lastuse, bool hw)
+ u64 packets, u64 drops,
+ u64 lastuse, bool hw)
{
#ifdef CONFIG_NET_CLS_ACT
if (!a->ops->stats_update)
return;
- a->ops->stats_update(a, bytes, packets, lastuse, hw);
+ a->ops->stats_update(a, bytes, packets, drops, lastuse, hw);
#endif
}
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 8d90fb9..e7ce719 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -90,12 +90,18 @@
int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr);
#endif
+int ipv6_chk_rpl_srh_loop(struct net *net, const struct in6_addr *segs,
+ unsigned char nsegs);
+
bool ipv6_chk_custom_prefix(const struct in6_addr *addr,
const unsigned int prefix_len,
struct net_device *dev);
int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev);
+struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr,
+ struct net_device *dev);
+
struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net,
const struct in6_addr *addr,
struct net_device *dev, int strict);
@@ -202,11 +208,11 @@
/*
* multicast prototypes (mcast.c)
*/
-static inline int ipv6_mc_may_pull(struct sk_buff *skb,
- unsigned int len)
+static inline bool ipv6_mc_may_pull(struct sk_buff *skb,
+ unsigned int len)
{
if (skb_transport_offset(skb) + ipv6_transport_len(skb) < len)
- return 0;
+ return false;
return pskb_may_pull(skb, len);
}
@@ -437,7 +443,7 @@
static inline bool ipv6_addr_is_ll_all_nodes(const struct in6_addr *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
- __be64 *p = (__be64 *)addr;
+ __be64 *p = (__force __be64 *)addr;
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(1))) == 0UL;
#else
return ((addr->s6_addr32[0] ^ htonl(0xff020000)) |
@@ -449,7 +455,7 @@
static inline bool ipv6_addr_is_ll_all_routers(const struct in6_addr *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
- __be64 *p = (__be64 *)addr;
+ __be64 *p = (__force __be64 *)addr;
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(2))) == 0UL;
#else
return ((addr->s6_addr32[0] ^ htonl(0xff020000)) |
@@ -466,7 +472,7 @@
static inline bool ipv6_addr_is_solict_mult(const struct in6_addr *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
- __be64 *p = (__be64 *)addr;
+ __be64 *p = (__force __be64 *)addr;
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) |
((p[1] ^ cpu_to_be64(0x00000001ff000000UL)) &
cpu_to_be64(0xffffffffff000000UL))) == 0UL;
@@ -481,7 +487,7 @@
static inline bool ipv6_addr_is_all_snoopers(const struct in6_addr *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
- __be64 *p = (__be64 *)addr;
+ __be64 *p = (__force __be64 *)addr;
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) |
(p[1] ^ cpu_to_be64(0x6a))) == 0UL;
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 55b980b..f6abcc0 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -72,4 +72,6 @@
void rxrpc_kernel_set_max_life(struct socket *, struct rxrpc_call *,
unsigned long);
+int rxrpc_sock_set_min_security_level(struct sock *sk, unsigned int val);
+
#endif /* _NET_RXRPC_H */
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 3426d6d..f42fddd 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -27,7 +27,7 @@
refcount_t refcnt;
int len;
unsigned int hash;
- struct sockaddr_un name[0];
+ struct sockaddr_un name[];
};
struct unix_skb_parms {
@@ -41,6 +41,10 @@
u32 consumed;
} __randomize_layout;
+struct scm_stat {
+ atomic_t nr_fds;
+};
+
#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb))
#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock)
@@ -65,6 +69,7 @@
#define UNIX_GC_MAYBE_CYCLE 1
struct socket_wq peer_wq;
wait_queue_entry_t peer_wake;
+ struct scm_stat scm_stat;
};
static inline struct unix_sock *unix_sk(const struct sock *sk)
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 80ea0f9..4d85892 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -10,7 +10,7 @@
#include <linux/kernel.h>
#include <linux/workqueue.h>
-#include <linux/vm_sockets.h>
+#include <uapi/linux/vm_sockets.h>
#include "vsock_addr.h"
@@ -27,6 +27,7 @@
struct vsock_sock {
/* sk must be the first member. */
struct sock sk;
+ const struct vsock_transport *transport;
struct sockaddr_vm local_addr;
struct sockaddr_vm remote_addr;
/* Links for the global tables of bound and connected sockets. */
@@ -64,16 +65,18 @@
bool sent_request;
bool ignore_connecting_rst;
+ /* Protected by lock_sock(sk) */
+ u64 buffer_size;
+ u64 buffer_min_size;
+ u64 buffer_max_size;
+
/* Private to transport. */
void *trans;
};
s64 vsock_stream_has_data(struct vsock_sock *vsk);
s64 vsock_stream_has_space(struct vsock_sock *vsk);
-struct sock *__vsock_create(struct net *net,
- struct socket *sock,
- struct sock *parent,
- gfp_t priority, unsigned short type, int kern);
+struct sock *vsock_create_connected(struct sock *parent);
/**** TRANSPORT ****/
@@ -88,7 +91,19 @@
u64 data2; /* Transport-defined. */
};
+/* Transport features flags */
+/* Transport provides host->guest communication */
+#define VSOCK_TRANSPORT_F_H2G 0x00000001
+/* Transport provides guest->host communication */
+#define VSOCK_TRANSPORT_F_G2H 0x00000002
+/* Transport provides DGRAM communication */
+#define VSOCK_TRANSPORT_F_DGRAM 0x00000004
+/* Transport provides local (loopback) communication */
+#define VSOCK_TRANSPORT_F_LOCAL 0x00000008
+
struct vsock_transport {
+ struct module *module;
+
/* Initialize/tear-down socket. */
int (*init)(struct vsock_sock *, struct vsock_sock *);
void (*destruct)(struct vsock_sock *);
@@ -139,33 +154,23 @@
struct vsock_transport_send_notify_data *);
int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t,
struct vsock_transport_send_notify_data *);
+ /* sk_lock held by the caller */
+ void (*notify_buffer_size)(struct vsock_sock *, u64 *);
/* Shutdown. */
int (*shutdown)(struct vsock_sock *, int);
- /* Buffer sizes. */
- void (*set_buffer_size)(struct vsock_sock *, u64);
- void (*set_min_buffer_size)(struct vsock_sock *, u64);
- void (*set_max_buffer_size)(struct vsock_sock *, u64);
- u64 (*get_buffer_size)(struct vsock_sock *);
- u64 (*get_min_buffer_size)(struct vsock_sock *);
- u64 (*get_max_buffer_size)(struct vsock_sock *);
-
/* Addressing. */
u32 (*get_local_cid)(void);
};
/**** CORE ****/
-int __vsock_core_init(const struct vsock_transport *t, struct module *owner);
-static inline int vsock_core_init(const struct vsock_transport *t)
-{
- return __vsock_core_init(t, THIS_MODULE);
-}
-void vsock_core_exit(void);
+int vsock_core_register(const struct vsock_transport *t, int features);
+void vsock_core_unregister(const struct vsock_transport *t);
/* The transport may downcast this to access transport-specific functions */
-const struct vsock_transport *vsock_core_get_transport(void);
+const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk);
/**** UTILS ****/
@@ -192,7 +197,10 @@
struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
struct sockaddr_vm *dst);
void vsock_remove_sock(struct vsock_sock *vsk);
-void vsock_for_each_connected_socket(void (*fn)(struct sock *sk));
+void vsock_for_each_connected_socket(struct vsock_transport *transport,
+ void (*fn)(struct sock *sk));
+int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk);
+bool vsock_find_cid(unsigned int cid);
/**** TAP ****/
diff --git a/include/net/bareudp.h b/include/net/bareudp.h
new file mode 100644
index 0000000..dc65a0d
--- /dev/null
+++ b/include/net/bareudp.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __NET_BAREUDP_H
+#define __NET_BAREUDP_H
+
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <net/rtnetlink.h>
+
+struct bareudp_conf {
+ __be16 ethertype;
+ __be16 port;
+ u16 sport_min;
+ bool multi_proto_mode;
+};
+
+struct net_device *bareudp_dev_create(struct net *net, const char *name,
+ u8 name_assign_type,
+ struct bareudp_conf *info);
+
+static inline bool netif_is_bareudp(const struct net_device *dev)
+{
+ return dev->rtnl_link_ops &&
+ !strcmp(dev->rtnl_link_ops->kind, "bareudp");
+}
+
+#endif
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index fabee6d..9125eff 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -41,6 +41,8 @@
#define BLUETOOTH_VER_1_1 1
#define BLUETOOTH_VER_1_2 2
#define BLUETOOTH_VER_2_0 3
+#define BLUETOOTH_VER_2_1 4
+#define BLUETOOTH_VER_4_0 6
/* Reserv for core and drivers use */
#define BT_SKB_RESERVE 8
@@ -121,6 +123,35 @@
#define BT_SNDMTU 12
#define BT_RCVMTU 13
+#define BT_PHY 14
+
+#define BT_PHY_BR_1M_1SLOT 0x00000001
+#define BT_PHY_BR_1M_3SLOT 0x00000002
+#define BT_PHY_BR_1M_5SLOT 0x00000004
+#define BT_PHY_EDR_2M_1SLOT 0x00000008
+#define BT_PHY_EDR_2M_3SLOT 0x00000010
+#define BT_PHY_EDR_2M_5SLOT 0x00000020
+#define BT_PHY_EDR_3M_1SLOT 0x00000040
+#define BT_PHY_EDR_3M_3SLOT 0x00000080
+#define BT_PHY_EDR_3M_5SLOT 0x00000100
+#define BT_PHY_LE_1M_TX 0x00000200
+#define BT_PHY_LE_1M_RX 0x00000400
+#define BT_PHY_LE_2M_TX 0x00000800
+#define BT_PHY_LE_2M_RX 0x00001000
+#define BT_PHY_LE_CODED_TX 0x00002000
+#define BT_PHY_LE_CODED_RX 0x00004000
+
+#define BT_MODE 15
+
+#define BT_MODE_BASIC 0x00
+#define BT_MODE_ERTM 0x01
+#define BT_MODE_STREAMING 0x02
+#define BT_MODE_LE_FLOWCTL 0x03
+#define BT_MODE_EXT_FLOWCTL 0x04
+
+#define BT_PKT_STATUS 16
+
+#define BT_SCM_PKT_STATUS 0x03
__printf(1, 2)
void bt_info(const char *fmt, ...);
@@ -128,15 +159,26 @@
void bt_warn(const char *fmt, ...);
__printf(1, 2)
void bt_err(const char *fmt, ...);
+#if IS_ENABLED(CONFIG_BT_FEATURE_DEBUG)
+void bt_dbg_set(bool enable);
+bool bt_dbg_get(void);
+__printf(1, 2)
+void bt_dbg(const char *fmt, ...);
+#endif
+__printf(1, 2)
+void bt_warn_ratelimited(const char *fmt, ...);
__printf(1, 2)
void bt_err_ratelimited(const char *fmt, ...);
#define BT_INFO(fmt, ...) bt_info(fmt "\n", ##__VA_ARGS__)
#define BT_WARN(fmt, ...) bt_warn(fmt "\n", ##__VA_ARGS__)
#define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__)
-#define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__)
-#define BT_ERR_RATELIMITED(fmt, ...) bt_err_ratelimited(fmt "\n", ##__VA_ARGS__)
+#if IS_ENABLED(CONFIG_BT_FEATURE_DEBUG)
+#define BT_DBG(fmt, ...) bt_dbg(fmt "\n", ##__VA_ARGS__)
+#else
+#define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__)
+#endif
#define bt_dev_info(hdev, fmt, ...) \
BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
@@ -147,8 +189,10 @@
#define bt_dev_dbg(hdev, fmt, ...) \
BT_DBG("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
+#define bt_dev_warn_ratelimited(hdev, fmt, ...) \
+ bt_warn_ratelimited("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
#define bt_dev_err_ratelimited(hdev, fmt, ...) \
- BT_ERR_RATELIMITED("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
+ bt_err_ratelimited("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
/* Connection and socket states */
enum {
@@ -248,6 +292,7 @@
struct sock *parent;
unsigned long flags;
void (*skb_msg_name)(struct sk_buff *, void *, int *);
+ void (*skb_put_cmsg)(struct sk_buff *, struct msghdr *, struct sock *);
};
enum {
@@ -297,6 +342,10 @@
struct l2cap_chan *chan;
};
+struct sco_ctrl {
+ u8 pkt_status;
+};
+
struct hci_dev;
typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode);
@@ -323,6 +372,7 @@
u8 incoming:1;
union {
struct l2cap_ctrl l2cap;
+ struct sco_ctrl sco;
struct hci_ctrl hci;
};
};
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 5bc1e30..243de74 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -27,6 +27,7 @@
#define HCI_MAX_ACL_SIZE 1024
#define HCI_MAX_SCO_SIZE 255
+#define HCI_MAX_ISO_SIZE 251
#define HCI_MAX_EVENT_SIZE 260
#define HCI_MAX_FRAME_SIZE (HCI_MAX_ACL_SIZE + 4)
@@ -52,6 +53,9 @@
#define HCI_NOTIFY_CONN_ADD 1
#define HCI_NOTIFY_CONN_DEL 2
#define HCI_NOTIFY_VOICE_SETTING 3
+#define HCI_NOTIFY_ENABLE_SCO_CVSD 4
+#define HCI_NOTIFY_ENABLE_SCO_TRANSP 5
+#define HCI_NOTIFY_DISABLE_SCO 6
/* HCI bus types */
#define HCI_VIRTUAL 0
@@ -64,6 +68,7 @@
#define HCI_SPI 7
#define HCI_I2C 8
#define HCI_SMD 9
+#define HCI_VIRTIO 10
/* HCI controller types */
#define HCI_PRIMARY 0x00
@@ -114,7 +119,7 @@
* wrongly configured local features that will require forcing
* them to enable this mode. Getting RSSI information with the
* inquiry responses is preferred since it allows for a better
- * user expierence.
+ * user experience.
*
* This quirk must be set before hci_register_dev is called.
*/
@@ -141,7 +146,7 @@
/* When this quirk is set, an external configuration step
* is required and will be indicated with the controller
- * configuation.
+ * configuration.
*
* This quirk can be set before hci_register_dev is called or
* during the hdev->setup vendor callback.
@@ -204,6 +209,43 @@
*
*/
HCI_QUIRK_NON_PERSISTENT_SETUP,
+
+ /* When this quirk is set, wide band speech is supported by
+ * the driver since no reliable mechanism exist to report
+ * this from the hardware, a driver flag is use to convey
+ * this support
+ *
+ * This quirk must be set before hci_register_dev is called.
+ */
+ HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
+
+ /* When this quirk is set, the controller has validated that
+ * LE states reported through the HCI_LE_READ_SUPPORTED_STATES are
+ * valid. This mechanism is necessary as many controllers have
+ * been seen has having trouble initiating a connectable
+ * advertisement despite the state combination being reported as
+ * supported.
+ */
+ HCI_QUIRK_VALID_LE_STATES,
+
+ /* When this quirk is set, then erroneous data reporting
+ * is ignored. This is mainly due to the fact that the HCI
+ * Read Default Erroneous Data Reporting command is advertised,
+ * but not supported; these controllers often reply with unknown
+ * command and tend to lock up randomly. Needing a hard reset.
+ *
+ * This quirk can be set before hci_register_dev is called or
+ * during the hdev->setup vendor callback.
+ */
+ HCI_QUIRK_BROKEN_ERR_DATA_REPORTING,
+
+ /*
+ * When this quirk is set, then the hci_suspend_notifier is not
+ * registered. This is intended for devices which drop completely
+ * from the bus on system-suspend and which will show up as a new
+ * HCI after resume.
+ */
+ HCI_QUIRK_NO_SUSPEND_NOTIFIER,
};
/* HCI device flags */
@@ -235,6 +277,7 @@
HCI_MGMT_DEV_CLASS_EVENTS,
HCI_MGMT_LOCAL_NAME_EVENTS,
HCI_MGMT_OOB_DATA_EVENTS,
+ HCI_MGMT_EXP_FEATURE_EVENTS,
};
/*
@@ -276,13 +319,16 @@
HCI_FAST_CONNECTABLE,
HCI_BREDR_ENABLED,
HCI_LE_SCAN_INTERRUPTED,
+ HCI_WIDEBAND_SPEECH_ENABLED,
HCI_DUT_MODE,
HCI_VENDOR_DIAG,
HCI_FORCE_BREDR_SMP,
HCI_FORCE_STATIC_ADDR,
HCI_LL_RPA_RESOLUTION,
+ HCI_ENABLE_LL_PRIVACY,
HCI_CMD_PENDING,
+ HCI_FORCE_NO_MITM,
__HCI_NUM_FLAGS,
};
@@ -303,6 +349,7 @@
#define HCI_ACLDATA_PKT 0x02
#define HCI_SCODATA_PKT 0x03
#define HCI_EVENT_PKT 0x04
+#define HCI_ISODATA_PKT 0x05
#define HCI_DIAG_PKT 0xf0
#define HCI_VENDOR_PKT 0xff
@@ -352,6 +399,15 @@
#define ACL_ACTIVE_BCAST 0x04
#define ACL_PICO_BCAST 0x08
+/* ISO PB flags */
+#define ISO_START 0x00
+#define ISO_CONT 0x01
+#define ISO_SINGLE 0x02
+#define ISO_END 0x03
+
+/* ISO TS flags */
+#define ISO_TS 0x01
+
/* Baseband links */
#define SCO_LINK 0x00
#define ACL_LINK 0x01
@@ -359,6 +415,7 @@
/* Low Energy links do not have defined link type. Use invented one */
#define LE_LINK 0x80
#define AMP_LINK 0x81
+#define ISO_LINK 0x82
#define INVALID_LINK 0xff
/* LMP features */
@@ -433,13 +490,14 @@
#define HCI_LE_SLAVE_FEATURES 0x08
#define HCI_LE_PING 0x10
#define HCI_LE_DATA_LEN_EXT 0x20
-#define HCI_LE_PHY_2M 0x01
-#define HCI_LE_PHY_CODED 0x08
-#define HCI_LE_EXT_ADV 0x10
+#define HCI_LE_LL_PRIVACY 0x40
#define HCI_LE_EXT_SCAN_POLICY 0x80
#define HCI_LE_PHY_2M 0x01
#define HCI_LE_PHY_CODED 0x08
+#define HCI_LE_EXT_ADV 0x10
#define HCI_LE_CHAN_SEL_ALG2 0x40
+#define HCI_LE_CIS_MASTER 0x10
+#define HCI_LE_CIS_SLAVE 0x20
/* Connection modes */
#define HCI_CM_ACTIVE 0x0000
@@ -918,10 +976,14 @@
#define HCI_OP_RESET 0x0c03
#define HCI_OP_SET_EVENT_FLT 0x0c05
-struct hci_cp_set_event_flt {
- __u8 flt_type;
- __u8 cond_type;
- __u8 condition[0];
+#define HCI_SET_EVENT_FLT_SIZE 9
+struct hci_cp_set_event_filter {
+ __u8 flt_type;
+ __u8 cond_type;
+ struct {
+ bdaddr_t bdaddr;
+ __u8 auto_accept;
+ } __packed addr_conn_flt;
} __packed;
/* Filter types */
@@ -935,8 +997,9 @@
#define HCI_CONN_SETUP_ALLOW_BDADDR 0x02
/* CONN_SETUP Conditions */
-#define HCI_CONN_SETUP_AUTO_OFF 0x01
-#define HCI_CONN_SETUP_AUTO_ON 0x02
+#define HCI_CONN_SETUP_AUTO_OFF 0x01
+#define HCI_CONN_SETUP_AUTO_ON 0x02
+#define HCI_CONN_SETUP_AUTO_ON_WITH_RS 0x03
#define HCI_OP_READ_STORED_LINK_KEY 0x0c0d
struct hci_cp_read_stored_link_key {
@@ -1072,6 +1135,19 @@
__s8 tx_power;
} __packed;
+#define HCI_OP_READ_DEF_ERR_DATA_REPORTING 0x0c5a
+ #define ERR_DATA_REPORTING_DISABLED 0x00
+ #define ERR_DATA_REPORTING_ENABLED 0x01
+struct hci_rp_read_def_err_data_reporting {
+ __u8 status;
+ __u8 err_data_reporting;
+} __packed;
+
+#define HCI_OP_WRITE_DEF_ERR_DATA_REPORTING 0x0c5b
+struct hci_cp_write_def_err_data_reporting {
+ __u8 err_data_reporting;
+} __packed;
+
#define HCI_OP_SET_EVENT_MASK_PAGE_2 0x0c63
#define HCI_OP_READ_LOCATION_DATA 0x0c64
@@ -1230,6 +1306,13 @@
#define HCI_OP_READ_LOCAL_CODECS 0x100b
+#define HCI_OP_READ_LOCAL_PAIRING_OPTS 0x100c
+struct hci_rp_read_local_pairing_opts {
+ __u8 status;
+ __u8 pairing_opts;
+ __u8 max_key_size;
+} __packed;
+
#define HCI_OP_READ_PAGE_SCAN_ACTIVITY 0x0c1b
struct hci_rp_read_page_scan_activity {
__u8 status;
@@ -1321,7 +1404,7 @@
__u8 status;
__u8 phy_handle;
__le16 rem_len;
- __u8 frag[0];
+ __u8 frag[];
} __packed;
#define HCI_OP_WRITE_REMOTE_AMP_ASSOC 0x140b
@@ -1329,7 +1412,7 @@
__u8 phy_handle;
__le16 len_so_far;
__le16 rem_len;
- __u8 frag[0];
+ __u8 frag[];
} __packed;
struct hci_rp_write_remote_amp_assoc {
__u8 status;
@@ -1574,6 +1657,8 @@
#define HCI_OP_LE_SET_ADDR_RESOLV_ENABLE 0x202d
+#define HCI_OP_LE_SET_RPA_TIMEOUT 0x202e
+
#define HCI_OP_LE_READ_MAX_DATA_LEN 0x202f
struct hci_rp_le_read_max_data_len {
__u8 status;
@@ -1599,7 +1684,7 @@
__u8 own_addr_type;
__u8 filter_policy;
__u8 scanning_phys;
- __u8 data[0];
+ __u8 data[];
} __packed;
#define LE_SCAN_PHY_1M 0x01
@@ -1627,7 +1712,7 @@
__u8 peer_addr_type;
bdaddr_t peer_addr;
__u8 phys;
- __u8 data[0];
+ __u8 data[];
} __packed;
struct hci_cp_le_ext_conn_param {
@@ -1679,7 +1764,7 @@
struct hci_cp_le_set_ext_adv_enable {
__u8 enable;
__u8 num_of_sets;
- __u8 data[0];
+ __u8 data[];
} __packed;
struct hci_cp_ext_adv_set {
@@ -1688,13 +1773,15 @@
__u8 max_events;
} __packed;
+#define HCI_MAX_EXT_AD_LENGTH 251
+
#define HCI_OP_LE_SET_EXT_ADV_DATA 0x2037
struct hci_cp_le_set_ext_adv_data {
__u8 handle;
__u8 operation;
__u8 frag_pref;
__u8 length;
- __u8 data[HCI_MAX_AD_LENGTH];
+ __u8 data[];
} __packed;
#define HCI_OP_LE_SET_EXT_SCAN_RSP_DATA 0x2038
@@ -1703,13 +1790,15 @@
__u8 operation;
__u8 frag_pref;
__u8 length;
- __u8 data[HCI_MAX_AD_LENGTH];
+ __u8 data[];
} __packed;
#define LE_SET_ADV_DATA_OP_COMPLETE 0x03
#define LE_SET_ADV_DATA_NO_FRAG 0x01
+#define HCI_OP_LE_REMOVE_ADV_SET 0x203c
+
#define HCI_OP_LE_CLEAR_ADV_SETS 0x203d
#define HCI_OP_LE_SET_ADV_SET_RAND_ADDR 0x2035
@@ -1718,6 +1807,86 @@
bdaddr_t bdaddr;
} __packed;
+#define HCI_OP_LE_READ_BUFFER_SIZE_V2 0x2060
+struct hci_rp_le_read_buffer_size_v2 {
+ __u8 status;
+ __le16 acl_mtu;
+ __u8 acl_max_pkt;
+ __le16 iso_mtu;
+ __u8 iso_max_pkt;
+} __packed;
+
+#define HCI_OP_LE_READ_ISO_TX_SYNC 0x2061
+struct hci_cp_le_read_iso_tx_sync {
+ __le16 handle;
+} __packed;
+
+struct hci_rp_le_read_iso_tx_sync {
+ __u8 status;
+ __le16 handle;
+ __le16 seq;
+ __le32 imestamp;
+ __u8 offset[3];
+} __packed;
+
+#define HCI_OP_LE_SET_CIG_PARAMS 0x2062
+struct hci_cis_params {
+ __u8 cis_id;
+ __le16 m_sdu;
+ __le16 s_sdu;
+ __u8 m_phy;
+ __u8 s_phy;
+ __u8 m_rtn;
+ __u8 s_rtn;
+} __packed;
+
+struct hci_cp_le_set_cig_params {
+ __u8 cig_id;
+ __u8 m_interval[3];
+ __u8 s_interval[3];
+ __u8 sca;
+ __u8 packing;
+ __u8 framing;
+ __le16 m_latency;
+ __le16 s_latency;
+ __u8 num_cis;
+ struct hci_cis_params cis[];
+} __packed;
+
+struct hci_rp_le_set_cig_params {
+ __u8 status;
+ __u8 cig_id;
+ __u8 num_handles;
+ __le16 handle[];
+} __packed;
+
+#define HCI_OP_LE_CREATE_CIS 0x2064
+struct hci_cis {
+ __le16 cis_handle;
+ __le16 acl_handle;
+} __packed;
+
+struct hci_cp_le_create_cis {
+ __u8 num_cis;
+ struct hci_cis cis[];
+} __packed;
+
+#define HCI_OP_LE_REMOVE_CIG 0x2065
+struct hci_cp_le_remove_cig {
+ __u8 cig_id;
+} __packed;
+
+#define HCI_OP_LE_ACCEPT_CIS 0x2066
+struct hci_cp_le_accept_cis {
+ __le16 handle;
+} __packed;
+
+#define HCI_OP_LE_REJECT_CIS 0x2067
+struct hci_cp_le_reject_cis {
+ __le16 handle;
+ __u8 reason;
+} __packed;
+
/* ---- HCI Events ---- */
#define HCI_EV_INQUIRY_COMPLETE 0x01
@@ -1843,7 +2012,7 @@
struct hci_ev_num_comp_pkts {
__u8 num_hndl;
- struct hci_comp_pkts_info handles[0];
+ struct hci_comp_pkts_info handles[];
} __packed;
#define HCI_EV_MODE_CHANGE 0x14
@@ -2076,7 +2245,7 @@
struct hci_ev_num_comp_blocks {
__le16 num_blocks;
__u8 num_hndl;
- struct hci_comp_blocks_info handles[0];
+ struct hci_comp_blocks_info handles[];
} __packed;
#define HCI_EV_SYNC_TRAIN_COMPLETE 0x4F
@@ -2123,8 +2292,10 @@
#define LE_EXT_ADV_SCAN_RSP 0x0008
#define LE_EXT_ADV_LEGACY_PDU 0x0010
-#define ADDR_LE_DEV_PUBLIC 0x00
-#define ADDR_LE_DEV_RANDOM 0x01
+#define ADDR_LE_DEV_PUBLIC 0x00
+#define ADDR_LE_DEV_RANDOM 0x01
+#define ADDR_LE_DEV_PUBLIC_RESOLVED 0x02
+#define ADDR_LE_DEV_RANDOM_RESOLVED 0x03
#define HCI_EV_LE_ADVERTISING_REPORT 0x02
struct hci_ev_le_advertising_info {
@@ -2132,7 +2303,7 @@
__u8 bdaddr_type;
bdaddr_t bdaddr;
__u8 length;
- __u8 data[0];
+ __u8 data[];
} __packed;
#define HCI_EV_LE_CONN_UPDATE_COMPLETE 0x03
@@ -2186,6 +2357,14 @@
__s8 rssi;
} __packed;
+#define HCI_EV_LE_PHY_UPDATE_COMPLETE 0x0c
+struct hci_ev_le_phy_update_complete {
+ __u8 status;
+ __le16 handle;
+ __u8 tx_phy;
+ __u8 rx_phy;
+} __packed;
+
#define HCI_EV_LE_EXT_ADV_REPORT 0x0d
struct hci_ev_le_ext_adv_report {
__le16 evt_type;
@@ -2200,7 +2379,7 @@
__u8 direct_addr_type;
bdaddr_t direct_addr;
__u8 length;
- __u8 data[0];
+ __u8 data[];
} __packed;
#define HCI_EV_LE_ENHANCED_CONN_COMPLETE 0x0a
@@ -2226,13 +2405,41 @@
__u8 num_evts;
} __packed;
+#define HCI_EVT_LE_CIS_ESTABLISHED 0x19
+struct hci_evt_le_cis_established {
+ __u8 status;
+ __le16 handle;
+ __u8 cig_sync_delay[3];
+ __u8 cis_sync_delay[3];
+ __u8 m_latency[3];
+ __u8 s_latency[3];
+ __u8 m_phy;
+ __u8 s_phy;
+ __u8 nse;
+ __u8 m_bn;
+ __u8 s_bn;
+ __u8 m_ft;
+ __u8 s_ft;
+ __le16 m_mtu;
+ __le16 s_mtu;
+ __le16 interval;
+} __packed;
+
+#define HCI_EVT_LE_CIS_REQ 0x1a
+struct hci_evt_le_cis_req {
+ __le16 acl_handle;
+ __le16 cis_handle;
+ __u8 cig_id;
+ __u8 cis_id;
+} __packed;
+
#define HCI_EV_VENDOR 0xff
/* Internal events generated by Bluetooth stack */
#define HCI_EV_STACK_INTERNAL 0xfd
struct hci_ev_stack_internal {
__u16 type;
- __u8 data[0];
+ __u8 data[];
} __packed;
#define HCI_EV_SI_DEVICE 0x01
@@ -2254,6 +2461,7 @@
#define HCI_EVENT_HDR_SIZE 2
#define HCI_ACL_HDR_SIZE 4
#define HCI_SCO_HDR_SIZE 3
+#define HCI_ISO_HDR_SIZE 4
struct hci_command_hdr {
__le16 opcode; /* OCF & OGF */
@@ -2275,6 +2483,30 @@
__u8 dlen;
} __packed;
+struct hci_iso_hdr {
+ __le16 handle;
+ __le16 dlen;
+ __u8 data[];
+} __packed;
+
+/* ISO data packet status flags */
+#define HCI_ISO_STATUS_VALID 0x00
+#define HCI_ISO_STATUS_INVALID 0x01
+#define HCI_ISO_STATUS_NOP 0x02
+
+#define HCI_ISO_DATA_HDR_SIZE 4
+struct hci_iso_data_hdr {
+ __le16 sn;
+ __le16 slen;
+};
+
+#define HCI_ISO_TS_DATA_HDR_SIZE 8
+struct hci_iso_ts_data_hdr {
+ __le32 ts;
+ __le16 sn;
+ __le16 slen;
+};
+
static inline struct hci_event_hdr *hci_event_hdr(const struct sk_buff *skb)
{
return (struct hci_event_hdr *) skb->data;
@@ -2300,4 +2532,22 @@
#define hci_handle(h) (h & 0x0fff)
#define hci_flags(h) (h >> 12)
+/* ISO handle and flags pack/unpack */
+#define hci_iso_flags_pb(f) (f & 0x0003)
+#define hci_iso_flags_ts(f) ((f >> 2) & 0x0001)
+#define hci_iso_flags_pack(pb, ts) ((pb & 0x03) | ((ts & 0x01) << 2))
+
+/* ISO data length and flags pack/unpack */
+#define hci_iso_data_len_pack(h, f) ((__u16) ((h) | ((f) << 14)))
+#define hci_iso_data_len(h) ((h) & 0x3fff)
+#define hci_iso_data_flags(h) ((h) >> 14)
+
+/* le24 support */
+static inline void hci_cpu_to_le24(__u32 val, __u8 dst[3])
+{
+ dst[0] = val & 0xff;
+ dst[1] = (val & 0xff00) >> 8;
+ dst[2] = (val & 0xff0000) >> 16;
+}
+
#endif /* __HCI_H */
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 14d00cc..a592a82 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -25,6 +25,7 @@
#ifndef __HCI_CORE_H
#define __HCI_CORE_H
+#include <linux/idr.h>
#include <linux/leds.h>
#include <linux/rculist.h>
@@ -88,6 +89,31 @@
unsigned long scan_duration;
};
+#define SUSPEND_NOTIFIER_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */
+
+enum suspend_tasks {
+ SUSPEND_PAUSE_DISCOVERY,
+ SUSPEND_UNPAUSE_DISCOVERY,
+
+ SUSPEND_PAUSE_ADVERTISING,
+ SUSPEND_UNPAUSE_ADVERTISING,
+
+ SUSPEND_SCAN_DISABLE,
+ SUSPEND_SCAN_ENABLE,
+ SUSPEND_DISCONNECTING,
+
+ SUSPEND_POWERING_DOWN,
+
+ SUSPEND_PREPARE_NOTIFIER,
+ __SUSPEND_NUM_TASKS
+};
+
+enum suspended_state {
+ BT_RUNNING = 0,
+ BT_SUSPEND_DISCONNECT,
+ BT_SUSPEND_CONFIGURE_WAKE,
+};
+
struct hci_conn_hash {
struct list_head list;
unsigned int acl_num;
@@ -111,6 +137,23 @@
u8 local_irk[16];
};
+struct bdaddr_list_with_flags {
+ struct list_head list;
+ bdaddr_t bdaddr;
+ u8 bdaddr_type;
+ u32 current_flags;
+};
+
+enum hci_conn_flags {
+ HCI_CONN_FLAG_REMOTE_WAKEUP,
+ HCI_CONN_FLAG_MAX
+};
+
+#define hci_conn_test_flag(nr, flags) ((flags) & (1U << nr))
+
+/* Make sure number of flags doesn't exceed sizeof(current_flags) */
+static_assert(HCI_CONN_FLAG_MAX < 32);
+
struct bt_uuid {
struct list_head list;
u8 uuid[16];
@@ -118,6 +161,13 @@
u8 svc_hint;
};
+struct blocked_key {
+ struct list_head list;
+ struct rcu_head rcu;
+ u8 type;
+ u8 val[16];
+};
+
struct smp_csrk {
bdaddr_t bdaddr;
u8 bdaddr_type;
@@ -176,9 +226,9 @@
__u16 remaining_time;
__u16 duration;
__u16 adv_data_len;
- __u8 adv_data[HCI_MAX_AD_LENGTH];
+ __u8 adv_data[HCI_MAX_EXT_AD_LENGTH];
__u16 scan_rsp_len;
- __u8 scan_rsp_data[HCI_MAX_AD_LENGTH];
+ __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH];
__s8 tx_power;
bdaddr_t random_addr;
bool rpa_expired;
@@ -188,6 +238,24 @@
#define HCI_MAX_ADV_INSTANCES 5
#define HCI_DEFAULT_ADV_DURATION 2
+struct adv_pattern {
+ struct list_head list;
+ __u8 ad_type;
+ __u8 offset;
+ __u8 length;
+ __u8 value[HCI_MAX_AD_LENGTH];
+};
+
+struct adv_monitor {
+ struct list_head patterns;
+ bool active;
+ __u16 handle;
+};
+
+#define HCI_MIN_ADV_MONITOR_HANDLE 1
+#define HCI_MAX_ADV_MONITOR_NUM_HANDLES 32
+#define HCI_MAX_ADV_MONITOR_NUM_PATTERNS 16
+
#define HCI_MAX_SHORT_NAME_LENGTH 10
/* Min encryption key size to match with SMP */
@@ -253,6 +321,7 @@
__u8 stored_num_keys;
__u8 io_capability;
__s8 inq_tx_power;
+ __u8 err_data_reporting;
__u16 page_scan_interval;
__u16 page_scan_window;
__u8 page_scan_type;
@@ -262,6 +331,14 @@
__u8 le_scan_type;
__u16 le_scan_interval;
__u16 le_scan_window;
+ __u16 le_scan_int_suspend;
+ __u16 le_scan_window_suspend;
+ __u16 le_scan_int_discovery;
+ __u16 le_scan_window_discovery;
+ __u16 le_scan_int_adv_monitor;
+ __u16 le_scan_window_adv_monitor;
+ __u16 le_scan_int_connect;
+ __u16 le_scan_window_connect;
__u16 le_conn_min_interval;
__u16 le_conn_max_interval;
__u16 le_conn_latency;
@@ -279,6 +356,8 @@
__u16 conn_info_max_age;
__u16 auth_payload_timeout;
__u8 min_enc_key_size;
+ __u8 max_enc_key_size;
+ __u8 pairing_opts;
__u8 ssp_debug_mode;
__u8 hw_error_code;
__u32 clock;
@@ -288,6 +367,17 @@
__u16 devid_product;
__u16 devid_version;
+ __u8 def_page_scan_type;
+ __u16 def_page_scan_int;
+ __u16 def_page_scan_window;
+ __u8 def_inq_scan_type;
+ __u16 def_inq_scan_int;
+ __u16 def_inq_scan_window;
+ __u16 def_br_lsto;
+ __u16 def_page_timeout;
+ __u16 def_multi_adv_rotation_duration;
+ __u16 def_le_autoconnect_timeout;
+
__u16 pkt_type;
__u16 esco_type;
__u16 link_policy;
@@ -382,6 +472,25 @@
void *smp_bredr_data;
struct discovery_state discovery;
+
+ int discovery_old_state;
+ bool discovery_paused;
+ int advertising_old_state;
+ bool advertising_paused;
+
+ struct notifier_block suspend_notifier;
+ struct work_struct suspend_prepare;
+ enum suspended_state suspend_state_next;
+ enum suspended_state suspend_state;
+ bool scanning_paused;
+ bool suspended;
+ u8 wake_reason;
+ bdaddr_t wake_addr;
+ u8 wake_addr_type;
+
+ wait_queue_head_t suspend_wait_q;
+ DECLARE_BITMAP(suspend_tasks, __SUSPEND_NUM_TASKS);
+
struct hci_conn_hash conn_hash;
struct list_head mgmt_pending;
@@ -397,6 +506,7 @@
struct list_head le_conn_params;
struct list_head pend_le_conns;
struct list_head pend_le_reports;
+ struct list_head blocked_keys;
struct hci_dev_stats stat;
@@ -413,9 +523,9 @@
DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS);
__s8 adv_tx_power;
- __u8 adv_data[HCI_MAX_AD_LENGTH];
+ __u8 adv_data[HCI_MAX_EXT_AD_LENGTH];
__u8 adv_data_len;
- __u8 scan_rsp_data[HCI_MAX_AD_LENGTH];
+ __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH];
__u8 scan_rsp_data_len;
struct list_head adv_instances;
@@ -424,6 +534,9 @@
__u16 adv_instance_timeout;
struct delayed_work adv_instance_expire;
+ struct idr adv_monitors_idr;
+ unsigned int adv_monitors_cnt;
+
__u8 irk[16];
__u32 rpa_timeout;
struct delayed_work rpa_expired;
@@ -433,6 +546,11 @@
struct led_trigger *power_led;
#endif
+#if IS_ENABLED(CONFIG_BT_MSFTEXT)
+ __u16 msft_opcode;
+ void *msft_data;
+#endif
+
int (*open)(struct hci_dev *hdev);
int (*close)(struct hci_dev *hdev);
int (*flush)(struct hci_dev *hdev);
@@ -445,10 +563,17 @@
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);
+ bool (*prevent_wake)(struct hci_dev *hdev);
};
#define HCI_PHY_HANDLE(handle) (handle & 0xff)
+enum conn_reasons {
+ CONN_REASON_PAIR_DEVICE,
+ CONN_REASON_L2CAP_CHAN,
+ CONN_REASON_SCO_CONNECT,
+};
+
struct hci_conn {
struct list_head list;
@@ -493,11 +618,15 @@
__u16 le_supv_timeout;
__u8 le_adv_data[HCI_MAX_AD_LENGTH];
__u8 le_adv_data_len;
+ __u8 le_tx_phy;
+ __u8 le_rx_phy;
__s8 rssi;
__s8 tx_power;
__s8 max_tx_power;
unsigned long flags;
+ enum conn_reasons conn_reason;
+
__u32 clock;
__u16 clock_accuracy;
@@ -566,6 +695,7 @@
struct hci_conn *conn;
bool explicit_connect;
+ u32 current_flags;
};
extern struct list_head hci_dev_list;
@@ -585,6 +715,7 @@
do { \
hci_dev_clear_flag(hdev, HCI_LE_SCAN); \
hci_dev_clear_flag(hdev, HCI_LE_ADV); \
+ hci_dev_clear_flag(hdev, HCI_LL_RPA_RESOLUTION);\
hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); \
} while (0)
@@ -922,12 +1053,14 @@
struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst,
u8 dst_type, u8 sec_level,
- u16 conn_timeout);
+ u16 conn_timeout,
+ enum conn_reasons conn_reason);
struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
u8 dst_type, u8 sec_level, u16 conn_timeout,
u8 role, bdaddr_t *direct_rpa);
struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst,
- u8 sec_level, u8 auth_type);
+ u8 sec_level, u8 auth_type,
+ enum conn_reasons conn_reason);
struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst,
__u16 setting);
int hci_conn_check_link_mode(struct hci_conn *conn);
@@ -1064,6 +1197,14 @@
int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb);
__printf(2, 3) void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...);
__printf(2, 3) void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...);
+
+static inline void hci_set_msft_opcode(struct hci_dev *hdev, __u16 opcode)
+{
+#if IS_ENABLED(CONFIG_BT_MSFTEXT)
+ hdev->msft_opcode = opcode;
+#endif
+}
+
int hci_dev_open(__u16 dev);
int hci_dev_close(__u16 dev);
int hci_dev_do_close(struct hci_dev *hdev);
@@ -1082,12 +1223,19 @@
struct bdaddr_list_with_irk *hci_bdaddr_list_lookup_with_irk(
struct list_head *list, bdaddr_t *bdaddr,
u8 type);
+struct bdaddr_list_with_flags *
+hci_bdaddr_list_lookup_with_flags(struct list_head *list, bdaddr_t *bdaddr,
+ u8 type);
int hci_bdaddr_list_add(struct list_head *list, bdaddr_t *bdaddr, u8 type);
int hci_bdaddr_list_add_with_irk(struct list_head *list, bdaddr_t *bdaddr,
- u8 type, u8 *peer_irk, u8 *local_irk);
+ u8 type, u8 *peer_irk, u8 *local_irk);
+int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr,
+ u8 type, u32 flags);
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);
+ 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,
@@ -1123,6 +1271,8 @@
struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr,
u8 addr_type, u8 val[16], bdaddr_t *rpa);
void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type);
+bool hci_is_blocked_key(struct hci_dev *hdev, u8 type, u8 val[16]);
+void hci_blocked_keys_clear(struct hci_dev *hdev);
void hci_smp_irks_clear(struct hci_dev *hdev);
bool hci_bdaddr_is_paired(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
@@ -1146,6 +1296,12 @@
int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance);
void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired);
+void hci_adv_monitors_clear(struct hci_dev *hdev);
+void hci_free_adv_monitor(struct adv_monitor *monitor);
+int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor);
+int hci_remove_adv_monitor(struct hci_dev *hdev, u16 handle);
+bool hci_is_adv_monitoring(struct hci_dev *hdev);
+
void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb);
void hci_init_sysfs(struct hci_dev *hdev);
@@ -1208,6 +1364,9 @@
#define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \
((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED))
+/* Use LL Privacy based address resolution if supported */
+#define use_ll_privacy(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY)
+
/* Use ext scanning if set ext scan param and ext scan enable is supported */
#define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \
((dev)->commands[37] & 0x40))
@@ -1485,6 +1644,8 @@
struct sk_buff *hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen,
const void *param, u32 timeout);
+u32 hci_conn_get_phy(struct hci_conn *conn);
+
/* ----- HCI Sockets ----- */
void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb);
void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
@@ -1500,6 +1661,7 @@
#define HCI_MGMT_NO_HDEV BIT(1)
#define HCI_MGMT_UNTRUSTED BIT(2)
#define HCI_MGMT_UNCONFIGURED BIT(3)
+#define HCI_MGMT_HDEV_OPTIONAL BIT(4)
struct hci_mgmt_handler {
int (*func) (struct sock *sk, struct hci_dev *hdev, void *data,
@@ -1593,6 +1755,9 @@
void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
u8 addr_type, s8 rssi, u8 *name, u8 name_len);
void mgmt_discovering(struct hci_dev *hdev, u8 discovering);
+void mgmt_suspending(struct hci_dev *hdev, u8 state);
+void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr,
+ u8 addr_type);
bool mgmt_powering_down(struct hci_dev *hdev);
void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent);
void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent);
diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h
index 240786b..2d5fcda 100644
--- a/include/net/bluetooth/hci_mon.h
+++ b/include/net/bluetooth/hci_mon.h
@@ -49,6 +49,8 @@
#define HCI_MON_CTRL_CLOSE 15
#define HCI_MON_CTRL_COMMAND 16
#define HCI_MON_CTRL_EVENT 17
+#define HCI_MON_ISO_TX_PKT 18
+#define HCI_MON_ISO_RX_PKT 19
struct hci_mon_new_index {
__u8 type;
diff --git a/include/net/bluetooth/hci_sock.h b/include/net/bluetooth/hci_sock.h
index 8e9138a..9949870 100644
--- a/include/net/bluetooth/hci_sock.h
+++ b/include/net/bluetooth/hci_sock.h
@@ -31,8 +31,8 @@
#define HCI_TIME_STAMP 3
/* CMSG flags */
-#define HCI_CMSG_DIR 0x0001
-#define HCI_CMSG_TSTAMP 0x0002
+#define HCI_CMSG_DIR 0x01
+#define HCI_CMSG_TSTAMP 0x02
struct sockaddr_hci {
sa_family_t hci_family;
@@ -144,19 +144,19 @@
struct hci_dev_list_req {
__u16 dev_num;
- struct hci_dev_req dev_req[0]; /* hci_dev_req structures */
+ struct hci_dev_req dev_req[]; /* hci_dev_req structures */
};
struct hci_conn_list_req {
__u16 dev_id;
__u16 conn_num;
- struct hci_conn_info conn_info[0];
+ struct hci_conn_info conn_info[];
};
struct hci_conn_info_req {
bdaddr_t bdaddr;
__u8 type;
- struct hci_conn_info conn_info[0];
+ struct hci_conn_info conn_info[];
};
struct hci_auth_info_req {
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 8efc241..1d12329 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -47,6 +47,7 @@
#define L2CAP_DEFAULT_ACC_LAT 0xFFFFFFFF
#define L2CAP_BREDR_MAX_PAYLOAD 1019 /* 3-DH5 packet */
#define L2CAP_LE_MIN_MTU 23
+#define L2CAP_ECRED_CONN_SCID_MAX 5
#define L2CAP_DISC_TIMEOUT msecs_to_jiffies(100)
#define L2CAP_DISC_REJ_TIMEOUT msecs_to_jiffies(5000)
@@ -119,6 +120,10 @@
#define L2CAP_LE_CONN_REQ 0x14
#define L2CAP_LE_CONN_RSP 0x15
#define L2CAP_LE_CREDITS 0x16
+#define L2CAP_ECRED_CONN_REQ 0x17
+#define L2CAP_ECRED_CONN_RSP 0x18
+#define L2CAP_ECRED_RECONF_REQ 0x19
+#define L2CAP_ECRED_RECONF_RSP 0x1a
/* L2CAP extended feature mask */
#define L2CAP_FEAT_FLOWCTL 0x00000001
@@ -290,6 +295,8 @@
#define L2CAP_CR_LE_ENCRYPTION 0x0008
#define L2CAP_CR_LE_INVALID_SCID 0x0009
#define L2CAP_CR_LE_SCID_IN_USE 0X000A
+#define L2CAP_CR_LE_UNACCEPT_PARAMS 0X000B
+#define L2CAP_CR_LE_INVALID_PARAMS 0X000C
/* connect/create channel status */
#define L2CAP_CS_NO_INFO 0x0000
@@ -299,14 +306,14 @@
struct l2cap_conf_req {
__le16 dcid;
__le16 flags;
- __u8 data[0];
+ __u8 data[];
} __packed;
struct l2cap_conf_rsp {
__le16 scid;
__le16 flags;
__le16 result;
- __u8 data[0];
+ __u8 data[];
} __packed;
#define L2CAP_CONF_SUCCESS 0x0000
@@ -322,7 +329,7 @@
struct l2cap_conf_opt {
__u8 type;
__u8 len;
- __u8 val[0];
+ __u8 val[];
} __packed;
#define L2CAP_CONF_OPT_SIZE 2
@@ -359,6 +366,7 @@
* ever be used in the BR/EDR configuration phase.
*/
#define L2CAP_MODE_LE_FLOWCTL 0x80
+#define L2CAP_MODE_EXT_FLOWCTL 0x81
struct l2cap_conf_efs {
__u8 id;
@@ -392,7 +400,7 @@
struct l2cap_info_rsp {
__le16 type;
__le16 result;
- __u8 data[0];
+ __u8 data[];
} __packed;
struct l2cap_create_chan_req {
@@ -483,6 +491,39 @@
__le16 credits;
} __packed;
+#define L2CAP_ECRED_MIN_MTU 64
+#define L2CAP_ECRED_MIN_MPS 64
+
+struct l2cap_ecred_conn_req {
+ __le16 psm;
+ __le16 mtu;
+ __le16 mps;
+ __le16 credits;
+ __le16 scid[];
+} __packed;
+
+struct l2cap_ecred_conn_rsp {
+ __le16 mtu;
+ __le16 mps;
+ __le16 credits;
+ __le16 result;
+ __le16 dcid[];
+};
+
+struct l2cap_ecred_reconf_req {
+ __le16 mtu;
+ __le16 mps;
+ __le16 scid[];
+} __packed;
+
+#define L2CAP_RECONF_SUCCESS 0x0000
+#define L2CAP_RECONF_INVALID_MTU 0x0001
+#define L2CAP_RECONF_INVALID_MPS 0x0002
+
+struct l2cap_ecred_reconf_rsp {
+ __le16 result;
+} __packed;
+
/* ----- L2CAP channels and connections ----- */
struct l2cap_seq_list {
__u16 head;
@@ -620,6 +661,7 @@
void (*suspend) (struct l2cap_chan *chan);
void (*set_shutdown) (struct l2cap_chan *chan);
long (*get_sndtimeo) (struct l2cap_chan *chan);
+ struct pid *(*get_peer_pid) (struct l2cap_chan *chan);
struct sk_buff *(*alloc_skb) (struct l2cap_chan *chan,
unsigned long hdr_len,
unsigned long len, int nb);
@@ -726,6 +768,7 @@
FLAG_EFS_ENABLE,
FLAG_DEFER_SETUP,
FLAG_LE_CONN_REQ_SENT,
+ FLAG_ECRED_CONN_REQ_SENT,
FLAG_PENDING_SECURITY,
FLAG_HOLD_HCI_CONN,
};
@@ -919,12 +962,14 @@
}
extern bool disable_ertm;
+extern bool enable_ecred;
int l2cap_init_sockets(void);
void l2cap_cleanup_sockets(void);
bool l2cap_is_socket(struct socket *sock);
void __l2cap_le_connect_rsp_defer(struct l2cap_chan *chan);
+void __l2cap_ecred_conn_rsp_defer(struct l2cap_chan *chan);
void __l2cap_connect_rsp_defer(struct l2cap_chan *chan);
int l2cap_add_psm(struct l2cap_chan *chan, bdaddr_t *src, __le16 psm);
@@ -934,6 +979,7 @@
void l2cap_chan_close(struct l2cap_chan *chan, int reason);
int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
bdaddr_t *dst, u8 dst_type);
+int l2cap_chan_reconfigure(struct l2cap_chan *chan, __u16 mtu);
int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len);
void l2cap_chan_busy(struct l2cap_chan *chan, int busy);
int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator);
@@ -941,6 +987,9 @@
int l2cap_ertm_init(struct l2cap_chan *chan);
void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan);
void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan);
+typedef void (*l2cap_chan_func_t)(struct l2cap_chan *chan, void *data);
+void l2cap_chan_list(struct l2cap_conn *conn, l2cap_chan_func_t func,
+ void *data);
void l2cap_chan_del(struct l2cap_chan *chan, int err);
void l2cap_send_conn_req(struct l2cap_chan *chan);
void l2cap_move_start(struct l2cap_chan *chan);
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 9cee7dd..6b55155 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -52,6 +52,12 @@
__le16 len;
} __packed;
+struct mgmt_tlv {
+ __le16 type;
+ __u8 length;
+ __u8 value[];
+} __packed;
+
struct mgmt_addr_info {
bdaddr_t bdaddr;
__u8 type;
@@ -70,14 +76,14 @@
struct mgmt_rp_read_commands {
__le16 num_commands;
__le16 num_events;
- __le16 opcodes[0];
+ __le16 opcodes[];
} __packed;
#define MGMT_OP_READ_INDEX_LIST 0x0003
#define MGMT_READ_INDEX_LIST_SIZE 0
struct mgmt_rp_read_index_list {
__le16 num_controllers;
- __le16 index[0];
+ __le16 index[];
} __packed;
/* Reserve one extra byte for names in management messages so that they
@@ -101,7 +107,8 @@
#define MGMT_SETTING_PRIVACY 0x00002000
#define MGMT_SETTING_CONFIGURATION 0x00004000
#define MGMT_SETTING_STATIC_ADDRESS 0x00008000
-#define MGMT_SETTING_PHY_CONFIGURATION 0x00010000
+#define MGMT_SETTING_PHY_CONFIGURATION 0x00010000
+#define MGMT_SETTING_WIDEBAND_SPEECH 0x00020000
#define MGMT_OP_READ_INFO 0x0004
#define MGMT_READ_INFO_SIZE 0
@@ -182,7 +189,7 @@
struct mgmt_cp_load_link_keys {
__u8 debug_keys;
__le16 key_count;
- struct mgmt_link_key_info keys[0];
+ struct mgmt_link_key_info keys[];
} __packed;
#define MGMT_LOAD_LINK_KEYS_SIZE 3
@@ -205,7 +212,7 @@
#define MGMT_OP_LOAD_LONG_TERM_KEYS 0x0013
struct mgmt_cp_load_long_term_keys {
__le16 key_count;
- struct mgmt_ltk_info keys[0];
+ struct mgmt_ltk_info keys[];
} __packed;
#define MGMT_LOAD_LONG_TERM_KEYS_SIZE 2
@@ -222,7 +229,7 @@
#define MGMT_GET_CONNECTIONS_SIZE 0
struct mgmt_rp_get_connections {
__le16 conn_count;
- struct mgmt_addr_info addr[0];
+ struct mgmt_addr_info addr[];
} __packed;
#define MGMT_OP_PIN_CODE_REPLY 0x0016
@@ -412,7 +419,7 @@
#define MGMT_OP_LOAD_IRKS 0x0030
struct mgmt_cp_load_irks {
__le16 irk_count;
- struct mgmt_irk_info irks[0];
+ struct mgmt_irk_info irks[];
} __packed;
#define MGMT_LOAD_IRKS_SIZE 2
@@ -464,7 +471,7 @@
#define MGMT_OP_LOAD_CONN_PARAM 0x0035
struct mgmt_cp_load_conn_param {
__le16 param_count;
- struct mgmt_conn_param params[0];
+ struct mgmt_conn_param params[];
} __packed;
#define MGMT_LOAD_CONN_PARAM_SIZE 2
@@ -472,7 +479,7 @@
#define MGMT_READ_UNCONF_INDEX_LIST_SIZE 0
struct mgmt_rp_read_unconf_index_list {
__le16 num_controllers;
- __le16 index[0];
+ __le16 index[];
} __packed;
#define MGMT_OPTION_EXTERNAL_CONFIG 0x00000001
@@ -503,7 +510,7 @@
__u8 type;
__s8 rssi;
__le16 uuid_count;
- __u8 uuids[0][16];
+ __u8 uuids[][16];
} __packed;
#define MGMT_START_SERVICE_DISCOVERY_SIZE 4
@@ -515,7 +522,7 @@
struct mgmt_rp_read_local_oob_ext_data {
__u8 type;
__le16 eir_len;
- __u8 eir[0];
+ __u8 eir[];
} __packed;
#define MGMT_OP_READ_EXT_INDEX_LIST 0x003C
@@ -526,7 +533,7 @@
__le16 index;
__u8 type;
__u8 bus;
- } entry[0];
+ } entry[];
} __packed;
#define MGMT_OP_READ_ADV_FEATURES 0x0003D
@@ -537,7 +544,7 @@
__u8 max_scan_rsp_len;
__u8 max_instances;
__u8 num_instances;
- __u8 instance[0];
+ __u8 instance[];
} __packed;
#define MGMT_OP_ADD_ADVERTISING 0x003E
@@ -548,7 +555,7 @@
__le16 timeout;
__u8 adv_data_len;
__u8 scan_rsp_len;
- __u8 data[0];
+ __u8 data[];
} __packed;
#define MGMT_ADD_ADVERTISING_SIZE 11
struct mgmt_rp_add_advertising {
@@ -565,6 +572,8 @@
#define MGMT_ADV_FLAG_SEC_1M BIT(7)
#define MGMT_ADV_FLAG_SEC_2M BIT(8)
#define MGMT_ADV_FLAG_SEC_CODED BIT(9)
+#define MGMT_ADV_FLAG_CAN_SET_TX_POWER BIT(10)
+#define MGMT_ADV_FLAG_HW_OFFLOAD BIT(11)
#define MGMT_ADV_FLAG_SEC_MASK (MGMT_ADV_FLAG_SEC_1M | MGMT_ADV_FLAG_SEC_2M | \
MGMT_ADV_FLAG_SEC_CODED)
@@ -602,7 +611,7 @@
__le32 supported_settings;
__le32 current_settings;
__le16 eir_len;
- __u8 eir[0];
+ __u8 eir[];
} __packed;
#define MGMT_OP_SET_APPEARANCE 0x0043
@@ -654,11 +663,130 @@
} __packed;
#define MGMT_SET_PHY_CONFIGURATION_SIZE 4
+#define MGMT_OP_SET_BLOCKED_KEYS 0x0046
+
+#define HCI_BLOCKED_KEY_TYPE_LINKKEY 0x00
+#define HCI_BLOCKED_KEY_TYPE_LTK 0x01
+#define HCI_BLOCKED_KEY_TYPE_IRK 0x02
+
+struct mgmt_blocked_key_info {
+ __u8 type;
+ __u8 val[16];
+} __packed;
+
+struct mgmt_cp_set_blocked_keys {
+ __le16 key_count;
+ struct mgmt_blocked_key_info keys[];
+} __packed;
+#define MGMT_OP_SET_BLOCKED_KEYS_SIZE 2
+
+#define MGMT_OP_SET_WIDEBAND_SPEECH 0x0047
+
+#define MGMT_OP_READ_SECURITY_INFO 0x0048
+#define MGMT_READ_SECURITY_INFO_SIZE 0
+struct mgmt_rp_read_security_info {
+ __le16 sec_len;
+ __u8 sec[];
+} __packed;
+
+#define MGMT_OP_READ_EXP_FEATURES_INFO 0x0049
+#define MGMT_READ_EXP_FEATURES_INFO_SIZE 0
+struct mgmt_rp_read_exp_features_info {
+ __le16 feature_count;
+ struct {
+ __u8 uuid[16];
+ __le32 flags;
+ } features[];
+} __packed;
+
+#define MGMT_OP_SET_EXP_FEATURE 0x004a
+struct mgmt_cp_set_exp_feature {
+ __u8 uuid[16];
+ __u8 param[];
+} __packed;
+#define MGMT_SET_EXP_FEATURE_SIZE 16
+struct mgmt_rp_set_exp_feature {
+ __u8 uuid[16];
+ __le32 flags;
+} __packed;
+
+#define MGMT_OP_READ_DEF_SYSTEM_CONFIG 0x004b
+#define MGMT_READ_DEF_SYSTEM_CONFIG_SIZE 0
+
+#define MGMT_OP_SET_DEF_SYSTEM_CONFIG 0x004c
+#define MGMT_SET_DEF_SYSTEM_CONFIG_SIZE 0
+
+#define MGMT_OP_READ_DEF_RUNTIME_CONFIG 0x004d
+#define MGMT_READ_DEF_RUNTIME_CONFIG_SIZE 0
+
+#define MGMT_OP_SET_DEF_RUNTIME_CONFIG 0x004e
+#define MGMT_SET_DEF_RUNTIME_CONFIG_SIZE 0
+
+#define MGMT_OP_GET_DEVICE_FLAGS 0x004F
+#define MGMT_GET_DEVICE_FLAGS_SIZE 7
+struct mgmt_cp_get_device_flags {
+ struct mgmt_addr_info addr;
+} __packed;
+struct mgmt_rp_get_device_flags {
+ struct mgmt_addr_info addr;
+ __le32 supported_flags;
+ __le32 current_flags;
+} __packed;
+
+#define MGMT_OP_SET_DEVICE_FLAGS 0x0050
+#define MGMT_SET_DEVICE_FLAGS_SIZE 11
+struct mgmt_cp_set_device_flags {
+ struct mgmt_addr_info addr;
+ __le32 current_flags;
+} __packed;
+struct mgmt_rp_set_device_flags {
+ struct mgmt_addr_info addr;
+} __packed;
+
+#define MGMT_ADV_MONITOR_FEATURE_MASK_OR_PATTERNS BIT(0)
+
+#define MGMT_OP_READ_ADV_MONITOR_FEATURES 0x0051
+#define MGMT_READ_ADV_MONITOR_FEATURES_SIZE 0
+struct mgmt_rp_read_adv_monitor_features {
+ __le32 supported_features;
+ __le32 enabled_features;
+ __le16 max_num_handles;
+ __u8 max_num_patterns;
+ __le16 num_handles;
+ __le16 handles[];
+} __packed;
+
+struct mgmt_adv_pattern {
+ __u8 ad_type;
+ __u8 offset;
+ __u8 length;
+ __u8 value[31];
+} __packed;
+
+#define MGMT_OP_ADD_ADV_PATTERNS_MONITOR 0x0052
+struct mgmt_cp_add_adv_patterns_monitor {
+ __u8 pattern_count;
+ struct mgmt_adv_pattern patterns[];
+} __packed;
+#define MGMT_ADD_ADV_PATTERNS_MONITOR_SIZE 1
+struct mgmt_rp_add_adv_patterns_monitor {
+ __le16 monitor_handle;
+} __packed;
+
+#define MGMT_OP_REMOVE_ADV_MONITOR 0x0053
+struct mgmt_cp_remove_adv_monitor {
+ __le16 monitor_handle;
+} __packed;
+#define MGMT_REMOVE_ADV_MONITOR_SIZE 2
+struct mgmt_rp_remove_adv_monitor {
+ __le16 monitor_handle;
+} __packed;
+
#define MGMT_EV_CMD_COMPLETE 0x0001
struct mgmt_ev_cmd_complete {
__le16 opcode;
__u8 status;
- __u8 data[0];
+ __u8 data[];
} __packed;
#define MGMT_EV_CMD_STATUS 0x0002
@@ -706,7 +834,7 @@
struct mgmt_addr_info addr;
__le32 flags;
__le16 eir_len;
- __u8 eir[0];
+ __u8 eir[];
} __packed;
#define MGMT_DEV_DISCONN_UNKNOWN 0x00
@@ -714,6 +842,7 @@
#define MGMT_DEV_DISCONN_LOCAL_HOST 0x02
#define MGMT_DEV_DISCONN_REMOTE 0x03
#define MGMT_DEV_DISCONN_AUTH_FAILURE 0x04
+#define MGMT_DEV_DISCONN_LOCAL_HOST_SUSPEND 0x05
#define MGMT_EV_DEVICE_DISCONNECTED 0x000C
struct mgmt_ev_device_disconnected {
@@ -761,7 +890,7 @@
__s8 rssi;
__le32 flags;
__le16 eir_len;
- __u8 eir[0];
+ __u8 eir[];
} __packed;
#define MGMT_EV_DISCOVERING 0x0013
@@ -856,7 +985,7 @@
struct mgmt_ev_local_oob_data_updated {
__u8 type;
__le16 eir_len;
- __u8 eir[0];
+ __u8 eir[];
} __packed;
#define MGMT_EV_ADVERTISING_ADDED 0x0023
@@ -872,10 +1001,48 @@
#define MGMT_EV_EXT_INFO_CHANGED 0x0025
struct mgmt_ev_ext_info_changed {
__le16 eir_len;
- __u8 eir[0];
+ __u8 eir[];
} __packed;
#define MGMT_EV_PHY_CONFIGURATION_CHANGED 0x0026
struct mgmt_ev_phy_configuration_changed {
__le32 selected_phys;
} __packed;
+
+#define MGMT_EV_EXP_FEATURE_CHANGED 0x0027
+struct mgmt_ev_exp_feature_changed {
+ __u8 uuid[16];
+ __le32 flags;
+} __packed;
+
+#define MGMT_EV_DEVICE_FLAGS_CHANGED 0x002a
+struct mgmt_ev_device_flags_changed {
+ struct mgmt_addr_info addr;
+ __le32 supported_flags;
+ __le32 current_flags;
+} __packed;
+
+#define MGMT_EV_ADV_MONITOR_ADDED 0x002b
+struct mgmt_ev_adv_monitor_added {
+ __le16 monitor_handle;
+} __packed;
+
+#define MGMT_EV_ADV_MONITOR_REMOVED 0x002c
+struct mgmt_ev_adv_monitor_removed {
+ __le16 monitor_handle;
+} __packed;
+
+#define MGMT_EV_CONTROLLER_SUSPEND 0x002d
+struct mgmt_ev_controller_suspend {
+ __u8 suspend_state;
+} __packed;
+
+#define MGMT_EV_CONTROLLER_RESUME 0x002e
+struct mgmt_ev_controller_resume {
+ __u8 wake_reason;
+ struct mgmt_addr_info addr;
+} __packed;
+
+#define MGMT_WAKE_REASON_NON_BT_WAKE 0x0
+#define MGMT_WAKE_REASON_UNEXPECTED 0x1
+#define MGMT_WAKE_REASON_REMOTE_WAKE 0x2
diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h
index da4acef..99d2687 100644
--- a/include/net/bluetooth/rfcomm.h
+++ b/include/net/bluetooth/rfcomm.h
@@ -34,7 +34,6 @@
#define RFCOMM_DEFAULT_MTU 127
#define RFCOMM_DEFAULT_CREDITS 7
-#define RFCOMM_MAX_L2CAP_MTU 1013
#define RFCOMM_MAX_CREDITS 40
#define RFCOMM_SKB_HEAD_RESERVE 8
@@ -356,7 +355,7 @@
struct rfcomm_dev_list_req {
u16 dev_num;
- struct rfcomm_dev_info dev_info[0];
+ struct rfcomm_dev_info dev_info[];
};
int rfcomm_dev_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
diff --git a/include/net/bluetooth/sco.h b/include/net/bluetooth/sco.h
index f40ddb4..1aa2e14 100644
--- a/include/net/bluetooth/sco.h
+++ b/include/net/bluetooth/sco.h
@@ -46,4 +46,6 @@
__u8 dev_class[3];
};
+#define SCO_CMSG_PKT_STATUS 0x01
+
#endif /* __SCO_H */
diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h
index c8696a2..1a28f29 100644
--- a/include/net/bond_3ad.h
+++ b/include/net/bond_3ad.h
@@ -262,7 +262,7 @@
struct ad_bond_info {
struct ad_system system; /* 802.3ad system structure */
struct bond_3ad_stats stats;
- u32 agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */
+ atomic_t agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */
u16 aggregator_identifier;
};
diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h
index b3504fc..191c36a 100644
--- a/include/net/bond_alb.h
+++ b/include/net/bond_alb.h
@@ -126,7 +126,7 @@
struct alb_bond_info {
struct tlb_client_info *tx_hashtbl; /* Dynamically allocated */
u32 unbalanced_load;
- int tx_rebalance_counter;
+ atomic_t tx_rebalance_counter;
int lp_counter;
/* -------- rlb parameters -------- */
int rlb_enabled;
@@ -158,6 +158,10 @@
void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave);
int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
+struct slave *bond_xmit_alb_slave_get(struct bonding *bond,
+ struct sk_buff *skb);
+struct slave *bond_xmit_tlb_slave_get(struct bonding *bond,
+ struct sk_buff *skb);
void bond_alb_monitor(struct work_struct *);
int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr);
void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id);
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 1bee8fd..67d6760 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -86,6 +86,9 @@
#define bond_for_each_slave_rcu(bond, pos, iter) \
netdev_for_each_lower_private_rcu((bond)->dev, pos, iter)
+#define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \
+ NETIF_F_GSO_ESP)
+
#ifdef CONFIG_NET_POLL_CONTROLLER
extern atomic_t netpoll_block_tx;
@@ -188,7 +191,7 @@
struct bond_up_slave {
unsigned int count;
struct rcu_head rcu;
- struct slave *arr[0];
+ struct slave *arr[];
};
/*
@@ -196,6 +199,11 @@
*/
#define BOND_LINK_NOCHANGE -1
+struct bond_ipsec {
+ struct list_head list;
+ struct xfrm_state *xs;
+};
+
/*
* Here are the locking policies for the two bonding locks:
* Get rcu_read_lock when reading or RTNL when writing slave list.
@@ -205,7 +213,8 @@
struct slave __rcu *curr_active_slave;
struct slave __rcu *current_arp_slave;
struct slave __rcu *primary_slave;
- struct bond_up_slave __rcu *slave_arr; /* Array of usable slaves */
+ struct bond_up_slave __rcu *usable_slaves;
+ struct bond_up_slave __rcu *all_slaves;
bool force_primary;
s32 slave_cnt; /* never change this value outside the attach/detach wrappers */
int (*recv_probe)(const struct sk_buff *, struct bonding *,
@@ -242,7 +251,11 @@
struct dentry *debug_dir;
#endif /* CONFIG_DEBUG_FS */
struct rtnl_link_stats64 bond_stats;
- struct lock_class_key stats_lock_key;
+#ifdef CONFIG_XFRM_OFFLOAD
+ struct list_head ipsec_list;
+ /* protecting ipsec_list */
+ spinlock_t ipsec_lock;
+#endif /* CONFIG_XFRM_OFFLOAD */
};
#define bond_slave_get_rcu(dev) \
@@ -510,18 +523,17 @@
}
#ifdef CONFIG_NET_POLL_CONTROLLER
-static inline void bond_netpoll_send_skb(const struct slave *slave,
+static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave,
struct sk_buff *skb)
{
- struct netpoll *np = slave->np;
-
- if (np)
- netpoll_send_skb(np, skb);
+ return netpoll_send_skb(slave->np, skb);
}
#else
-static inline void bond_netpoll_send_skb(const struct slave *slave,
+static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave,
struct sk_buff *skb)
{
+ BUG();
+ return NETDEV_TX_OK;
}
#endif
@@ -615,7 +627,7 @@
};
int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave);
-void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev);
+netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev);
int bond_create(struct net *net, const char *name);
int bond_create_sysfs(struct bond_net *net);
void bond_destroy_sysfs(struct bond_net *net);
@@ -751,10 +763,11 @@
/* exported from bond_sysfs_slave.c */
extern const struct sysfs_ops slave_sysfs_ops;
-static inline void bond_tx_drop(struct net_device *dev, struct sk_buff *skb)
+static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb)
{
atomic_long_inc(&dev->tx_dropped);
dev_kfree_skb_any(skb);
+ return NET_XMIT_DROP;
}
#endif /* _NET_BONDING_H */
diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index 8e4f831..3c516dd 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -3,6 +3,17 @@
#ifndef _BPF_SK_STORAGE_H
#define _BPF_SK_STORAGE_H
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <net/sock.h>
+#include <uapi/linux/sock_diag.h>
+#include <uapi/linux/btf.h>
+#include <linux/bpf_local_storage.h>
+
struct sock;
void bpf_sk_storage_free(struct sock *sk);
@@ -10,14 +21,42 @@
extern const struct bpf_func_proto bpf_sk_storage_get_proto;
extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
+struct bpf_local_storage_elem;
+struct bpf_sk_storage_diag;
+struct sk_buff;
+struct nlattr;
+struct sock;
+
#ifdef CONFIG_BPF_SYSCALL
int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk);
+struct bpf_sk_storage_diag *
+bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs);
+void bpf_sk_storage_diag_free(struct bpf_sk_storage_diag *diag);
+int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
+ struct sock *sk, struct sk_buff *skb,
+ int stg_array_type,
+ unsigned int *res_diag_size);
#else
static inline int bpf_sk_storage_clone(const struct sock *sk,
struct sock *newsk)
{
return 0;
}
+static inline struct bpf_sk_storage_diag *
+bpf_sk_storage_diag_alloc(const struct nlattr *nla)
+{
+ return NULL;
+}
+static inline void bpf_sk_storage_diag_free(struct bpf_sk_storage_diag *diag)
+{
+}
+static inline int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
+ struct sock *sk, struct sk_buff *skb,
+ int stg_array_type,
+ unsigned int *res_diag_size)
+{
+ return 0;
+}
#endif
#endif /* _BPF_SK_STORAGE_H */
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 9899b9a..716b7c5 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -114,7 +114,11 @@
struct napi_struct *napi)
{
#ifdef CONFIG_NET_RX_BUSY_POLL
- skb->napi_id = napi->napi_id;
+ /* If the skb was already marked with a valid NAPI ID, avoid overwriting
+ * it.
+ */
+ if (skb->napi_id < MIN_NAPI_ID)
+ skb->napi_id = napi->napi_id;
#endif
}
diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h
index 0640941..51f7bb4 100644
--- a/include/net/caif/caif_layer.h
+++ b/include/net/caif/caif_layer.h
@@ -156,7 +156,7 @@
* CAIF packets upwards in the stack.
* Packet handling rules:
* - The CAIF packet (cfpkt) ownership is passed to the
- * called receive function. This means that the the
+ * called receive function. This means that the
* packet cannot be accessed after passing it to the
* above layer using up->receive().
*
@@ -184,7 +184,7 @@
* CAIF packet downwards in the stack.
* Packet handling rules:
* - The CAIF packet (cfpkt) ownership is passed to the
- * transmit function. This means that the the packet
+ * transmit function. This means that the packet
* cannot be accessed after passing it to the below
* layer using dn->transmit().
*
diff --git a/include/net/caif/caif_spi.h b/include/net/caif/caif_spi.h
deleted file mode 100644
index a0bf4cb..0000000
--- a/include/net/caif/caif_spi.h
+++ /dev/null
@@ -1,155 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Author: Daniel Martensson / Daniel.Martensson@stericsson.com
- */
-
-#ifndef CAIF_SPI_H_
-#define CAIF_SPI_H_
-
-#include <net/caif/caif_device.h>
-
-#define SPI_CMD_WR 0x00
-#define SPI_CMD_RD 0x01
-#define SPI_CMD_EOT 0x02
-#define SPI_CMD_IND 0x04
-
-#define SPI_DMA_BUF_LEN 8192
-
-#define WL_SZ 2 /* 16 bits. */
-#define SPI_CMD_SZ 4 /* 32 bits. */
-#define SPI_IND_SZ 4 /* 32 bits. */
-
-#define SPI_XFER 0
-#define SPI_SS_ON 1
-#define SPI_SS_OFF 2
-#define SPI_TERMINATE 3
-
-/* Minimum time between different levels is 50 microseconds. */
-#define MIN_TRANSITION_TIME_USEC 50
-
-/* Defines for calculating duration of SPI transfers for a particular
- * number of bytes.
- */
-#define SPI_MASTER_CLK_MHZ 13
-#define SPI_XFER_TIME_USEC(bytes, clk) (((bytes) * 8) / clk)
-
-/* Normally this should be aligned on the modem in order to benefit from full
- * duplex transfers. However a size of 8188 provokes errors when running with
- * the modem. These errors occur when packet sizes approaches 4 kB of data.
- */
-#define CAIF_MAX_SPI_FRAME 4092
-
-/* Maximum number of uplink CAIF frames that can reside in the same SPI frame.
- * This number should correspond with the modem setting. The application side
- * CAIF accepts any number of embedded downlink CAIF frames.
- */
-#define CAIF_MAX_SPI_PKTS 9
-
-/* Decides if SPI buffers should be prefilled with 0xFF pattern for easier
- * debugging. Both TX and RX buffers will be filled before the transfer.
- */
-#define CFSPI_DBG_PREFILL 0
-
-/* Structure describing a SPI transfer. */
-struct cfspi_xfer {
- u16 tx_dma_len;
- u16 rx_dma_len;
- void *va_tx[2];
- dma_addr_t pa_tx[2];
- void *va_rx;
- dma_addr_t pa_rx;
-};
-
-/* Structure implemented by the SPI interface. */
-struct cfspi_ifc {
- void (*ss_cb) (bool assert, struct cfspi_ifc *ifc);
- void (*xfer_done_cb) (struct cfspi_ifc *ifc);
- void *priv;
-};
-
-/* Structure implemented by SPI clients. */
-struct cfspi_dev {
- int (*init_xfer) (struct cfspi_xfer *xfer, struct cfspi_dev *dev);
- void (*sig_xfer) (bool xfer, struct cfspi_dev *dev);
- struct cfspi_ifc *ifc;
- char *name;
- u32 clk_mhz;
- void *priv;
-};
-
-/* Enumeration describing the CAIF SPI state. */
-enum cfspi_state {
- CFSPI_STATE_WAITING = 0,
- CFSPI_STATE_AWAKE,
- CFSPI_STATE_FETCH_PKT,
- CFSPI_STATE_GET_NEXT,
- CFSPI_STATE_INIT_XFER,
- CFSPI_STATE_WAIT_ACTIVE,
- CFSPI_STATE_SIG_ACTIVE,
- CFSPI_STATE_WAIT_XFER_DONE,
- CFSPI_STATE_XFER_DONE,
- CFSPI_STATE_WAIT_INACTIVE,
- CFSPI_STATE_SIG_INACTIVE,
- CFSPI_STATE_DELIVER_PKT,
- CFSPI_STATE_MAX,
-};
-
-/* Structure implemented by SPI physical interfaces. */
-struct cfspi {
- struct caif_dev_common cfdev;
- struct net_device *ndev;
- struct platform_device *pdev;
- struct sk_buff_head qhead;
- struct sk_buff_head chead;
- u16 cmd;
- u16 tx_cpck_len;
- u16 tx_npck_len;
- u16 rx_cpck_len;
- u16 rx_npck_len;
- struct cfspi_ifc ifc;
- struct cfspi_xfer xfer;
- struct cfspi_dev *dev;
- unsigned long state;
- struct work_struct work;
- struct workqueue_struct *wq;
- struct list_head list;
- int flow_off_sent;
- u32 qd_low_mark;
- u32 qd_high_mark;
- struct completion comp;
- wait_queue_head_t wait;
- spinlock_t lock;
- bool flow_stop;
- bool slave;
- bool slave_talked;
-#ifdef CONFIG_DEBUG_FS
- enum cfspi_state dbg_state;
- u16 pcmd;
- u16 tx_ppck_len;
- u16 rx_ppck_len;
- struct dentry *dbgfs_dir;
- struct dentry *dbgfs_state;
- struct dentry *dbgfs_frame;
-#endif /* CONFIG_DEBUG_FS */
-};
-
-extern int spi_frm_align;
-extern int spi_up_head_align;
-extern int spi_up_tail_align;
-extern int spi_down_head_align;
-extern int spi_down_tail_align;
-extern struct platform_driver cfspi_spi_driver;
-
-void cfspi_dbg_state(struct cfspi *cfspi, int state);
-int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-int cfspi_xmitlen(struct cfspi *cfspi);
-int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-int cfspi_spi_remove(struct platform_device *pdev);
-int cfspi_spi_probe(struct platform_device *pdev);
-int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-int cfspi_xmitlen(struct cfspi *cfspi);
-int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-void cfspi_xfer(struct work_struct *work);
-
-#endif /* CAIF_SPI_H_ */
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 69b9ccb..2a819be 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -7,7 +7,7 @@
* Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2019 Intel Corporation
+ * Copyright (C) 2018-2020 Intel Corporation
*/
#include <linux/netdevice.h>
@@ -72,12 +72,12 @@
*
* @IEEE80211_CHAN_DISABLED: This channel is disabled.
* @IEEE80211_CHAN_NO_IR: do not initiate radiation, this includes
- * sending probe requests or beaconing.
+ * sending probe requests or beaconing.
* @IEEE80211_CHAN_RADAR: Radar detection is required on this channel.
* @IEEE80211_CHAN_NO_HT40PLUS: extension channel above this channel
- * is not permitted.
+ * is not permitted.
* @IEEE80211_CHAN_NO_HT40MINUS: extension channel below this channel
- * is not permitted.
+ * is not permitted.
* @IEEE80211_CHAN_NO_OFDM: OFDM is not allowed on this channel.
* @IEEE80211_CHAN_NO_80MHZ: If the driver supports 80 MHz on the band,
* this flag indicates that an 80 MHz channel cannot use this
@@ -95,6 +95,17 @@
* on this channel.
* @IEEE80211_CHAN_NO_10MHZ: 10 MHz bandwidth is not permitted
* on this channel.
+ * @IEEE80211_CHAN_NO_HE: HE operation is not permitted on this channel.
+ * @IEEE80211_CHAN_1MHZ: 1 MHz bandwidth is permitted
+ * on this channel.
+ * @IEEE80211_CHAN_2MHZ: 2 MHz bandwidth is permitted
+ * on this channel.
+ * @IEEE80211_CHAN_4MHZ: 4 MHz bandwidth is permitted
+ * on this channel.
+ * @IEEE80211_CHAN_8MHZ: 8 MHz bandwidth is permitted
+ * on this channel.
+ * @IEEE80211_CHAN_16MHZ: 16 MHz bandwidth is permitted
+ * on this channel.
*
*/
enum ieee80211_channel_flags {
@@ -111,6 +122,12 @@
IEEE80211_CHAN_IR_CONCURRENT = 1<<10,
IEEE80211_CHAN_NO_20MHZ = 1<<11,
IEEE80211_CHAN_NO_10MHZ = 1<<12,
+ IEEE80211_CHAN_NO_HE = 1<<13,
+ IEEE80211_CHAN_1MHZ = 1<<14,
+ IEEE80211_CHAN_2MHZ = 1<<15,
+ IEEE80211_CHAN_4MHZ = 1<<16,
+ IEEE80211_CHAN_8MHZ = 1<<17,
+ IEEE80211_CHAN_16MHZ = 1<<18,
};
#define IEEE80211_CHAN_NO_HT40 \
@@ -126,6 +143,7 @@
* with cfg80211.
*
* @center_freq: center frequency in MHz
+ * @freq_offset: offset from @center_freq, in KHz
* @hw_value: hardware-specific value for the channel
* @flags: channel flags from &enum ieee80211_channel_flags.
* @orig_flags: channel flags at registration time, used by regulatory
@@ -147,6 +165,7 @@
struct ieee80211_channel {
enum nl80211_band band;
u32 center_freq;
+ u16 freq_offset;
u16 hw_value;
u32 flags;
int max_antenna_gain;
@@ -250,13 +269,49 @@
* struct ieee80211_he_obss_pd - AP settings for spatial reuse
*
* @enable: is the feature enabled.
+ * @sr_ctrl: The SR Control field of SRP element.
+ * @non_srg_max_offset: non-SRG maximum tx power offset
* @min_offset: minimal tx power offset an associated station shall use
* @max_offset: maximum tx power offset an associated station shall use
+ * @bss_color_bitmap: bitmap that indicates the BSS color values used by
+ * members of the SRG
+ * @partial_bssid_bitmap: bitmap that indicates the partial BSSID values
+ * used by members of the SRG
*/
struct ieee80211_he_obss_pd {
bool enable;
+ u8 sr_ctrl;
+ u8 non_srg_max_offset;
u8 min_offset;
u8 max_offset;
+ u8 bss_color_bitmap[8];
+ u8 partial_bssid_bitmap[8];
+};
+
+/**
+ * struct cfg80211_he_bss_color - AP settings for BSS coloring
+ *
+ * @color: the current color.
+ * @enabled: HE BSS color is used
+ * @partial: define the AID equation.
+ */
+struct cfg80211_he_bss_color {
+ u8 color;
+ bool enabled;
+ bool partial;
+};
+
+/**
+ * struct ieee80211_he_bss_color - AP settings for BSS coloring
+ *
+ * @color: the current color.
+ * @disabled: is the feature disabled.
+ * @partial: define the AID equation.
+ */
+struct ieee80211_he_bss_color {
+ u8 color;
+ bool disabled;
+ bool partial;
};
/**
@@ -324,10 +379,13 @@
*
* @types_mask: interface types mask
* @he_cap: holds the HE capabilities
+ * @he_6ghz_capa: HE 6 GHz capabilities, must be filled in for a
+ * 6 GHz band channel (and 0 may be valid value).
*/
struct ieee80211_sband_iftype_data {
u16 types_mask;
struct ieee80211_sta_he_cap he_cap;
+ struct ieee80211_he_6ghz_capa he_6ghz_capa;
};
/**
@@ -385,12 +443,28 @@
};
/**
+ * struct ieee80211_sta_s1g_cap - STA's S1G capabilities
+ *
+ * This structure describes most essential parameters needed
+ * to describe 802.11ah S1G capabilities for a STA.
+ *
+ * @s1g_supported: is STA an S1G STA
+ * @cap: S1G capabilities information
+ * @nss_mcs: Supported NSS MCS set
+ */
+struct ieee80211_sta_s1g_cap {
+ bool s1g;
+ u8 cap[10]; /* use S1G_CAPAB_ */
+ u8 nss_mcs[5];
+};
+
+/**
* struct ieee80211_supported_band - frequency band definition
*
* This structure describes a frequency band a wiphy
* is able to operate in.
*
- * @channels: Array of channels the hardware can operate in
+ * @channels: Array of channels the hardware can operate with
* in this band.
* @band: the band this structure represents
* @n_channels: Number of channels in @channels
@@ -400,7 +474,9 @@
* @n_bitrates: Number of bitrates in @bitrates
* @ht_cap: HT capabilities in this band
* @vht_cap: VHT capabilities in this band
+ * @s1g_cap: S1G capabilities in this band
* @edmg_cap: EDMG capabilities in this band
+ * @s1g_cap: S1G capabilities in this band (S1B band only, of course)
* @n_iftype_data: number of iftype data entries
* @iftype_data: interface type data entries. Note that the bits in
* @types_mask inside this structure cannot overlap (i.e. only
@@ -415,6 +491,7 @@
int n_bitrates;
struct ieee80211_sta_ht_cap ht_cap;
struct ieee80211_sta_vht_cap vht_cap;
+ struct ieee80211_sta_s1g_cap s1g_cap;
struct ieee80211_edmg edmg_cap;
u16 n_iftype_data;
const struct ieee80211_sband_iftype_data *iftype_data;
@@ -480,6 +557,26 @@
}
/**
+ * ieee80211_get_he_6ghz_capa - return HE 6 GHz capabilities
+ * @sband: the sband to search for the STA on
+ * @iftype: the iftype to search for
+ *
+ * Return: the 6GHz capabilities
+ */
+static inline __le16
+ieee80211_get_he_6ghz_capa(const struct ieee80211_supported_band *sband,
+ enum nl80211_iftype iftype)
+{
+ const struct ieee80211_sband_iftype_data *data =
+ ieee80211_get_sband_iftype_data(sband, iftype);
+
+ if (WARN_ON(!data || !data->he_cap.has_he))
+ return 0;
+
+ return data->he_6ghz_capa.capa;
+}
+
+/**
* wiphy_read_of_freq_limits - read frequency limits from device tree
*
* @wiphy: the wireless device to get extra limits for
@@ -565,6 +662,7 @@
* with the get_key() callback, must be in little endian,
* length given by @seq_len.
* @seq_len: length of @seq.
+ * @vlan_id: vlan_id for VLAN group key (if nonzero)
* @mode: key install mode (RX_TX, NO_TX or SET_TX)
*/
struct key_params {
@@ -572,6 +670,7 @@
const u8 *seq;
int key_len;
int seq_len;
+ u16 vlan_id;
u32 cipher;
enum nl80211_key_mode mode;
};
@@ -587,6 +686,7 @@
* If edmg is requested (i.e. the .channels member is non-zero),
* chan will define the primary channel and all other
* parameters are ignored.
+ * @freq1_offset: offset from @center_freq1, in KHz
*/
struct cfg80211_chan_def {
struct ieee80211_channel *chan;
@@ -594,6 +694,64 @@
u32 center_freq1;
u32 center_freq2;
struct ieee80211_edmg edmg;
+ u16 freq1_offset;
+};
+
+/*
+ * cfg80211_bitrate_mask - masks for bitrate control
+ */
+struct cfg80211_bitrate_mask {
+ struct {
+ u32 legacy;
+ u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN];
+ u16 vht_mcs[NL80211_VHT_NSS_MAX];
+ u16 he_mcs[NL80211_HE_NSS_MAX];
+ enum nl80211_txrate_gi gi;
+ enum nl80211_he_gi he_gi;
+ enum nl80211_he_ltf he_ltf;
+ } control[NUM_NL80211_BANDS];
+};
+
+
+/**
+ * struct cfg80211_tid_cfg - TID specific configuration
+ * @config_override: Flag to notify driver to reset TID configuration
+ * of the peer.
+ * @tids: bitmap of TIDs to modify
+ * @mask: bitmap of attributes indicating which parameter changed,
+ * similar to &nl80211_tid_config_supp.
+ * @noack: noack configuration value for the TID
+ * @retry_long: retry count value
+ * @retry_short: retry count value
+ * @ampdu: Enable/Disable MPDU aggregation
+ * @rtscts: Enable/Disable RTS/CTS
+ * @amsdu: Enable/Disable MSDU aggregation
+ * @txrate_type: Tx bitrate mask type
+ * @txrate_mask: Tx bitrate to be applied for the TID
+ */
+struct cfg80211_tid_cfg {
+ bool config_override;
+ u8 tids;
+ u64 mask;
+ enum nl80211_tid_config noack;
+ u8 retry_long, retry_short;
+ enum nl80211_tid_config ampdu;
+ enum nl80211_tid_config rtscts;
+ enum nl80211_tid_config amsdu;
+ enum nl80211_tx_rate_setting txrate_type;
+ struct cfg80211_bitrate_mask txrate_mask;
+};
+
+/**
+ * struct cfg80211_tid_config - TID configuration
+ * @peer: Station's MAC address
+ * @n_tid_conf: Number of TID specific configurations to be applied
+ * @tid_conf: Configuration change info
+ */
+struct cfg80211_tid_config {
+ const u8 *peer;
+ u32 n_tid_conf;
+ struct cfg80211_tid_cfg tid_conf[];
};
/**
@@ -648,6 +806,7 @@
return (chandef1->chan == chandef2->chan &&
chandef1->width == chandef2->width &&
chandef1->center_freq1 == chandef2->center_freq1 &&
+ chandef1->freq1_offset == chandef2->freq1_offset &&
chandef1->center_freq2 == chandef2->center_freq2);
}
@@ -840,6 +999,8 @@
* protocol frames.
* @control_port_over_nl80211: TRUE if userspace expects to exchange control
* port frames over NL80211 instead of the network interface.
+ * @control_port_no_preauth: disables pre-auth rx over the nl80211 control
+ * port for mac80211
* @wep_keys: static WEP keys, if not NULL points to an array of
* CFG80211_MAX_WEP_KEYS WEP keys
* @wep_tx_key: key index (0..3) of the default TX static WEP key
@@ -859,6 +1020,7 @@
__be16 control_port_ethertype;
bool control_port_no_encrypt;
bool control_port_over_nl80211;
+ bool control_port_no_preauth;
struct key_params *wep_keys;
int wep_tx_key;
const u8 *psk;
@@ -932,16 +1094,37 @@
struct mac_address mac_addrs[];
};
-/*
- * cfg80211_bitrate_mask - masks for bitrate control
+/**
+ * struct cfg80211_fils_discovery - FILS discovery parameters from
+ * IEEE Std 802.11ai-2016, Annex C.3 MIB detail.
+ *
+ * @min_interval: Minimum packet interval in TUs (0 - 10000)
+ * @max_interval: Maximum packet interval in TUs (0 - 10000)
+ * @tmpl_len: Template length
+ * @tmpl: Template data for FILS discovery frame including the action
+ * frame headers.
*/
-struct cfg80211_bitrate_mask {
- struct {
- u32 legacy;
- u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN];
- u16 vht_mcs[NL80211_VHT_NSS_MAX];
- enum nl80211_txrate_gi gi;
- } control[NUM_NL80211_BANDS];
+struct cfg80211_fils_discovery {
+ u32 min_interval;
+ u32 max_interval;
+ size_t tmpl_len;
+ const u8 *tmpl;
+};
+
+/**
+ * struct cfg80211_unsol_bcast_probe_resp - Unsolicited broadcast probe
+ * response parameters in 6GHz.
+ *
+ * @interval: Packet interval in TUs. Maximum allowed is 20 TU, as mentioned
+ * in IEEE P802.11ax/D6.0 26.17.2.3.2 - AP behavior for fast passive
+ * scanning
+ * @tmpl_len: Template length
+ * @tmpl: Template data for probe response
+ */
+struct cfg80211_unsol_bcast_probe_resp {
+ u32 interval;
+ size_t tmpl_len;
+ const u8 *tmpl;
};
/**
@@ -986,8 +1169,13 @@
* @ht_required: stations must support HT
* @vht_required: stations must support VHT
* @twt_responder: Enable Target Wait Time
+ * @he_required: stations must support HE
* @flags: flags, as defined in enum cfg80211_ap_settings_flags
* @he_obss_pd: OBSS Packet Detection settings
+ * @he_bss_color: BSS Color settings
+ * @he_oper: HE operation IE (or %NULL if HE isn't enabled)
+ * @fils_discovery: FILS discovery transmission parameters
+ * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters
*/
struct cfg80211_ap_settings {
struct cfg80211_chan_def chandef;
@@ -1012,10 +1200,14 @@
const struct ieee80211_ht_cap *ht_cap;
const struct ieee80211_vht_cap *vht_cap;
const struct ieee80211_he_cap_elem *he_cap;
- bool ht_required, vht_required;
+ const struct ieee80211_he_operation *he_oper;
+ bool ht_required, vht_required, he_required;
bool twt_responder;
u32 flags;
struct ieee80211_he_obss_pd he_obss_pd;
+ struct cfg80211_he_bss_color he_bss_color;
+ struct cfg80211_fils_discovery fils_discovery;
+ struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp;
};
/**
@@ -1124,6 +1316,7 @@
* (bitmask of BIT(%NL80211_STA_FLAG_...))
* @listen_interval: listen interval or -1 for no change
* @aid: AID or zero for no change
+ * @vlan_id: VLAN ID for station (if nonzero)
* @peer_aid: mesh peer AID or zero for no change
* @plink_action: plink action to take
* @plink_state: set the peer link state for a station
@@ -1151,6 +1344,8 @@
* @he_capa: HE capabilities of station
* @he_capa_len: the length of the HE capabilities
* @airtime_weight: airtime scheduler weight for this station
+ * @txpwr: transmit power for an associated station
+ * @he_6ghz_capa: HE 6 GHz Band capabilities of station
*/
struct station_parameters {
const u8 *supported_rates;
@@ -1159,6 +1354,7 @@
u32 sta_modify_mask;
int listen_interval;
u16 aid;
+ u16 vlan_id;
u16 peer_aid;
u8 supported_rates_len;
u8 plink_action;
@@ -1182,6 +1378,7 @@
u8 he_capa_len;
u16 airtime_weight;
struct sta_txpwr txpwr;
+ const struct ieee80211_he_6ghz_capa *he_6ghz_capa;
};
/**
@@ -1247,7 +1444,7 @@
enum cfg80211_station_type statype);
/**
- * enum station_info_rate_flags - bitrate info flags
+ * enum rate_info_flags - bitrate info flags
*
* Used by the driver to indicate the specific rate transmission
* type for 802.11n transmissions.
@@ -1320,7 +1517,7 @@
};
/**
- * enum station_info_rate_flags - bitrate info flags
+ * enum bss_param_flags - bitrate info flags
*
* Used by the driver to indicate the specific rate transmission
* type for 802.11n transmissions.
@@ -1468,6 +1665,7 @@
* an FCS error. This counter should be incremented only when TA of the
* received packet with an FCS error matches the peer MAC address.
* @airtime_link_metric: mesh airtime link metric.
+ * @connected_to_as: true if mesh STA has a path to authentication server
*/
struct station_info {
u64 filled;
@@ -1525,6 +1723,8 @@
u32 fcs_err_count;
u32 airtime_link_metric;
+
+ u8 connected_to_as;
};
#if IS_ENABLED(CONFIG_CFG80211)
@@ -1651,8 +1851,9 @@
* (or NULL for no change)
* @basic_rates_len: number of basic rates
* @ap_isolate: do not forward packets between connected stations
+ * (0 = no, 1 = yes, -1 = do not change)
* @ht_opmode: HT Operation mode
- * (u16 = opmode, -1 = do not change)
+ * (u16 = opmode, -1 = do not change)
* @p2p_ctwindow: P2P CT Window (-1 = no change)
* @p2p_opp_ps: P2P opportunistic PS (-1 = no change)
*/
@@ -1740,6 +1941,11 @@
* connected to a mesh gate in mesh formation info. If false, the
* value in mesh formation is determined by the presence of root paths
* in the mesh path table
+ * @dot11MeshNolearn: Try to avoid multi-hop path discovery (e.g. PREQ/PREP
+ * for HWMP) if the destination is a direct neighbor. Note that this might
+ * not be the optimal decision as a multi-hop route might be better. So
+ * if using this setting you will likely also want to disable
+ * dot11MeshForwarding and use another mesh routing protocol on top.
*/
struct mesh_config {
u16 dot11MeshRetryTimeout;
@@ -1760,6 +1966,7 @@
u16 dot11MeshHWMPnetDiameterTraversalTime;
u8 dot11MeshHWMPRootMode;
bool dot11MeshConnectedToMeshGate;
+ bool dot11MeshConnectedToAuthServer;
u16 dot11MeshHWMPRannInterval;
bool dot11MeshGateAnnouncementProtocol;
bool dot11MeshForwarding;
@@ -1771,6 +1978,7 @@
enum nl80211_mesh_power_mode power_mode;
u16 dot11MeshAwakeWindowDuration;
u32 plink_timeout;
+ bool dot11MeshNolearn;
};
/**
@@ -1899,6 +2107,27 @@
};
/**
+ * struct cfg80211_scan_6ghz_params - relevant for 6 GHz only
+ *
+ * @short_bssid: short ssid to scan for
+ * @bssid: bssid to scan for
+ * @channel_idx: idx of the channel in the channel array in the scan request
+ * which the above info relvant to
+ * @unsolicited_probe: the AP transmits unsolicited probe response every 20 TU
+ * @short_ssid_valid: short_ssid is valid and can be used
+ * @psc_no_listen: when set, and the channel is a PSC channel, no need to wait
+ * 20 TUs before starting to send probe requests.
+ */
+struct cfg80211_scan_6ghz_params {
+ u32 short_ssid;
+ u32 channel_idx;
+ u8 bssid[ETH_ALEN];
+ bool unsolicited_probe;
+ bool short_ssid_valid;
+ bool psc_no_listen;
+};
+
+/**
* struct cfg80211_scan_request - scan request description
*
* @ssids: SSIDs to scan for (active scan only)
@@ -1925,6 +2154,10 @@
* @mac_addr_mask: MAC address mask used with randomisation, bits that
* are 0 in the mask should be randomised, bits that are 1 should
* be taken from the @mac_addr
+ * @scan_6ghz: relevant for split scan request only,
+ * true if this is the second scan request
+ * @n_6ghz_params: number of 6 GHz params
+ * @scan_6ghz_params: 6 GHz params
* @bssid: BSSID to scan for (most commonly, the wildcard BSSID)
*/
struct cfg80211_scan_request {
@@ -1952,9 +2185,12 @@
struct cfg80211_scan_info info;
bool notified;
bool no_cck;
+ bool scan_6ghz;
+ u32 n_6ghz_params;
+ struct cfg80211_scan_6ghz_params *scan_6ghz_params;
/* keep last */
- struct ieee80211_channel *channels[0];
+ struct ieee80211_channel *channels[];
};
static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask)
@@ -2028,8 +2264,8 @@
* @ie_len: length of ie in octets
* @flags: bit field of flags controlling operation
* @match_sets: sets of parameters to be matched for a scan result
- * entry to be considered valid and to be passed to the host
- * (others are filtered out).
+ * entry to be considered valid and to be passed to the host
+ * (others are filtered out).
* If ommited, all results are passed.
* @n_match_sets: number of match sets
* @report_results: indicates that results were reported for this request
@@ -2100,7 +2336,7 @@
struct list_head list;
/* keep last */
- struct ieee80211_channel *channels[0];
+ struct ieee80211_channel *channels[];
};
/**
@@ -2222,7 +2458,7 @@
u8 bssid_index;
u8 max_bssid_indicator;
- u8 priv[0] __aligned(sizeof(void *));
+ u8 priv[] __aligned(sizeof(void *));
};
/**
@@ -2331,6 +2567,8 @@
* @fils_nonces: FILS nonces (part of AAD) for protecting (Re)Association
* Request/Response frame or %NULL if FILS is not used. This field starts
* with 16 octets of STA Nonce followed by 16 octets of AP Nonce.
+ * @s1g_capa: S1G capability override
+ * @s1g_capa_mask: S1G capability override mask
*/
struct cfg80211_assoc_request {
struct cfg80211_bss *bss;
@@ -2345,6 +2583,7 @@
const u8 *fils_kek;
size_t fils_kek_len;
const u8 *fils_nonces;
+ struct ieee80211_s1g_cap s1g_capa, s1g_capa_mask;
};
/**
@@ -2422,7 +2661,7 @@
* 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.
* @wep_keys: static WEP keys, if not NULL points to an array of
- * CFG80211_MAX_WEP_KEYS WEP keys
+ * CFG80211_MAX_WEP_KEYS WEP keys
* @wep_tx_key: key index (0..3) of the default TX static WEP key
*/
struct cfg80211_ibss_params {
@@ -2602,6 +2841,13 @@
#define IEEE80211_DEFAULT_AIRTIME_WEIGHT 256
+/* The per TXQ device queue limit in airtime */
+#define IEEE80211_DEFAULT_AQL_TXQ_LIMIT_L 5000
+#define IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H 12000
+
+/* The per interface airtime threshold to switch to lower queue limit */
+#define IEEE80211_AQL_THRESHOLD 24000
+
/**
* struct cfg80211_pmksa - PMK Security Association
*
@@ -2620,6 +2866,17 @@
* @cache_id: 2-octet cache identifier advertized by a FILS AP identifying the
* scope of PMKSA. This is valid only if @ssid_len is non-zero (may be
* %NULL).
+ * @pmk_lifetime: Maximum lifetime for PMKSA in seconds
+ * (dot11RSNAConfigPMKLifetime) or 0 if not specified.
+ * The configured PMKSA must not be used for PMKSA caching after
+ * expiration and any keys derived from this PMK become invalid on
+ * expiration, i.e., the current association must be dropped if the PMK
+ * used for it expires.
+ * @pmk_reauth_threshold: Threshold time for reauthentication (percentage of
+ * PMK lifetime, dot11RSNAConfigPMKReauthThreshold) or 0 if not specified.
+ * Drivers are expected to trigger a full authentication instead of using
+ * this PMKSA for caching when reassociating to a new BSS after this
+ * threshold to generate a new PMK before the current one expires.
*/
struct cfg80211_pmksa {
const u8 *bssid;
@@ -2629,6 +2886,8 @@
const u8 *ssid;
size_t ssid_len;
const u8 *cache_id;
+ u32 pmk_lifetime;
+ u8 pmk_reauth_threshold;
};
/**
@@ -2803,12 +3062,17 @@
/**
* struct cfg80211_gtk_rekey_data - rekey data
- * @kek: key encryption key (NL80211_KEK_LEN bytes)
- * @kck: key confirmation key (NL80211_KCK_LEN bytes)
+ * @kek: key encryption key (@kek_len bytes)
+ * @kck: key confirmation key (@kck_len bytes)
* @replay_ctr: replay counter (NL80211_REPLAY_CTR_LEN bytes)
+ * @kek_len: length of kek
+ * @kck_len length of kck
+ * @akm: akm (oui, id)
*/
struct cfg80211_gtk_rekey_data {
const u8 *kek, *kck, *replay_ctr;
+ u32 akm;
+ u8 kek_len, kck_len;
};
/**
@@ -3193,6 +3457,12 @@
* @ftmr_retries: number of retries for FTM request
* @request_lci: request LCI information
* @request_civicloc: request civic location information
+ * @trigger_based: use trigger based ranging for the measurement
+ * If neither @trigger_based nor @non_trigger_based is set,
+ * EDCA based ranging will be used.
+ * @non_trigger_based: use non trigger based ranging for the measurement
+ * If neither @trigger_based nor @non_trigger_based is set,
+ * EDCA based ranging will be used.
*
* See also nl80211 for the respective attribute documentation.
*/
@@ -3202,7 +3472,9 @@
u8 requested:1,
asap:1,
request_lci:1,
- request_civicloc:1;
+ request_civicloc:1,
+ trigger_based:1,
+ non_trigger_based:1;
u8 num_bursts_exp;
u8 burst_duration;
u8 ftms_per_burst;
@@ -3282,6 +3554,21 @@
};
/**
+ * struct mgmt_frame_regs - management frame registrations data
+ * @global_stypes: bitmap of management frame subtypes registered
+ * for the entire device
+ * @interface_stypes: bitmap of management frame subtypes registered
+ * for the given interface
+ * @global_mcast_rx: mcast RX is needed globally for these subtypes
+ * @interface_mcast_stypes: mcast RX is needed on this interface
+ * for these subtypes
+ */
+struct mgmt_frame_regs {
+ u32 global_stypes, interface_stypes;
+ u32 global_mcast_stypes, interface_mcast_stypes;
+};
+
+/**
* struct cfg80211_ops - backend description for wireless configuration
*
* This struct is registered by fullmac card drivers and/or wireless stacks
@@ -3329,6 +3616,8 @@
*
* @set_default_mgmt_key: set the default management frame key on an interface
*
+ * @set_default_beacon_key: set the default Beacon frame key on an interface
+ *
* @set_rekey_data: give the data necessary for GTK rekeying to the driver
*
* @start_ap: Start acting in AP mode defined by the parameters.
@@ -3503,8 +3792,8 @@
* The driver should not call cfg80211_sched_scan_stopped() for a requested
* stop (when this method returns 0).
*
- * @mgmt_frame_register: Notify driver that a management frame type was
- * registered. The callback is allowed to sleep.
+ * @update_mgmt_frame_registrations: Notify the driver that management frame
+ * registrations were updated. The callback is allowed to sleep.
*
* @set_antenna: Set antenna configuration (tx_ant, rx_ant) on the device.
* Parameters are bitmaps of allowed antennas to use for TX/RX. Drivers may
@@ -3628,6 +3917,10 @@
*
* @probe_mesh_link: Probe direct Mesh peer's link quality by sending data frame
* and overrule HWMP path selection algorithm.
+ * @set_tid_config: TID specific configuration, this can be peer or BSS specific
+ * This callback may sleep.
+ * @reset_tid_config: Reset TID specific configuration for the peer, for the
+ * given TIDs. This callback may sleep.
*/
struct cfg80211_ops {
int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -3661,6 +3954,9 @@
int (*set_default_mgmt_key)(struct wiphy *wiphy,
struct net_device *netdev,
u8 key_index);
+ int (*set_default_beacon_key)(struct wiphy *wiphy,
+ struct net_device *netdev,
+ u8 key_index);
int (*start_ap)(struct wiphy *wiphy, struct net_device *dev,
struct cfg80211_ap_settings *settings);
@@ -3820,9 +4116,9 @@
struct net_device *dev,
u32 rate, u32 pkts, u32 intvl);
- void (*mgmt_frame_register)(struct wiphy *wiphy,
- struct wireless_dev *wdev,
- u16 frame_type, bool reg);
+ void (*update_mgmt_frame_registrations)(struct wiphy *wiphy,
+ struct wireless_dev *wdev,
+ struct mgmt_frame_regs *upd);
int (*set_antenna)(struct wiphy *wiphy, u32 tx_ant, u32 rx_ant);
int (*get_antenna)(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant);
@@ -3934,7 +4230,8 @@
struct net_device *dev,
const u8 *buf, size_t len,
const u8 *dest, const __be16 proto,
- const bool noencrypt);
+ const bool noencrypt,
+ u64 *cookie);
int (*get_ftm_responder_stats)(struct wiphy *wiphy,
struct net_device *dev,
@@ -3948,6 +4245,10 @@
struct cfg80211_update_owe_info *owe_info);
int (*probe_mesh_link)(struct wiphy *wiphy, struct net_device *dev,
const u8 *buf, size_t len);
+ int (*set_tid_config)(struct wiphy *wiphy, struct net_device *dev,
+ struct cfg80211_tid_config *tid_conf);
+ int (*reset_tid_config)(struct wiphy *wiphy, struct net_device *dev,
+ const u8 *peer, u8 tids);
};
/*
@@ -3958,6 +4259,8 @@
/**
* enum wiphy_flags - wiphy capability flags
*
+ * @WIPHY_FLAG_SPLIT_SCAN_6GHZ: if set to true, the scan request will be split
+ * into two, first for legacy bands and second for UHB.
* @WIPHY_FLAG_NETNS_OK: if not set, do not allow changing the netns of this
* wiphy at all
* @WIPHY_FLAG_PS_ON_BY_DEFAULT: if set to true, powersave will be enabled
@@ -3996,11 +4299,12 @@
* beaconing mode (AP, IBSS, Mesh, ...).
* @WIPHY_FLAG_HAS_STATIC_WEP: The device supports static WEP key installation
* before connection.
+ * @WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK: The device supports bigger kek and kck keys
*/
enum wiphy_flags {
- /* use hole at 0 */
+ WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0),
/* use hole at 1 */
- /* use hole at 2 */
+ WIPHY_FLAG_SPLIT_SCAN_6GHZ = BIT(2),
WIPHY_FLAG_NETNS_OK = BIT(3),
WIPHY_FLAG_PS_ON_BY_DEFAULT = BIT(4),
WIPHY_FLAG_4ADDR_AP = BIT(5),
@@ -4345,6 +4649,8 @@
* forbid using the value 15 to let the responder pick)
* @ftm.max_ftms_per_burst: maximum FTMs per burst supported (set to 0 if
* not limited)
+ * @ftm.trigger_based: trigger based ranging measurement is supported
+ * @ftm.non_trigger_based: non trigger based ranging measurement is supported
*/
struct cfg80211_pmsr_capabilities {
unsigned int max_peers;
@@ -4360,24 +4666,49 @@
asap:1,
non_asap:1,
request_lci:1,
- request_civicloc:1;
+ request_civicloc:1,
+ trigger_based:1,
+ non_trigger_based:1;
} ftm;
};
/**
+ * struct wiphy_iftype_akm_suites - This structure encapsulates supported akm
+ * suites for interface types defined in @iftypes_mask. Each type in the
+ * @iftypes_mask must be unique across all instances of iftype_akm_suites.
+ *
+ * @iftypes_mask: bitmask of interfaces types
+ * @akm_suites: points to an array of supported akm suites
+ * @n_akm_suites: number of supported AKM suites
+ */
+struct wiphy_iftype_akm_suites {
+ u16 iftypes_mask;
+ const u32 *akm_suites;
+ int n_akm_suites;
+};
+
+/**
* struct wiphy - wireless hardware description
* @reg_notifier: the driver's regulatory notification callback,
* note that if your driver uses wiphy_apply_custom_regulatory()
* the reg_notifier's request can be passed as NULL
* @regd: the driver's regulatory domain, if one was requested via
- * the regulatory_hint() API. This can be used by the driver
+ * the regulatory_hint() API. This can be used by the driver
* on the reg_notifier() if it chooses to ignore future
* regulatory domain changes caused by other drivers.
* @signal_type: signal type reported in &struct cfg80211_bss.
* @cipher_suites: supported cipher suites
* @n_cipher_suites: number of supported cipher suites
- * @akm_suites: supported AKM suites
+ * @akm_suites: supported AKM suites. These are the default AKMs supported if
+ * the supported AKMs not advertized for a specific interface type in
+ * iftype_akm_suites.
* @n_akm_suites: number of supported AKM suites
+ * @iftype_akm_suites: array of supported akm suites info per interface type.
+ * Note that the bits in @iftypes_mask inside this structure cannot
+ * overlap (i.e. only one occurrence of each type is allowed across all
+ * instances of iftype_akm_suites).
+ * @num_iftype_akm_suites: number of interface types for which supported akm
+ * suites are specified separately.
* @retry_short: Retry limit for short frames (dot11ShortRetryLimit)
* @retry_long: Retry limit for long frames (dot11LongRetryLimit)
* @frag_threshold: Fragmentation threshold (dot11FragmentationThreshold);
@@ -4398,10 +4729,11 @@
* the same number of arbitrary MAC addresses.
* @registered: protects ->resume and ->suspend sysfs callbacks against
* unregister hardware
- * @debugfsdir: debugfs directory used for this wiphy, will be renamed
- * automatically on wiphy renames
- * @dev: (virtual) struct device for this wiphy
- * @registered: helps synchronize suspend/resume with wiphy unregister
+ * @debugfsdir: debugfs directory used for this wiphy (ieee80211/<wiphyname>).
+ * It will be renamed automatically on wiphy renames
+ * @dev: (virtual) struct device for this wiphy. The item in
+ * /sys/class/ieee80211/ points to this. You need use set_wiphy_dev()
+ * (see below).
* @wext: wireless extension handlers
* @priv: driver private data (sized according to wiphy_new() parameter)
* @interface_modes: bitmask of interfaces types valid for this wiphy,
@@ -4512,12 +4844,6 @@
* and probe responses. This value should be set if the driver
* wishes to limit the number of csa counters. Default (0) means
* infinite.
- * @max_adj_channel_rssi_comp: max offset of between the channel on which the
- * frame was sent and the channel on which the frame was heard for which
- * the reported rssi is still valid. If a driver is able to compensate the
- * low rssi when a frame is heard on different channel, then it should set
- * this variable to the maximal offset for which it can compensate.
- * This value should be set in MHz.
* @bss_select_support: bitmask indicating the BSS selection criteria supported
* by the driver in the .connect() callback. The bit position maps to the
* attribute indices defined in &enum nl80211_bss_select_attr.
@@ -4531,17 +4857,32 @@
* @txq_memory_limit: configuration internal TX queue memory limit
* @txq_quantum: configuration of internal TX queue scheduler quantum
*
+ * @tx_queue_len: allow setting transmit queue len for drivers not using
+ * wake_tx_queue
+ *
* @support_mbssid: can HW support association with nontransmitted AP
* @support_only_he_mbssid: don't parse MBSSID elements if it is not
* HE AP, in order to avoid compatibility issues.
* @support_mbssid must be set for this to have any effect.
*
* @pmsr_capa: peer measurement capabilities
+ *
+ * @tid_config_support: describes the per-TID config support that the
+ * device has
+ * @tid_config_support.vif: bitmap of attributes (configurations)
+ * supported by the driver for each vif
+ * @tid_config_support.peer: bitmap of attributes (configurations)
+ * supported by the driver for each peer
+ * @tid_config_support.max_retry: maximum supported retry count for
+ * long/short retry configuration
+ *
+ * @max_data_retry_count: maximum supported per TID retry count for
+ * configuration through the %NL80211_TID_CONFIG_ATTR_RETRY_SHORT and
+ * %NL80211_TID_CONFIG_ATTR_RETRY_LONG attributes
*/
struct wiphy {
/* assign these fields before you register the wiphy */
- /* permanent MAC address(es) */
u8 perm_addr[ETH_ALEN];
u8 addr_mask[ETH_ALEN];
@@ -4584,6 +4925,9 @@
int n_akm_suites;
const u32 *akm_suites;
+ const struct wiphy_iftype_akm_suites *iftype_akm_suites;
+ unsigned int num_iftype_akm_suites;
+
u8 retry_short;
u8 retry_long;
u32 frag_threshold;
@@ -4605,11 +4949,6 @@
u32 available_antennas_tx;
u32 available_antennas_rx;
- /*
- * Bitmap of supported protocols for probe response offloading
- * see &enum nl80211_probe_resp_offload_support_attr. Only valid
- * when the wiphy flag @WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD is set.
- */
u32 probe_resp_offload;
const u8 *extended_capabilities, *extended_capabilities_mask;
@@ -4618,16 +4957,10 @@
const struct wiphy_iftype_ext_capab *iftype_ext_capab;
unsigned int num_iftype_ext_capab;
- /* If multiple wiphys are registered and you're handed e.g.
- * a regular netdev with assigned ieee80211_ptr, you won't
- * know whether it points to a wiphy your driver has registered
- * or not. Assign this to something global to your driver to
- * help determine whether you own this wiphy or not. */
const void *privid;
struct ieee80211_supported_band *bands[NUM_NL80211_BANDS];
- /* Lets us get back the wiphy on the callback */
void (*reg_notifier)(struct wiphy *wiphy,
struct regulatory_request *request);
@@ -4635,14 +4968,10 @@
const struct ieee80211_regdomain __rcu *regd;
- /* the item in /sys/class/ieee80211/ points to this,
- * you need use set_wiphy_dev() (see below) */
struct device dev;
- /* protects ->resume, ->suspend sysfs callbacks against unregister hw */
bool registered;
- /* dir in debugfs: ieee80211/<wiphyname> */
struct dentry *debugfsdir;
const struct ieee80211_ht_cap *ht_capa_mod_mask;
@@ -4650,7 +4979,6 @@
struct list_head wdev_list;
- /* the network namespace this phy lives in currently */
possible_net_t _net;
#ifdef CONFIG_CFG80211_WEXT
@@ -4666,7 +4994,6 @@
u16 max_ap_assoc_sta;
u8 max_num_csa_counters;
- u8 max_adj_channel_rssi_comp;
u32 bss_select_support;
@@ -4676,12 +5003,21 @@
u32 txq_memory_limit;
u32 txq_quantum;
+ unsigned long tx_queue_len;
+
u8 support_mbssid:1,
support_only_he_mbssid:1;
const struct cfg80211_pmsr_capabilities *pmsr_capa;
- char priv[0] __aligned(NETDEV_ALIGN);
+ struct {
+ u64 peer, vif;
+ u8 max_retry;
+ } tid_config_support;
+
+ u8 max_data_retry_count;
+
+ char priv[] __aligned(NETDEV_ALIGN);
};
static inline struct net *wiphy_net(struct wiphy *wiphy)
@@ -4866,7 +5202,8 @@
* netdev and may otherwise be used by driver read-only, will be update
* by cfg80211 on change_interface
* @mgmt_registrations: list of registrations for management frames
- * @mgmt_registrations_lock: lock for the list
+ * @mgmt_registrations_need_update: mgmt registrations were updated,
+ * need to propagate the update to the driver
* @mtx: mutex used to lock data in this struct, may be used by drivers
* and some API functions require it held
* @beacon_interval: beacon interval used on this device for transmitting
@@ -4897,6 +5234,8 @@
* @pmsr_list: (private) peer measurement requests
* @pmsr_lock: (private) peer measurements requests/results lock
* @pmsr_free_wk: (private) peer measurements cleanup work
+ * @unprot_beacon_reported: (private) timestamp of last
+ * unprotected beacon report
*/
struct wireless_dev {
struct wiphy *wiphy;
@@ -4909,7 +5248,7 @@
u32 identifier;
struct list_head mgmt_registrations;
- spinlock_t mgmt_registrations_lock;
+ u8 mgmt_registrations_need_update:1;
struct mutex mtx;
@@ -4973,6 +5312,8 @@
struct list_head pmsr_list;
spinlock_t pmsr_lock;
struct work_struct pmsr_free_wk;
+
+ unsigned long unprot_beacon_reported;
};
static inline u8 *wdev_address(struct wireless_dev *wdev)
@@ -5008,29 +5349,116 @@
*/
/**
+ * ieee80211_channel_equal - compare two struct ieee80211_channel
+ *
+ * @a: 1st struct ieee80211_channel
+ * @b: 2nd struct ieee80211_channel
+ * Return: true if center frequency of @a == @b
+ */
+static inline bool
+ieee80211_channel_equal(struct ieee80211_channel *a,
+ struct ieee80211_channel *b)
+{
+ return (a->center_freq == b->center_freq &&
+ a->freq_offset == b->freq_offset);
+}
+
+/**
+ * ieee80211_channel_to_khz - convert ieee80211_channel to frequency in KHz
+ * @chan: struct ieee80211_channel to convert
+ * Return: The corresponding frequency (in KHz)
+ */
+static inline u32
+ieee80211_channel_to_khz(const struct ieee80211_channel *chan)
+{
+ return MHZ_TO_KHZ(chan->center_freq) + chan->freq_offset;
+}
+
+/**
+ * ieee80211_s1g_channel_width - get allowed channel width from @chan
+ *
+ * Only allowed for band NL80211_BAND_S1GHZ
+ * @chan: channel
+ * Return: The allowed channel width for this center_freq
+ */
+enum nl80211_chan_width
+ieee80211_s1g_channel_width(const struct ieee80211_channel *chan);
+
+/**
+ * ieee80211_channel_to_freq_khz - convert channel number to frequency
+ * @chan: channel number
+ * @band: band, necessary due to channel number overlap
+ * Return: The corresponding frequency (in KHz), or 0 if the conversion failed.
+ */
+u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band);
+
+/**
* ieee80211_channel_to_frequency - convert channel number to frequency
* @chan: channel number
* @band: band, necessary due to channel number overlap
* Return: The corresponding frequency (in MHz), or 0 if the conversion failed.
*/
-int ieee80211_channel_to_frequency(int chan, enum nl80211_band band);
+static inline int
+ieee80211_channel_to_frequency(int chan, enum nl80211_band band)
+{
+ return KHZ_TO_MHZ(ieee80211_channel_to_freq_khz(chan, band));
+}
+
+/**
+ * ieee80211_freq_khz_to_channel - convert frequency to channel number
+ * @freq: center frequency in KHz
+ * Return: The corresponding channel, or 0 if the conversion failed.
+ */
+int ieee80211_freq_khz_to_channel(u32 freq);
/**
* ieee80211_frequency_to_channel - convert frequency to channel number
- * @freq: center frequency
+ * @freq: center frequency in MHz
* Return: The corresponding channel, or 0 if the conversion failed.
*/
-int ieee80211_frequency_to_channel(int freq);
+static inline int
+ieee80211_frequency_to_channel(int freq)
+{
+ return ieee80211_freq_khz_to_channel(MHZ_TO_KHZ(freq));
+}
+
+/**
+ * ieee80211_get_channel_khz - get channel struct from wiphy for specified
+ * frequency
+ * @wiphy: the struct wiphy to get the channel for
+ * @freq: the center frequency (in KHz) of the channel
+ * Return: The channel struct from @wiphy at @freq.
+ */
+struct ieee80211_channel *
+ieee80211_get_channel_khz(struct wiphy *wiphy, u32 freq);
/**
* ieee80211_get_channel - get channel struct from wiphy for specified frequency
*
* @wiphy: the struct wiphy to get the channel for
- * @freq: the center frequency of the channel
- *
+ * @freq: the center frequency (in MHz) of the channel
* Return: The channel struct from @wiphy at @freq.
*/
-struct ieee80211_channel *ieee80211_get_channel(struct wiphy *wiphy, int freq);
+static inline struct ieee80211_channel *
+ieee80211_get_channel(struct wiphy *wiphy, int freq)
+{
+ return ieee80211_get_channel_khz(wiphy, MHZ_TO_KHZ(freq));
+}
+
+/**
+ * cfg80211_channel_is_psc - Check if the channel is a 6 GHz PSC
+ * @chan: control channel to check
+ *
+ * The Preferred Scanning Channels (PSC) are defined in
+ * Draft IEEE P802.11ax/D5.0, 26.17.2.3.3
+ */
+static inline bool cfg80211_channel_is_psc(struct ieee80211_channel *chan)
+{
+ if (chan->band != NL80211_BAND_6GHZ)
+ return false;
+
+ return ieee80211_frequency_to_channel(chan->center_freq) % 16 == 5;
+}
/**
* ieee80211_get_response_rate - get basic rate for a given rate
@@ -5063,7 +5491,7 @@
* Radiotap parsing functions -- for controlled injection support
*
* Implemented in net/wireless/radiotap.c
- * Documentation in Documentation/networking/radiotap-headers.txt
+ * Documentation in Documentation/networking/radiotap-headers.rst
*/
struct radiotap_align_size {
@@ -5218,7 +5646,7 @@
*
* @skb: The input A-MSDU frame without any headers.
* @list: The output list of 802.3 frames. It must be allocated and
- * initialized by by the caller.
+ * initialized by the caller.
* @addr: The device MAC address.
* @iftype: The device interface type.
* @extra_headroom: The hardware extra headroom for SKBs in the @list.
@@ -5456,9 +5884,9 @@
* @wiphy: the wireless device giving the hint (used only for reporting
* conflicts)
* @alpha2: the ISO/IEC 3166 alpha2 the driver claims its regulatory domain
- * should be in. If @rd is set this should be NULL. Note that if you
- * set this to NULL you should still set rd->alpha2 to some accepted
- * alpha2.
+ * should be in. If @rd is set this should be NULL. Note that if you
+ * set this to NULL you should still set rd->alpha2 to some accepted
+ * alpha2.
*
* Wireless drivers can use this function to hint to the wireless core
* what it believes should be the current regulatory domain by
@@ -5987,12 +6415,16 @@
/**
* cfg80211_rx_unprot_mlme_mgmt - notification of unprotected mlme mgmt frame
* @dev: network device
- * @buf: deauthentication frame (header + body)
+ * @buf: received management frame (header + body)
* @len: length of the frame data
*
* This function is called whenever a received deauthentication or dissassoc
* frame has been dropped in station mode because of MFP being used but the
- * frame was not protected. This function may sleep.
+ * frame was not protected. This is also used to notify reception of a Beacon
+ * frame that was dropped because it did not include a valid MME MIC while
+ * beacon protection was enabled (BIGTK configured in station mode).
+ *
+ * This function may sleep.
*/
void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev,
const u8 *buf, size_t len);
@@ -6033,7 +6465,8 @@
struct ieee80211_channel *channel, gfp_t gfp);
/**
- * cfg80211_notify_new_candidate - notify cfg80211 of a new mesh peer candidate
+ * cfg80211_notify_new_peer_candidate - notify cfg80211 of a new mesh peer
+ * candidate
*
* @dev: network device
* @macaddr: the MAC address of the new candidate
@@ -6598,7 +7031,7 @@
* time it is accessed in __cfg80211_roamed() due to delay in scheduling
* rdev->event_work. In case of any failures, the reference is released
* either in cfg80211_roamed() or in __cfg80211_romed(), Otherwise, it will be
- * released while diconneting from the current bss.
+ * released while disconnecting from the current bss.
*/
void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info,
gfp_t gfp);
@@ -6746,6 +7179,26 @@
gfp_t gfp);
/**
+ * cfg80211_rx_mgmt_khz - notification of received, unprocessed management frame
+ * @wdev: wireless device receiving the frame
+ * @freq: Frequency on which the frame was received in KHz
+ * @sig_dbm: signal strength in dBm, or 0 if unknown
+ * @buf: Management frame (header + body)
+ * @len: length of the frame data
+ * @flags: flags, as defined in enum nl80211_rxmgmt_flags
+ *
+ * This function is called whenever an Action frame is received for a station
+ * mode interface, but is not processed in kernel.
+ *
+ * Return: %true if a user space application has registered for this frame.
+ * For action frames, that makes it responsible for rejecting unrecognized
+ * action frames; %false otherwise, in which case for action frames the
+ * driver is responsible for rejecting the frame.
+ */
+bool cfg80211_rx_mgmt_khz(struct wireless_dev *wdev, int freq, int sig_dbm,
+ const u8 *buf, size_t len, u32 flags);
+
+/**
* cfg80211_rx_mgmt - notification of received, unprocessed management frame
* @wdev: wireless device receiving the frame
* @freq: Frequency on which the frame was received in MHz
@@ -6762,8 +7215,13 @@
* action frames; %false otherwise, in which case for action frames the
* driver is responsible for rejecting the frame.
*/
-bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_dbm,
- const u8 *buf, size_t len, u32 flags);
+static inline bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq,
+ int sig_dbm, const u8 *buf, size_t len,
+ u32 flags)
+{
+ return cfg80211_rx_mgmt_khz(wdev, MHZ_TO_KHZ(freq), sig_dbm, buf, len,
+ flags);
+}
/**
* cfg80211_mgmt_tx_status - notification of TX status for management frame
@@ -6781,6 +7239,23 @@
void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
const u8 *buf, size_t len, bool ack, gfp_t gfp);
+/**
+ * cfg80211_control_port_tx_status - notification of TX status for control
+ * port frames
+ * @wdev: wireless device receiving the frame
+ * @cookie: Cookie returned by cfg80211_ops::tx_control_port()
+ * @buf: Data frame (header + body)
+ * @len: length of the frame data
+ * @ack: Whether frame was acknowledged
+ * @gfp: context flags
+ *
+ * This function is called whenever a control port frame was requested to be
+ * transmitted with cfg80211_ops::tx_control_port() to report the TX status of
+ * the transmission attempt.
+ */
+void cfg80211_control_port_tx_status(struct wireless_dev *wdev, u64 cookie,
+ const u8 *buf, size_t len, bool ack,
+ gfp_t gfp);
/**
* cfg80211_rx_control_port - notification about a received control port frame
@@ -6962,6 +7437,21 @@
bool is_valid_ack_signal, gfp_t gfp);
/**
+ * cfg80211_report_obss_beacon_khz - report beacon from other APs
+ * @wiphy: The wiphy that received the beacon
+ * @frame: the frame
+ * @len: length of the frame
+ * @freq: frequency the frame was received on in KHz
+ * @sig_dbm: signal strength in dBm, or 0 if unknown
+ *
+ * Use this function to report to userspace when a beacon was
+ * received. It is not useful to call this when there is no
+ * netdev that is in AP/GO mode.
+ */
+void cfg80211_report_obss_beacon_khz(struct wiphy *wiphy, const u8 *frame,
+ size_t len, int freq, int sig_dbm);
+
+/**
* cfg80211_report_obss_beacon - report beacon from other APs
* @wiphy: The wiphy that received the beacon
* @frame: the frame
@@ -6973,9 +7463,13 @@
* received. It is not useful to call this when there is no
* netdev that is in AP/GO mode.
*/
-void cfg80211_report_obss_beacon(struct wiphy *wiphy,
- const u8 *frame, size_t len,
- int freq, int sig_dbm);
+static inline void cfg80211_report_obss_beacon(struct wiphy *wiphy,
+ const u8 *frame, size_t len,
+ int freq, int sig_dbm)
+{
+ cfg80211_report_obss_beacon_khz(wiphy, frame, len, MHZ_TO_KHZ(freq),
+ sig_dbm);
+}
/**
* cfg80211_reg_can_beacon - check if beaconing is allowed
@@ -7054,6 +7548,19 @@
bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef,
u8 *op_class);
+/**
+ * ieee80211_chandef_to_khz - convert chandef to frequency in KHz
+ *
+ * @chandef: the chandef to convert
+ *
+ * Returns the center frequency of chandef (1st segment) in KHz.
+ */
+static inline u32
+ieee80211_chandef_to_khz(const struct cfg80211_chan_def *chandef)
+{
+ return MHZ_TO_KHZ(chandef->center_freq1) + chandef->freq1_offset;
+}
+
/*
* cfg80211_tdls_oper_request - request userspace to perform TDLS operation
* @dev: the device on which the operation is requested
@@ -7098,7 +7605,7 @@
void cfg80211_unregister_wdev(struct wireless_dev *wdev);
/**
- * struct cfg80211_ft_event - FT Information Elements
+ * struct cfg80211_ft_event_params - FT Information Elements
* @ies: FT IEs
* @ies_len: length of the FT IE in bytes
* @target_ap: target AP's MAC address
@@ -7512,4 +8019,10 @@
struct cfg80211_update_owe_info *owe_info,
gfp_t gfp);
+/**
+ * cfg80211_bss_flush - resets all the scan entries
+ * @wiphy: the wiphy
+ */
+void cfg80211_bss_flush(struct wiphy *wiphy);
+
#endif /* __NET_CFG80211_H */
diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 6f86073..6ed0784 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -214,7 +214,7 @@
/* the network namespace this phy lives in currently */
possible_net_t _net;
- char priv[0] __aligned(NETDEV_ALIGN);
+ char priv[] __aligned(NETDEV_ALIGN);
};
static inline struct net *wpan_phy_net(struct wpan_phy *wpan_phy)
diff --git a/include/net/checksum.h b/include/net/checksum.h
index 97bf488..8b7d0c3 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -22,39 +22,39 @@
#include <asm/checksum.h>
#ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
-static inline
+static __always_inline
__wsum csum_and_copy_from_user (const void __user *src, void *dst,
- int len, __wsum sum, int *err_ptr)
+ int len)
{
- if (access_ok(src, len))
- return csum_partial_copy_from_user(src, dst, len, sum, err_ptr);
-
- if (len)
- *err_ptr = -EFAULT;
-
- return sum;
+ if (copy_from_user(dst, src, len))
+ return 0;
+ return csum_partial(dst, len, ~0U);
}
#endif
#ifndef HAVE_CSUM_COPY_USER
-static __inline__ __wsum csum_and_copy_to_user
-(const void *src, void __user *dst, int len, __wsum sum, int *err_ptr)
+static __always_inline __wsum csum_and_copy_to_user
+(const void *src, void __user *dst, int len)
{
- sum = csum_partial(src, len, sum);
+ __wsum sum = csum_partial(src, len, ~0U);
- if (access_ok(dst, len)) {
- if (copy_to_user(dst, src, len) == 0)
- return sum;
- }
- if (len)
- *err_ptr = -EFAULT;
+ if (copy_to_user(dst, src, len) == 0)
+ return sum;
+ return 0;
+}
+#endif
- return (__force __wsum)-1; /* invalid checksum */
+#ifndef _HAVE_ARCH_CSUM_AND_COPY
+static __always_inline __wsum
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
+{
+ memcpy(dst, src, len);
+ return csum_partial(dst, len, 0);
}
#endif
#ifndef HAVE_ARCH_CSUM_ADD
-static inline __wsum csum_add(__wsum csum, __wsum addend)
+static __always_inline __wsum csum_add(__wsum csum, __wsum addend)
{
u32 res = (__force u32)csum;
res += (__force u32)addend;
@@ -62,12 +62,12 @@
}
#endif
-static inline __wsum csum_sub(__wsum csum, __wsum addend)
+static __always_inline __wsum csum_sub(__wsum csum, __wsum addend)
{
return csum_add(csum, ~addend);
}
-static inline __sum16 csum16_add(__sum16 csum, __be16 addend)
+static __always_inline __sum16 csum16_add(__sum16 csum, __be16 addend)
{
u16 res = (__force u16)csum;
@@ -75,12 +75,12 @@
return (__force __sum16)(res + (res < (__force u16)addend));
}
-static inline __sum16 csum16_sub(__sum16 csum, __be16 addend)
+static __always_inline __sum16 csum16_sub(__sum16 csum, __be16 addend)
{
return csum16_add(csum, ~addend);
}
-static inline __wsum
+static __always_inline __wsum
csum_block_add(__wsum csum, __wsum csum2, int offset)
{
u32 sum = (__force u32)csum2;
@@ -92,36 +92,37 @@
return csum_add(csum, (__force __wsum)sum);
}
-static inline __wsum
+static __always_inline __wsum
csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len)
{
return csum_block_add(csum, csum2, offset);
}
-static inline __wsum
+static __always_inline __wsum
csum_block_sub(__wsum csum, __wsum csum2, int offset)
{
return csum_block_add(csum, ~csum2, offset);
}
-static inline __wsum csum_unfold(__sum16 n)
+static __always_inline __wsum csum_unfold(__sum16 n)
{
return (__force __wsum)n;
}
-static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum)
+static __always_inline
+__wsum csum_partial_ext(const void *buff, int len, __wsum sum)
{
return csum_partial(buff, len, sum);
}
#define CSUM_MANGLED_0 ((__force __sum16)0xffff)
-static inline void csum_replace_by_diff(__sum16 *sum, __wsum diff)
+static __always_inline void csum_replace_by_diff(__sum16 *sum, __wsum diff)
{
*sum = csum_fold(csum_add(diff, ~csum_unfold(*sum)));
}
-static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to)
+static __always_inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to)
{
__wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from);
@@ -134,11 +135,16 @@
* m : old value of a 16bit field
* m' : new value of a 16bit field
*/
-static inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new)
+static __always_inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new)
{
*sum = ~csum16_add(csum16_sub(~(*sum), old), new);
}
+static inline void csum_replace(__wsum *csum, __wsum old, __wsum new)
+{
+ *csum = csum_add(csum_sub(*csum, old), new);
+}
+
struct sk_buff;
void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
__be32 from, __be32 to, bool pseudohdr);
@@ -148,16 +154,16 @@
void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb,
__wsum diff, bool pseudohdr);
-static inline void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb,
- __be16 from, __be16 to,
- bool pseudohdr)
+static __always_inline
+void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb,
+ __be16 from, __be16 to, bool pseudohdr)
{
inet_proto_csum_replace4(sum, skb, (__force __be32)from,
(__force __be32)to, pseudohdr);
}
-static inline __wsum remcsum_adjust(void *ptr, __wsum csum,
- int start, int offset)
+static __always_inline __wsum remcsum_adjust(void *ptr, __wsum csum,
+ int start, int offset)
{
__sum16 *psum = (__sum16 *)(ptr + offset);
__wsum delta;
@@ -173,7 +179,7 @@
return delta;
}
-static inline void remcsum_unadjust(__sum16 *psum, __wsum delta)
+static __always_inline void remcsum_unadjust(__sum16 *psum, __wsum delta)
{
*psum = csum_fold(csum_sub(delta, (__force __wsum)*psum));
}
diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
index 428b672..53dd7d9 100644
--- a/include/net/cipso_ipv4.h
+++ b/include/net/cipso_ipv4.h
@@ -150,18 +150,6 @@
{
return 0;
}
-
-static inline int cipso_v4_doi_domhsh_add(struct cipso_v4_doi *doi_def,
- const char *domain)
-{
- return -ENOSYS;
-}
-
-static inline int cipso_v4_doi_domhsh_remove(struct cipso_v4_doi *doi_def,
- const char *domain)
-{
- return 0;
-}
#endif /* CONFIG_NETLABEL */
/*
diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index 4295de3..7e78e7d 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -45,9 +45,14 @@
sock_cgroup_set_classid(skcd, classid);
}
+static inline u32 __task_get_classid(struct task_struct *task)
+{
+ return task_cls_state(task)->classid;
+}
+
static inline u32 task_get_classid(const struct sk_buff *skb)
{
- u32 classid = task_cls_state(current)->classid;
+ u32 classid = __task_get_classid(current);
/* Due to the nature of the classifier it is required to ignore all
* packets originating from softirq context as accessing `current'
diff --git a/include/net/compat.h b/include/net/compat.h
index f277653..745db0d 100644
--- a/include/net/compat.h
+++ b/include/net/compat.h
@@ -30,6 +30,24 @@
compat_int_t cmsg_type;
};
+struct compat_rtentry {
+ u32 rt_pad1;
+ struct sockaddr rt_dst; /* target address */
+ struct sockaddr rt_gateway; /* gateway addr (RTF_GATEWAY) */
+ struct sockaddr rt_genmask; /* target network mask (IP) */
+ unsigned short rt_flags;
+ short rt_pad2;
+ u32 rt_pad3;
+ unsigned char rt_tos;
+ unsigned char rt_class;
+ short rt_pad4;
+ short rt_metric; /* +1 for binary compatibility! */
+ compat_uptr_t rt_dev; /* forcing the device at add */
+ u32 rt_mtu; /* per route MTU/Window */
+ u32 rt_window; /* Window clamping */
+ unsigned short rt_irtt; /* Initial RTT */
+};
+
#else /* defined(CONFIG_COMPAT) */
/*
* To avoid compiler warnings:
@@ -38,19 +56,38 @@
#define compat_mmsghdr mmsghdr
#endif /* defined(CONFIG_COMPAT) */
+int __get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg,
+ struct sockaddr __user **save_addr, compat_uptr_t *ptr,
+ compat_size_t *len);
int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *,
struct sockaddr __user **, struct iovec **);
-struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval);
int put_cmsg_compat(struct msghdr*, int, int, int, void *);
int cmsghdr_from_user_compat_to_kern(struct msghdr *, struct sock *,
unsigned char *, int);
-int compat_mc_setsockopt(struct sock *, int, int, char __user *, unsigned int,
- int (*)(struct sock *, int, int, char __user *,
- unsigned int));
-int compat_mc_getsockopt(struct sock *, int, int, char __user *, int __user *,
- int (*)(struct sock *, int, int, char __user *,
- int __user *));
+struct compat_group_req {
+ __u32 gr_interface;
+ struct __kernel_sockaddr_storage gr_group
+ __aligned(4);
+} __packed;
+
+struct compat_group_source_req {
+ __u32 gsr_interface;
+ struct __kernel_sockaddr_storage gsr_group
+ __aligned(4);
+ struct __kernel_sockaddr_storage gsr_source
+ __aligned(4);
+} __packed;
+
+struct compat_group_filter {
+ __u32 gf_interface;
+ struct __kernel_sockaddr_storage gf_group
+ __aligned(4);
+ __u32 gf_fmode;
+ __u32 gf_numsrc;
+ struct __kernel_sockaddr_storage gf_slist[1]
+ __aligned(4);
+} __packed;
#endif /* NET_COMPAT_H */
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 2116c88..b01bb9b 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -16,7 +16,17 @@
#include <linux/workqueue.h>
#include <linux/refcount.h>
#include <net/net_namespace.h>
+#include <net/flow_offload.h>
#include <uapi/linux/devlink.h>
+#include <linux/xarray.h>
+
+#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \
+ (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX)
+
+struct devlink_dev_stats {
+ u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE];
+ u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE];
+};
struct devlink_ops;
@@ -28,18 +38,23 @@
struct list_head resource_list;
struct list_head param_list;
struct list_head region_list;
- u32 snapshot_id;
struct list_head reporter_list;
struct mutex reporters_lock; /* protects reporter_list */
struct devlink_dpipe_headers *dpipe_headers;
struct list_head trap_list;
struct list_head trap_group_list;
+ struct list_head trap_policer_list;
const struct devlink_ops *ops;
+ struct xarray snapshot_ids;
+ struct devlink_dev_stats stats;
struct device *dev;
possible_net_t _net;
- struct mutex lock;
+ struct mutex lock; /* Serializes access to devlink instance specific objects such as
+ * port, sb, dpipe, resource, params, region, traps and more.
+ */
u8 reload_failed:1,
- reload_enabled:1;
+ reload_enabled:1,
+ registered:1;
char priv[0] __aligned(NETDEV_ALIGN);
};
@@ -48,22 +63,50 @@
* A physical port which is visible to the user
* for a given port flavour.
*/
- u32 split_subport_number;
+ u32 split_subport_number; /* If the port is split, this is the number of subport. */
};
+/**
+ * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes
+ * @controller: Associated controller number
+ * @pf: Associated PCI PF number for this port.
+ * @external: when set, indicates if a port is for an external controller
+ */
struct devlink_port_pci_pf_attrs {
- u16 pf; /* Associated PCI PF for this port. */
+ u32 controller;
+ u16 pf;
+ u8 external:1;
};
+/**
+ * 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.
+ * @external: when set, indicates if a port is for an external controller
+ */
struct devlink_port_pci_vf_attrs {
- u16 pf; /* Associated PCI PF for this port. */
- u16 vf; /* Associated PCI VF for of the PCI PF for this port. */
+ u32 controller;
+ u16 pf;
+ u16 vf;
+ u8 external:1;
};
+/**
+ * struct devlink_port_attrs - devlink port object
+ * @flavour: flavour of the port
+ * @split: indicates if this is split port
+ * @splittable: indicates if the port can be split.
+ * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink.
+ * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL
+ * @phys: physical port attributes
+ * @pci_pf: PCI PF port attributes
+ * @pci_vf: PCI VF port attributes
+ */
struct devlink_port_attrs {
- u8 set:1,
- split:1,
- switch_port:1;
+ u8 split:1,
+ splittable:1;
+ u32 lanes;
enum devlink_port_flavour flavour;
struct netdev_phys_item_id switch_id;
union {
@@ -76,6 +119,7 @@
struct devlink_port {
struct list_head list;
struct list_head param_list;
+ struct list_head region_list;
struct devlink *devlink;
unsigned int index;
bool registered;
@@ -86,7 +130,11 @@
enum devlink_port_type desired_type;
void *type_dev;
struct devlink_port_attrs attrs;
+ u8 attrs_set:1,
+ switch_port:1;
struct delayed_work type_warn_dw;
+ struct list_head reporter_list;
+ struct mutex reporters_lock; /* Protects reporter_list */
};
struct devlink_sb_pool_info {
@@ -354,6 +402,25 @@
};
/**
+ * struct devlink_flash_notify - devlink dev flash notify data
+ * @status_msg: current status string
+ * @component: firmware component being updated
+ * @done: amount of work completed of total amount
+ * @total: amount of work expected to be done
+ * @timeout: expected max timeout in seconds
+ *
+ * These are values to be given to userland to be displayed in order
+ * to show current activity in a firmware update process.
+ */
+struct devlink_flash_notify {
+ const char *status_msg;
+ const char *component;
+ unsigned long done;
+ unsigned long total;
+ unsigned long timeout;
+};
+
+/**
* struct devlink_param - devlink configuration parameter data
* @name: name of the parameter
* @generic: indicates if the parameter is generic or driver specific
@@ -401,6 +468,8 @@
DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE,
+ DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
+ DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET,
/* add new param generic ids above here*/
__DEVLINK_PARAM_GENERIC_ID_MAX,
@@ -435,6 +504,12 @@
"reset_dev_on_drv_probe"
#define DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE DEVLINK_PARAM_TYPE_U8
+#define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME "enable_roce"
+#define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE DEVLINK_PARAM_TYPE_BOOL
+
+#define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME "enable_remote_dev_reset"
+#define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL
+
#define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \
{ \
.id = DEVLINK_PARAM_GENERIC_ID_##_id, \
@@ -474,17 +549,81 @@
#define DEVLINK_INFO_VERSION_GENERIC_FW "fw"
/* Control processor FW version */
#define DEVLINK_INFO_VERSION_GENERIC_FW_MGMT "fw.mgmt"
+/* FW interface specification version */
+#define DEVLINK_INFO_VERSION_GENERIC_FW_MGMT_API "fw.mgmt.api"
/* Data path microcode controlling high-speed packet processing */
#define DEVLINK_INFO_VERSION_GENERIC_FW_APP "fw.app"
/* UNDI software version */
#define DEVLINK_INFO_VERSION_GENERIC_FW_UNDI "fw.undi"
/* NCSI support/handler version */
#define DEVLINK_INFO_VERSION_GENERIC_FW_NCSI "fw.ncsi"
+/* FW parameter set id */
+#define DEVLINK_INFO_VERSION_GENERIC_FW_PSID "fw.psid"
+/* RoCE FW version */
+#define DEVLINK_INFO_VERSION_GENERIC_FW_ROCE "fw.roce"
+/* Firmware bundle identifier */
+#define DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID "fw.bundle_id"
+
+/**
+ * struct devlink_flash_update_params - Flash Update parameters
+ * @file_name: the name of the flash firmware file to update from
+ * @component: the flash component to update
+ *
+ * With the exception of file_name, drivers must opt-in to parameters by
+ * setting the appropriate bit in the supported_flash_update_params field in
+ * their devlink_ops structure.
+ */
+struct devlink_flash_update_params {
+ const char *file_name;
+ const char *component;
+ u32 overwrite_mask;
+};
+
+#define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT BIT(0)
+#define DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK BIT(1)
struct devlink_region;
struct devlink_info_req;
-typedef void devlink_snapshot_data_dest_t(const void *data);
+/**
+ * struct devlink_region_ops - Region operations
+ * @name: region name
+ * @destructor: callback used to free snapshot memory when deleting
+ * @snapshot: callback to request an immediate snapshot. On success,
+ * the data variable must be updated to point to the snapshot data.
+ * The function will be called while the devlink instance lock is
+ * held.
+ * @priv: Pointer to driver private data for the region operation
+ */
+struct devlink_region_ops {
+ const char *name;
+ void (*destructor)(const void *data);
+ int (*snapshot)(struct devlink *devlink,
+ const struct devlink_region_ops *ops,
+ struct netlink_ext_ack *extack,
+ u8 **data);
+ void *priv;
+};
+
+/**
+ * struct devlink_port_region_ops - Region operations for a port
+ * @name: region name
+ * @destructor: callback used to free snapshot memory when deleting
+ * @snapshot: callback to request an immediate snapshot. On success,
+ * the data variable must be updated to point to the snapshot data.
+ * The function will be called while the devlink instance lock is
+ * held.
+ * @priv: Pointer to driver private data for the region operation
+ */
+struct devlink_port_region_ops {
+ const char *name;
+ void (*destructor)(const void *data);
+ int (*snapshot)(struct devlink_port *port,
+ const struct devlink_port_region_ops *ops,
+ struct netlink_ext_ack *extack,
+ u8 **data);
+ void *priv;
+};
struct devlink_fmsg;
struct devlink_health_reporter;
@@ -502,16 +641,60 @@
* @dump: callback to dump an object
* if priv_ctx is NULL, run a full dump
* @diagnose: callback to diagnose the current status
+ * @test: callback to trigger a test event
*/
struct devlink_health_reporter_ops {
char *name;
int (*recover)(struct devlink_health_reporter *reporter,
- void *priv_ctx);
+ void *priv_ctx, struct netlink_ext_ack *extack);
int (*dump)(struct devlink_health_reporter *reporter,
- struct devlink_fmsg *fmsg, void *priv_ctx);
+ struct devlink_fmsg *fmsg, void *priv_ctx,
+ struct netlink_ext_ack *extack);
int (*diagnose)(struct devlink_health_reporter *reporter,
- struct devlink_fmsg *fmsg);
+ struct devlink_fmsg *fmsg,
+ struct netlink_ext_ack *extack);
+ int (*test)(struct devlink_health_reporter *reporter,
+ struct netlink_ext_ack *extack);
+};
+
+/**
+ * struct devlink_trap_metadata - Packet trap metadata.
+ * @trap_name: Trap name.
+ * @trap_group_name: Trap group name.
+ * @input_dev: Input netdevice.
+ * @fa_cookie: Flow action user cookie.
+ * @trap_type: Trap type.
+ */
+struct devlink_trap_metadata {
+ const char *trap_name;
+ const char *trap_group_name;
+ struct net_device *input_dev;
+ const struct flow_action_cookie *fa_cookie;
+ enum devlink_trap_type trap_type;
+};
+
+/**
+ * struct devlink_trap_policer - Immutable packet trap policer attributes.
+ * @id: Policer identifier.
+ * @init_rate: Initial rate in packets / sec.
+ * @init_burst: Initial burst size in packets.
+ * @max_rate: Maximum rate.
+ * @min_rate: Minimum rate.
+ * @max_burst: Maximum burst size.
+ * @min_burst: Minimum burst size.
+ *
+ * Describes immutable attributes of packet trap policers that drivers register
+ * with devlink.
+ */
+struct devlink_trap_policer {
+ u32 id;
+ u64 init_rate;
+ u64 init_burst;
+ u64 max_rate;
+ u64 min_rate;
+ u64 max_burst;
+ u64 min_burst;
};
/**
@@ -519,6 +702,7 @@
* @name: Trap group name.
* @id: Trap group identifier.
* @generic: Whether the trap group is generic or not.
+ * @init_policer_id: Initial policer identifier.
*
* Describes immutable attributes of packet trap groups that drivers register
* with devlink.
@@ -527,9 +711,11 @@
const char *name;
u16 id;
bool generic;
+ u32 init_policer_id;
};
#define DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT BIT(0)
+#define DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE BIT(1)
/**
* struct devlink_trap - Immutable packet trap attributes.
@@ -538,7 +724,7 @@
* @generic: Whether the trap is generic or not.
* @id: Trap identifier.
* @name: Trap name.
- * @group: Immutable packet trap group attributes.
+ * @init_group_id: Initial group identifier.
* @metadata_cap: Metadata types that can be provided by the trap.
*
* Describes immutable attributes of packet traps that drivers register with
@@ -550,12 +736,12 @@
bool generic;
u16 id;
const char *name;
- struct devlink_trap_group group;
+ u16 init_group_id;
u32 metadata_cap;
};
/* All traps must be documented in
- * Documentation/networking/devlink-trap.rst
+ * Documentation/networking/devlink/devlink-trap.rst
*/
enum devlink_trap_generic_id {
DEVLINK_TRAP_GENERIC_ID_SMAC_MC,
@@ -567,6 +753,87 @@
DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_ROUTE,
DEVLINK_TRAP_GENERIC_ID_TTL_ERROR,
DEVLINK_TRAP_GENERIC_ID_TAIL_DROP,
+ DEVLINK_TRAP_GENERIC_ID_NON_IP_PACKET,
+ DEVLINK_TRAP_GENERIC_ID_UC_DIP_MC_DMAC,
+ DEVLINK_TRAP_GENERIC_ID_DIP_LB,
+ DEVLINK_TRAP_GENERIC_ID_SIP_MC,
+ DEVLINK_TRAP_GENERIC_ID_SIP_LB,
+ DEVLINK_TRAP_GENERIC_ID_CORRUPTED_IP_HDR,
+ DEVLINK_TRAP_GENERIC_ID_IPV4_SIP_BC,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_RESERVED_SCOPE,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE,
+ DEVLINK_TRAP_GENERIC_ID_MTU_ERROR,
+ DEVLINK_TRAP_GENERIC_ID_UNRESOLVED_NEIGH,
+ DEVLINK_TRAP_GENERIC_ID_RPF,
+ DEVLINK_TRAP_GENERIC_ID_REJECT_ROUTE,
+ DEVLINK_TRAP_GENERIC_ID_IPV4_LPM_UNICAST_MISS,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_LPM_UNICAST_MISS,
+ DEVLINK_TRAP_GENERIC_ID_NON_ROUTABLE,
+ DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR,
+ DEVLINK_TRAP_GENERIC_ID_OVERLAY_SMAC_MC,
+ DEVLINK_TRAP_GENERIC_ID_INGRESS_FLOW_ACTION_DROP,
+ DEVLINK_TRAP_GENERIC_ID_EGRESS_FLOW_ACTION_DROP,
+ DEVLINK_TRAP_GENERIC_ID_STP,
+ DEVLINK_TRAP_GENERIC_ID_LACP,
+ DEVLINK_TRAP_GENERIC_ID_LLDP,
+ DEVLINK_TRAP_GENERIC_ID_IGMP_QUERY,
+ DEVLINK_TRAP_GENERIC_ID_IGMP_V1_REPORT,
+ DEVLINK_TRAP_GENERIC_ID_IGMP_V2_REPORT,
+ DEVLINK_TRAP_GENERIC_ID_IGMP_V3_REPORT,
+ DEVLINK_TRAP_GENERIC_ID_IGMP_V2_LEAVE,
+ DEVLINK_TRAP_GENERIC_ID_MLD_QUERY,
+ DEVLINK_TRAP_GENERIC_ID_MLD_V1_REPORT,
+ DEVLINK_TRAP_GENERIC_ID_MLD_V2_REPORT,
+ DEVLINK_TRAP_GENERIC_ID_MLD_V1_DONE,
+ DEVLINK_TRAP_GENERIC_ID_IPV4_DHCP,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_DHCP,
+ DEVLINK_TRAP_GENERIC_ID_ARP_REQUEST,
+ DEVLINK_TRAP_GENERIC_ID_ARP_RESPONSE,
+ DEVLINK_TRAP_GENERIC_ID_ARP_OVERLAY,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_NEIGH_SOLICIT,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_NEIGH_ADVERT,
+ DEVLINK_TRAP_GENERIC_ID_IPV4_BFD,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_BFD,
+ DEVLINK_TRAP_GENERIC_ID_IPV4_OSPF,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_OSPF,
+ DEVLINK_TRAP_GENERIC_ID_IPV4_BGP,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_BGP,
+ DEVLINK_TRAP_GENERIC_ID_IPV4_VRRP,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_VRRP,
+ DEVLINK_TRAP_GENERIC_ID_IPV4_PIM,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_PIM,
+ DEVLINK_TRAP_GENERIC_ID_UC_LB,
+ DEVLINK_TRAP_GENERIC_ID_LOCAL_ROUTE,
+ DEVLINK_TRAP_GENERIC_ID_EXTERNAL_ROUTE,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_UC_DIP_LINK_LOCAL_SCOPE,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_DIP_ALL_NODES,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_DIP_ALL_ROUTERS,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_ROUTER_SOLICIT,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_ROUTER_ADVERT,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_REDIRECT,
+ DEVLINK_TRAP_GENERIC_ID_IPV4_ROUTER_ALERT,
+ DEVLINK_TRAP_GENERIC_ID_IPV6_ROUTER_ALERT,
+ DEVLINK_TRAP_GENERIC_ID_PTP_EVENT,
+ DEVLINK_TRAP_GENERIC_ID_PTP_GENERAL,
+ DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_SAMPLE,
+ DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_TRAP,
+ DEVLINK_TRAP_GENERIC_ID_EARLY_DROP,
+ DEVLINK_TRAP_GENERIC_ID_VXLAN_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_LLC_SNAP_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_VLAN_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_PPPOE_PPP_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_MPLS_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_ARP_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_IP_1_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_IP_N_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_GRE_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_UDP_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_TCP_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_IPSEC_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_SCTP_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_DCCP_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_GTP_PARSING,
+ DEVLINK_TRAP_GENERIC_ID_ESP_PARSING,
/* Add new generic trap IDs above */
__DEVLINK_TRAP_GENERIC_ID_MAX,
@@ -574,12 +841,35 @@
};
/* All trap groups must be documented in
- * Documentation/networking/devlink-trap.rst
+ * Documentation/networking/devlink/devlink-trap.rst
*/
enum devlink_trap_group_generic_id {
DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS,
DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_L3_EXCEPTIONS,
DEVLINK_TRAP_GROUP_GENERIC_ID_BUFFER_DROPS,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_TUNNEL_DROPS,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_DROPS,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_STP,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_LACP,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_LLDP,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_MC_SNOOPING,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_DHCP,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_NEIGH_DISCOVERY,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_BFD,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_OSPF,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_BGP,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_VRRP,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_PIM,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_UC_LB,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_LOCAL_DELIVERY,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_EXTERNAL_DELIVERY,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_IPV6,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_EVENT,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_GENERAL,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_SAMPLE,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_TRAP,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_PARSER_ERROR_DROPS,
/* Add new generic trap group IDs above */
__DEVLINK_TRAP_GROUP_GENERIC_ID_MAX,
@@ -605,26 +895,236 @@
"ttl_value_is_too_small"
#define DEVLINK_TRAP_GENERIC_NAME_TAIL_DROP \
"tail_drop"
+#define DEVLINK_TRAP_GENERIC_NAME_NON_IP_PACKET \
+ "non_ip"
+#define DEVLINK_TRAP_GENERIC_NAME_UC_DIP_MC_DMAC \
+ "uc_dip_over_mc_dmac"
+#define DEVLINK_TRAP_GENERIC_NAME_DIP_LB \
+ "dip_is_loopback_address"
+#define DEVLINK_TRAP_GENERIC_NAME_SIP_MC \
+ "sip_is_mc"
+#define DEVLINK_TRAP_GENERIC_NAME_SIP_LB \
+ "sip_is_loopback_address"
+#define DEVLINK_TRAP_GENERIC_NAME_CORRUPTED_IP_HDR \
+ "ip_header_corrupted"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV4_SIP_BC \
+ "ipv4_sip_is_limited_bc"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_MC_DIP_RESERVED_SCOPE \
+ "ipv6_mc_dip_reserved_scope"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE \
+ "ipv6_mc_dip_interface_local_scope"
+#define DEVLINK_TRAP_GENERIC_NAME_MTU_ERROR \
+ "mtu_value_is_too_small"
+#define DEVLINK_TRAP_GENERIC_NAME_UNRESOLVED_NEIGH \
+ "unresolved_neigh"
+#define DEVLINK_TRAP_GENERIC_NAME_RPF \
+ "mc_reverse_path_forwarding"
+#define DEVLINK_TRAP_GENERIC_NAME_REJECT_ROUTE \
+ "reject_route"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV4_LPM_UNICAST_MISS \
+ "ipv4_lpm_miss"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_LPM_UNICAST_MISS \
+ "ipv6_lpm_miss"
+#define DEVLINK_TRAP_GENERIC_NAME_NON_ROUTABLE \
+ "non_routable_packet"
+#define DEVLINK_TRAP_GENERIC_NAME_DECAP_ERROR \
+ "decap_error"
+#define DEVLINK_TRAP_GENERIC_NAME_OVERLAY_SMAC_MC \
+ "overlay_smac_is_mc"
+#define DEVLINK_TRAP_GENERIC_NAME_INGRESS_FLOW_ACTION_DROP \
+ "ingress_flow_action_drop"
+#define DEVLINK_TRAP_GENERIC_NAME_EGRESS_FLOW_ACTION_DROP \
+ "egress_flow_action_drop"
+#define DEVLINK_TRAP_GENERIC_NAME_STP \
+ "stp"
+#define DEVLINK_TRAP_GENERIC_NAME_LACP \
+ "lacp"
+#define DEVLINK_TRAP_GENERIC_NAME_LLDP \
+ "lldp"
+#define DEVLINK_TRAP_GENERIC_NAME_IGMP_QUERY \
+ "igmp_query"
+#define DEVLINK_TRAP_GENERIC_NAME_IGMP_V1_REPORT \
+ "igmp_v1_report"
+#define DEVLINK_TRAP_GENERIC_NAME_IGMP_V2_REPORT \
+ "igmp_v2_report"
+#define DEVLINK_TRAP_GENERIC_NAME_IGMP_V3_REPORT \
+ "igmp_v3_report"
+#define DEVLINK_TRAP_GENERIC_NAME_IGMP_V2_LEAVE \
+ "igmp_v2_leave"
+#define DEVLINK_TRAP_GENERIC_NAME_MLD_QUERY \
+ "mld_query"
+#define DEVLINK_TRAP_GENERIC_NAME_MLD_V1_REPORT \
+ "mld_v1_report"
+#define DEVLINK_TRAP_GENERIC_NAME_MLD_V2_REPORT \
+ "mld_v2_report"
+#define DEVLINK_TRAP_GENERIC_NAME_MLD_V1_DONE \
+ "mld_v1_done"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV4_DHCP \
+ "ipv4_dhcp"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_DHCP \
+ "ipv6_dhcp"
+#define DEVLINK_TRAP_GENERIC_NAME_ARP_REQUEST \
+ "arp_request"
+#define DEVLINK_TRAP_GENERIC_NAME_ARP_RESPONSE \
+ "arp_response"
+#define DEVLINK_TRAP_GENERIC_NAME_ARP_OVERLAY \
+ "arp_overlay"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_NEIGH_SOLICIT \
+ "ipv6_neigh_solicit"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_NEIGH_ADVERT \
+ "ipv6_neigh_advert"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV4_BFD \
+ "ipv4_bfd"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_BFD \
+ "ipv6_bfd"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV4_OSPF \
+ "ipv4_ospf"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_OSPF \
+ "ipv6_ospf"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV4_BGP \
+ "ipv4_bgp"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_BGP \
+ "ipv6_bgp"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV4_VRRP \
+ "ipv4_vrrp"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_VRRP \
+ "ipv6_vrrp"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV4_PIM \
+ "ipv4_pim"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_PIM \
+ "ipv6_pim"
+#define DEVLINK_TRAP_GENERIC_NAME_UC_LB \
+ "uc_loopback"
+#define DEVLINK_TRAP_GENERIC_NAME_LOCAL_ROUTE \
+ "local_route"
+#define DEVLINK_TRAP_GENERIC_NAME_EXTERNAL_ROUTE \
+ "external_route"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_UC_DIP_LINK_LOCAL_SCOPE \
+ "ipv6_uc_dip_link_local_scope"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_DIP_ALL_NODES \
+ "ipv6_dip_all_nodes"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_DIP_ALL_ROUTERS \
+ "ipv6_dip_all_routers"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_ROUTER_SOLICIT \
+ "ipv6_router_solicit"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_ROUTER_ADVERT \
+ "ipv6_router_advert"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_REDIRECT \
+ "ipv6_redirect"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV4_ROUTER_ALERT \
+ "ipv4_router_alert"
+#define DEVLINK_TRAP_GENERIC_NAME_IPV6_ROUTER_ALERT \
+ "ipv6_router_alert"
+#define DEVLINK_TRAP_GENERIC_NAME_PTP_EVENT \
+ "ptp_event"
+#define DEVLINK_TRAP_GENERIC_NAME_PTP_GENERAL \
+ "ptp_general"
+#define DEVLINK_TRAP_GENERIC_NAME_FLOW_ACTION_SAMPLE \
+ "flow_action_sample"
+#define DEVLINK_TRAP_GENERIC_NAME_FLOW_ACTION_TRAP \
+ "flow_action_trap"
+#define DEVLINK_TRAP_GENERIC_NAME_EARLY_DROP \
+ "early_drop"
+#define DEVLINK_TRAP_GENERIC_NAME_VXLAN_PARSING \
+ "vxlan_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_LLC_SNAP_PARSING \
+ "llc_snap_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_VLAN_PARSING \
+ "vlan_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_PPPOE_PPP_PARSING \
+ "pppoe_ppp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_MPLS_PARSING \
+ "mpls_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_ARP_PARSING \
+ "arp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_IP_1_PARSING \
+ "ip_1_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_IP_N_PARSING \
+ "ip_n_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_GRE_PARSING \
+ "gre_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_UDP_PARSING \
+ "udp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_TCP_PARSING \
+ "tcp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_IPSEC_PARSING \
+ "ipsec_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_SCTP_PARSING \
+ "sctp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_DCCP_PARSING \
+ "dccp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_GTP_PARSING \
+ "gtp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_ESP_PARSING \
+ "esp_parsing"
+
#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \
"l2_drops"
#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L3_DROPS \
"l3_drops"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L3_EXCEPTIONS \
+ "l3_exceptions"
#define DEVLINK_TRAP_GROUP_GENERIC_NAME_BUFFER_DROPS \
"buffer_drops"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_TUNNEL_DROPS \
+ "tunnel_drops"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_DROPS \
+ "acl_drops"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_STP \
+ "stp"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_LACP \
+ "lacp"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_LLDP \
+ "lldp"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_MC_SNOOPING \
+ "mc_snooping"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_DHCP \
+ "dhcp"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_NEIGH_DISCOVERY \
+ "neigh_discovery"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_BFD \
+ "bfd"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_OSPF \
+ "ospf"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_BGP \
+ "bgp"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_VRRP \
+ "vrrp"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_PIM \
+ "pim"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_UC_LB \
+ "uc_loopback"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_LOCAL_DELIVERY \
+ "local_delivery"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_EXTERNAL_DELIVERY \
+ "external_delivery"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_IPV6 \
+ "ipv6"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_PTP_EVENT \
+ "ptp_event"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_PTP_GENERAL \
+ "ptp_general"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_SAMPLE \
+ "acl_sample"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_TRAP \
+ "acl_trap"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_PARSER_ERROR_DROPS \
+ "parser_error_drops"
-#define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group, _metadata_cap) \
+#define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group_id, \
+ _metadata_cap) \
{ \
.type = DEVLINK_TRAP_TYPE_##_type, \
.init_action = DEVLINK_TRAP_ACTION_##_init_action, \
.generic = true, \
.id = DEVLINK_TRAP_GENERIC_ID_##_id, \
.name = DEVLINK_TRAP_GENERIC_NAME_##_id, \
- .group = _group, \
+ .init_group_id = _group_id, \
.metadata_cap = _metadata_cap, \
}
-#define DEVLINK_TRAP_DRIVER(_type, _init_action, _id, _name, _group, \
+#define DEVLINK_TRAP_DRIVER(_type, _init_action, _id, _name, _group_id, \
_metadata_cap) \
{ \
.type = DEVLINK_TRAP_TYPE_##_type, \
@@ -632,21 +1132,45 @@
.generic = false, \
.id = _id, \
.name = _name, \
- .group = _group, \
+ .init_group_id = _group_id, \
.metadata_cap = _metadata_cap, \
}
-#define DEVLINK_TRAP_GROUP_GENERIC(_id) \
+#define DEVLINK_TRAP_GROUP_GENERIC(_id, _policer_id) \
{ \
.name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id, \
.id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id, \
.generic = true, \
+ .init_policer_id = _policer_id, \
+ }
+
+#define DEVLINK_TRAP_POLICER(_id, _rate, _burst, _max_rate, _min_rate, \
+ _max_burst, _min_burst) \
+ { \
+ .id = _id, \
+ .init_rate = _rate, \
+ .init_burst = _burst, \
+ .max_rate = _max_rate, \
+ .min_rate = _min_rate, \
+ .max_burst = _max_burst, \
+ .min_burst = _min_burst, \
}
struct devlink_ops {
- int (*reload_down)(struct devlink *devlink,
+ /**
+ * @supported_flash_update_params:
+ * mask of parameters supported by the driver's .flash_update
+ * implemementation.
+ */
+ u32 supported_flash_update_params;
+ unsigned long reload_actions;
+ unsigned long reload_limits;
+ int (*reload_down)(struct devlink *devlink, bool netns_change,
+ enum devlink_reload_action action,
+ enum devlink_reload_limit limit,
struct netlink_ext_ack *extack);
- int (*reload_up)(struct devlink *devlink,
+ int (*reload_up)(struct devlink *devlink, enum devlink_reload_action action,
+ enum devlink_reload_limit limit, u32 *actions_performed,
struct netlink_ext_ack *extack);
int (*port_type_set)(struct devlink_port *devlink_port,
enum devlink_port_type port_type);
@@ -704,8 +1228,15 @@
struct netlink_ext_ack *extack);
int (*info_get)(struct devlink *devlink, struct devlink_info_req *req,
struct netlink_ext_ack *extack);
- int (*flash_update)(struct devlink *devlink, const char *file_name,
- const char *component,
+ /**
+ * @flash_update: Device flash update function
+ *
+ * Used to perform a flash update for the device. The set of
+ * parameters supported by the driver should be set in
+ * supported_flash_update_params.
+ */
+ int (*flash_update)(struct devlink *devlink,
+ struct devlink_flash_update_params *params,
struct netlink_ext_ack *extack);
/**
* @trap_init: Trap initialization function.
@@ -730,7 +1261,8 @@
*/
int (*trap_action_set)(struct devlink *devlink,
const struct devlink_trap *trap,
- enum devlink_trap_action action);
+ enum devlink_trap_action action,
+ struct netlink_ext_ack *extack);
/**
* @trap_group_init: Trap group initialization function.
*
@@ -739,6 +1271,80 @@
*/
int (*trap_group_init)(struct devlink *devlink,
const struct devlink_trap_group *group);
+ /**
+ * @trap_group_set: Trap group parameters set function.
+ *
+ * Note: @policer can be NULL when a policer is being unbound from
+ * @group.
+ */
+ int (*trap_group_set)(struct devlink *devlink,
+ const struct devlink_trap_group *group,
+ const struct devlink_trap_policer *policer,
+ struct netlink_ext_ack *extack);
+ /**
+ * @trap_group_action_set: Trap group action set function.
+ *
+ * If this callback is populated, it will take precedence over looping
+ * over all traps in a group and calling .trap_action_set().
+ */
+ int (*trap_group_action_set)(struct devlink *devlink,
+ const struct devlink_trap_group *group,
+ enum devlink_trap_action action,
+ struct netlink_ext_ack *extack);
+ /**
+ * @trap_policer_init: Trap policer initialization function.
+ *
+ * Should be used by device drivers to initialize the trap policer in
+ * the underlying device.
+ */
+ int (*trap_policer_init)(struct devlink *devlink,
+ const struct devlink_trap_policer *policer);
+ /**
+ * @trap_policer_fini: Trap policer de-initialization function.
+ *
+ * Should be used by device drivers to de-initialize the trap policer
+ * in the underlying device.
+ */
+ void (*trap_policer_fini)(struct devlink *devlink,
+ const struct devlink_trap_policer *policer);
+ /**
+ * @trap_policer_set: Trap policer parameters set function.
+ */
+ int (*trap_policer_set)(struct devlink *devlink,
+ const struct devlink_trap_policer *policer,
+ u64 rate, u64 burst,
+ struct netlink_ext_ack *extack);
+ /**
+ * @trap_policer_counter_get: Trap policer counter get function.
+ *
+ * Should be used by device drivers to report number of packets dropped
+ * by the policer.
+ */
+ int (*trap_policer_counter_get)(struct devlink *devlink,
+ const struct devlink_trap_policer *policer,
+ u64 *p_drops);
+ /**
+ * @port_function_hw_addr_get: Port function's hardware address get function.
+ *
+ * Should be used by device drivers to report the hardware address of a function managed
+ * by the devlink port. Driver should return -EOPNOTSUPP if it doesn't support port
+ * function handling for a particular port.
+ *
+ * Note: @extack can be NULL when port notifier queries the port function.
+ */
+ int (*port_function_hw_addr_get)(struct devlink *devlink, struct devlink_port *port,
+ u8 *hw_addr, int *hw_addr_len,
+ struct netlink_ext_ack *extack);
+ /**
+ * @port_function_hw_addr_set: Port function's hardware address set function.
+ *
+ * Should be used by device drivers to set the hardware address of a function managed
+ * by the devlink port. Driver should return -EOPNOTSUPP if it doesn't support port
+ * function handling for a particular port.
+ */
+ int (*port_function_hw_addr_set)(struct devlink *devlink, struct devlink_port *port,
+ const u8 *hw_addr, int hw_addr_len,
+ struct netlink_ext_ack *extack);
};
static inline void *devlink_priv(struct devlink *devlink)
@@ -772,6 +1378,8 @@
struct ib_device;
+struct net *devlink_net(const struct devlink *devlink);
+void devlink_net_set(struct devlink *devlink, struct net *net);
struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size);
int devlink_register(struct devlink *devlink, struct device *dev);
void devlink_unregister(struct devlink *devlink);
@@ -788,18 +1396,11 @@
struct ib_device *ibdev);
void devlink_port_type_clear(struct devlink_port *devlink_port);
void devlink_port_attrs_set(struct devlink_port *devlink_port,
- enum devlink_port_flavour flavour,
- u32 port_number, bool split,
- u32 split_subport_number,
- const unsigned char *switch_id,
- unsigned char switch_id_len);
-void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port,
- const unsigned char *switch_id,
- unsigned char switch_id_len, u16 pf);
-void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
- const unsigned char *switch_id,
- unsigned char switch_id_len,
- u16 pf, u16 vf);
+ struct devlink_port_attrs *devlink_port_attrs);
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller,
+ u16 pf, bool external);
+void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller,
+ u16 pf, u16 vf, bool external);
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
u32 size, u16 ingress_pools_count,
u16 egress_pools_count, u16 ingress_tc_count,
@@ -879,19 +1480,27 @@
u32 param_id);
void devlink_param_value_str_fill(union devlink_param_value *dst_val,
const char *src);
-struct devlink_region *devlink_region_create(struct devlink *devlink,
- const char *region_name,
- u32 region_max_snapshots,
- u64 region_size);
+struct devlink_region *
+devlink_region_create(struct devlink *devlink,
+ const struct devlink_region_ops *ops,
+ u32 region_max_snapshots, u64 region_size);
+struct devlink_region *
+devlink_port_region_create(struct devlink_port *port,
+ const struct devlink_port_region_ops *ops,
+ u32 region_max_snapshots, u64 region_size);
void devlink_region_destroy(struct devlink_region *region);
-u32 devlink_region_shapshot_id_get(struct devlink *devlink);
+void devlink_port_region_destroy(struct devlink_region *region);
+
+int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id);
+void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id);
int devlink_region_snapshot_create(struct devlink_region *region,
- u8 *data, u32 snapshot_id,
- devlink_snapshot_data_dest_t *data_destructor);
+ u8 *data, u32 snapshot_id);
int devlink_info_serial_number_put(struct devlink_info_req *req,
const char *sn);
int devlink_info_driver_name_put(struct devlink_info_req *req,
const char *name);
+int devlink_info_board_serial_number_put(struct devlink_info_req *req,
+ const char *bsn);
int devlink_info_version_fixed_put(struct devlink_info_req *req,
const char *version_name,
const char *version_value);
@@ -911,6 +1520,9 @@
int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg,
const char *name);
int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg);
+int devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg,
+ const char *name);
+int devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg);
int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value);
int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value);
@@ -931,16 +1543,24 @@
int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name,
const char *value);
int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name,
- const void *value, u16 value_len);
+ const void *value, u32 value_len);
struct devlink_health_reporter *
devlink_health_reporter_create(struct devlink *devlink,
const struct devlink_health_reporter_ops *ops,
- u64 graceful_period, bool auto_recover,
- void *priv);
+ u64 graceful_period, void *priv);
+
+struct devlink_health_reporter *
+devlink_port_health_reporter_create(struct devlink_port *port,
+ const struct devlink_health_reporter_ops *ops,
+ u64 graceful_period, void *priv);
+
void
devlink_health_reporter_destroy(struct devlink_health_reporter *reporter);
+void
+devlink_port_health_reporter_destroy(struct devlink_health_reporter *reporter);
+
void *
devlink_health_reporter_priv(struct devlink_health_reporter *reporter);
int devlink_health_report(struct devlink_health_reporter *reporter,
@@ -948,8 +1568,13 @@
void
devlink_health_reporter_state_update(struct devlink_health_reporter *reporter,
enum devlink_health_reporter_state state);
+void
+devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter);
bool devlink_is_reload_failed(const struct devlink *devlink);
+void devlink_remote_reload_actions_performed(struct devlink *devlink,
+ enum devlink_reload_limit limit,
+ u32 actions_performed);
void devlink_flash_update_begin_notify(struct devlink *devlink);
void devlink_flash_update_end_notify(struct devlink *devlink);
@@ -958,6 +1583,10 @@
const char *component,
unsigned long done,
unsigned long total);
+void devlink_flash_update_timeout_notify(struct devlink *devlink,
+ const char *status_msg,
+ const char *component,
+ unsigned long timeout);
int devlink_traps_register(struct devlink *devlink,
const struct devlink_trap *traps,
@@ -965,10 +1594,24 @@
void devlink_traps_unregister(struct devlink *devlink,
const struct devlink_trap *traps,
size_t traps_count);
-void devlink_trap_report(struct devlink *devlink,
- struct sk_buff *skb, void *trap_ctx,
- struct devlink_port *in_devlink_port);
+void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
+ void *trap_ctx, struct devlink_port *in_devlink_port,
+ const struct flow_action_cookie *fa_cookie);
void *devlink_trap_ctx_priv(void *trap_ctx);
+int devlink_trap_groups_register(struct devlink *devlink,
+ const struct devlink_trap_group *groups,
+ size_t groups_count);
+void devlink_trap_groups_unregister(struct devlink *devlink,
+ const struct devlink_trap_group *groups,
+ size_t groups_count);
+int
+devlink_trap_policers_register(struct devlink *devlink,
+ const struct devlink_trap_policer *policers,
+ size_t policers_count);
+void
+devlink_trap_policers_unregister(struct devlink *devlink,
+ const struct devlink_trap_policer *policers,
+ size_t policers_count);
#if IS_ENABLED(CONFIG_NET_DEVLINK)
diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h
index 6dd2213..ccc6e9d 100644
--- a/include/net/dn_fib.h
+++ b/include/net/dn_fib.h
@@ -90,7 +90,7 @@
int (*flush)(struct dn_fib_table *t);
int (*dump)(struct dn_fib_table *t, struct sk_buff *skb, struct netlink_callback *cb);
- unsigned char data[0];
+ unsigned char data[];
};
#ifdef CONFIG_DECNET_ROUTER
diff --git a/include/net/drop_monitor.h b/include/net/drop_monitor.h
deleted file mode 100644
index f68bc37..0000000
--- a/include/net/drop_monitor.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-
-#ifndef _NET_DROP_MONITOR_H_
-#define _NET_DROP_MONITOR_H_
-
-#include <linux/ktime.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-
-/**
- * struct net_dm_hw_metadata - Hardware-supplied packet metadata.
- * @trap_group_name: Hardware trap group name.
- * @trap_name: Hardware trap name.
- * @input_dev: Input netdevice.
- */
-struct net_dm_hw_metadata {
- const char *trap_group_name;
- const char *trap_name;
- struct net_device *input_dev;
-};
-
-#if IS_REACHABLE(CONFIG_NET_DROP_MONITOR)
-void net_dm_hw_report(struct sk_buff *skb,
- const struct net_dm_hw_metadata *hw_metadata);
-#else
-static inline void
-net_dm_hw_report(struct sk_buff *skb,
- const struct net_dm_hw_metadata *hw_metadata)
-{
-}
-#endif
-
-#endif /* _NET_DROP_MONITOR_H_ */
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 541fb51..35429a1 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -42,6 +42,9 @@
#define DSA_TAG_PROTO_8021Q_VALUE 12
#define DSA_TAG_PROTO_SJA1105_VALUE 13
#define DSA_TAG_PROTO_KSZ8795_VALUE 14
+#define DSA_TAG_PROTO_OCELOT_VALUE 15
+#define DSA_TAG_PROTO_AR9331_VALUE 16
+#define DSA_TAG_PROTO_RTL4_A_VALUE 17
enum dsa_tag_protocol {
DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE,
@@ -59,6 +62,9 @@
DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE,
DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE,
DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE,
+ DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE,
+ DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE,
+ DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE,
};
struct packet_type;
@@ -68,8 +74,8 @@
struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev);
struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt);
- int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto,
- int *offset);
+ void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto,
+ int *offset);
/* Used to determine which traffic should match the DSA filter in
* eth_type_trans, and which, if any, should bypass it and be processed
* as regular on the master net device.
@@ -78,6 +84,23 @@
unsigned int overhead;
const char *name;
enum dsa_tag_protocol proto;
+ /* Some tagging protocols either mangle or shift the destination MAC
+ * address, in which case the DSA master would drop packets on ingress
+ * if what it understands out of the destination MAC address is not in
+ * its RX filter.
+ */
+ bool promisc_on_master;
+ bool tail_tag;
+};
+
+/* This structure defines the control interfaces that are overlayed by the
+ * DSA layer on top of the DSA CPU/management net_device instance. This is
+ * used by the core net_device layer while calling various net_device_ops
+ * function pointers.
+ */
+struct dsa_netdevice_ops {
+ int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr,
+ int cmd);
};
#define DSA_TAG_DRIVER_ALIAS "dsa_tag-"
@@ -86,7 +109,6 @@
struct dsa_skb_cb {
struct sk_buff *clone;
- bool deferred_xmit;
};
struct __dsa_skb_cb {
@@ -94,8 +116,6 @@
u8 priv[48 - sizeof(struct dsa_skb_cb)];
};
-#define __DSA_SKB_CB(skb) ((struct __dsa_skb_cb *)((skb)->cb))
-
#define DSA_SKB_CB(skb) ((struct dsa_skb_cb *)((skb)->cb))
#define DSA_SKB_CB_PRIV(skb) \
@@ -122,20 +142,17 @@
*/
struct dsa_platform_data *pd;
- /*
- * The switch port to which the CPU is attached.
- */
- struct dsa_port *cpu_dp;
+ /* List of switch ports */
+ struct list_head ports;
- /*
- * Data for the individual switch chips.
- */
- struct dsa_switch *ds[DSA_MAX_SWITCHES];
+ /* List of DSA links composing the routing table */
+ struct list_head rtable;
};
-/* TC matchall action types, only mirroring for now */
+/* TC matchall action types */
enum dsa_port_mall_action_type {
DSA_PORT_MALL_MIRROR,
+ DSA_PORT_MALL_POLICER,
};
/* TC mirroring entry */
@@ -144,6 +161,12 @@
bool ingress;
};
+/* TC port policer entry */
+struct dsa_mall_policer_tc_entry {
+ u32 burst;
+ u64 rate_bytes_per_sec;
+};
+
/* TC matchall entry */
struct dsa_mall_tc_entry {
struct list_head list;
@@ -151,6 +174,7 @@
enum dsa_port_mall_action_type type;
union {
struct dsa_mall_mirror_tc_entry mirror;
+ struct dsa_mall_policer_tc_entry policer;
};
};
@@ -191,11 +215,11 @@
u8 stp_state;
struct net_device *bridge_dev;
struct devlink_port devlink_port;
+ bool devlink_port_setup;
struct phylink *pl;
struct phylink_config pl_config;
- struct work_struct xmit_work;
- struct sk_buff_head xmit_queue;
+ struct list_head list;
/*
* Give the switch driver somewhere to hang its per-port private data
@@ -211,10 +235,25 @@
/*
* Original copy of the master netdev net_device_ops
*/
- const struct net_device_ops *orig_ndo_ops;
+ const struct dsa_netdevice_ops *netdev_ops;
+
+ bool setup;
+};
+
+/* TODO: ideally DSA ports would have a single dp->link_dp member,
+ * and no dst->rtable nor this struct dsa_link would be needed,
+ * but this would require some more complex tree walking,
+ * so keep it stupid at the moment and list them all.
+ */
+struct dsa_link {
+ struct dsa_port *dp;
+ struct dsa_port *link_dp;
+ struct list_head list;
};
struct dsa_switch {
+ bool setup;
+
struct device *dev;
/*
@@ -243,13 +282,6 @@
const struct dsa_switch_ops *ops;
/*
- * An array of which element [a] indicates which port on this
- * switch should be used to send packets to that are destined
- * for switch a. Can be NULL if there is only one switch chip.
- */
- s8 rtable[DSA_MAX_SWITCHES];
-
- /*
* Slave mii_bus and devices for the individual ports.
*/
u32 phys_mii_mask;
@@ -270,19 +302,50 @@
*/
bool vlan_filtering_is_global;
+ /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges
+ * that have vlan_filtering=0. All drivers should ideally set this (and
+ * then the option would get removed), but it is unknown whether this
+ * would break things or not.
+ */
+ bool configure_vlan_while_not_filtering;
+
+ /* If the switch driver always programs the CPU port as egress tagged
+ * despite the VLAN configuration indicating otherwise, then setting
+ * @untag_bridge_pvid will force the DSA receive path to pop the bridge's
+ * default_pvid VLAN tagged frames to offer a consistent behavior
+ * between a vlan_filtering=0 and vlan_filtering=1 bridge device.
+ */
+ bool untag_bridge_pvid;
+
/* In case vlan_filtering_is_global is set, the VLAN awareness state
* should be retrieved from here and not from the per-port settings.
*/
bool vlan_filtering;
- /* Dynamically allocated ports, keep last */
+ /* MAC PCS does not provide link state change interrupt, and requires
+ * polling. Flag passed on to PHYLINK.
+ */
+ bool pcs_poll;
+
+ /* For switches that only have the MRU configurable. To ensure the
+ * configured MTU is not exceeded, normalization of MRU on all bridged
+ * interfaces is needed.
+ */
+ bool mtu_enforcement_ingress;
+
size_t num_ports;
- struct dsa_port ports[];
};
-static inline const struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p)
+static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p)
{
- return &ds->ports[p];
+ struct dsa_switch_tree *dst = ds->dst;
+ struct dsa_port *dp;
+
+ list_for_each_entry(dp, &dst->ports, list)
+ if (dp->ds == ds && dp->index == p)
+ return dp;
+
+ return NULL;
}
static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p)
@@ -317,6 +380,19 @@
return mask;
}
+/* Return the local port used to reach an arbitrary switch device */
+static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device)
+{
+ struct dsa_switch_tree *dst = ds->dst;
+ struct dsa_link *dl;
+
+ list_for_each_entry(dl, &dst->rtable, list)
+ if (dl->dp->ds == ds && dl->link_dp->ds->index == device)
+ return dl->dp->index;
+
+ return ds->num_ports;
+}
+
/* Return the local port used to reach an arbitrary switch port */
static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device,
int port)
@@ -324,7 +400,7 @@
if (device == ds->index)
return port;
else
- return ds->rtable[device];
+ return dsa_routing_port(ds, device);
}
/* Return the local port used to reach the dedicated CPU port */
@@ -353,7 +429,8 @@
bool is_static, void *data);
struct dsa_switch_ops {
enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds,
- int port);
+ int port,
+ enum dsa_tag_protocol mprot);
int (*setup)(struct dsa_switch *ds);
void (*teardown)(struct dsa_switch *ds);
@@ -392,7 +469,9 @@
void (*phylink_mac_link_up)(struct dsa_switch *ds, int port,
unsigned int mode,
phy_interface_t interface,
- struct phy_device *phydev);
+ struct phy_device *phydev,
+ int speed, int duplex,
+ bool tx_pause, bool rx_pause);
void (*phylink_fixed_state)(struct dsa_switch *ds, int port,
struct phylink_link_state *state);
/*
@@ -473,7 +552,8 @@
* VLAN support
*/
int (*port_vlan_filtering)(struct dsa_switch *ds, int port,
- bool vlan_filtering);
+ bool vlan_filtering,
+ struct switchdev_trans *trans);
int (*port_vlan_prepare)(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_vlan *vlan);
void (*port_vlan_add)(struct dsa_switch *ds, int port,
@@ -510,21 +590,32 @@
/*
* TC integration
*/
+ int (*cls_flower_add)(struct dsa_switch *ds, int port,
+ struct flow_cls_offload *cls, bool ingress);
+ int (*cls_flower_del)(struct dsa_switch *ds, int port,
+ struct flow_cls_offload *cls, bool ingress);
+ int (*cls_flower_stats)(struct dsa_switch *ds, int port,
+ struct flow_cls_offload *cls, bool ingress);
int (*port_mirror_add)(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror,
bool ingress);
void (*port_mirror_del)(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror);
+ int (*port_policer_add)(struct dsa_switch *ds, int port,
+ struct dsa_mall_policer_tc_entry *policer);
+ void (*port_policer_del)(struct dsa_switch *ds, int port);
int (*port_setup_tc)(struct dsa_switch *ds, int port,
enum tc_setup_type type, void *type_data);
/*
* Cross-chip operations
*/
- int (*crosschip_bridge_join)(struct dsa_switch *ds, int sw_index,
- int port, struct net_device *br);
- void (*crosschip_bridge_leave)(struct dsa_switch *ds, int sw_index,
- int port, struct net_device *br);
+ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index,
+ int sw_index, int port,
+ struct net_device *br);
+ void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index,
+ int sw_index, int port,
+ struct net_device *br);
/*
* PTP functionality
@@ -538,13 +629,93 @@
bool (*port_rxtstamp)(struct dsa_switch *ds, int port,
struct sk_buff *skb, unsigned int type);
+ /* Devlink parameters, etc */
+ int (*devlink_param_get)(struct dsa_switch *ds, u32 id,
+ struct devlink_param_gset_ctx *ctx);
+ int (*devlink_param_set)(struct dsa_switch *ds, u32 id,
+ struct devlink_param_gset_ctx *ctx);
+ int (*devlink_info_get)(struct dsa_switch *ds,
+ struct devlink_info_req *req,
+ struct netlink_ext_ack *extack);
+
/*
- * Deferred frame Tx
+ * MTU change functionality. Switches can also adjust their MRU through
+ * this method. By MTU, one understands the SDU (L2 payload) length.
+ * If the switch needs to account for the DSA tag on the CPU port, this
+ * method needs to do so privately.
*/
- netdev_tx_t (*port_deferred_xmit)(struct dsa_switch *ds, int port,
- struct sk_buff *skb);
+ int (*port_change_mtu)(struct dsa_switch *ds, int port,
+ int new_mtu);
+ int (*port_max_mtu)(struct dsa_switch *ds, int port);
};
+#define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \
+ DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \
+ dsa_devlink_param_get, dsa_devlink_param_set, NULL)
+
+int dsa_devlink_param_get(struct devlink *dl, u32 id,
+ struct devlink_param_gset_ctx *ctx);
+int dsa_devlink_param_set(struct devlink *dl, u32 id,
+ struct devlink_param_gset_ctx *ctx);
+int dsa_devlink_params_register(struct dsa_switch *ds,
+ const struct devlink_param *params,
+ size_t params_count);
+void dsa_devlink_params_unregister(struct dsa_switch *ds,
+ const struct devlink_param *params,
+ size_t params_count);
+int dsa_devlink_resource_register(struct dsa_switch *ds,
+ const char *resource_name,
+ u64 resource_size,
+ u64 resource_id,
+ u64 parent_resource_id,
+ const struct devlink_resource_size_params *size_params);
+
+void dsa_devlink_resources_unregister(struct dsa_switch *ds);
+
+void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds,
+ u64 resource_id,
+ devlink_resource_occ_get_t *occ_get,
+ void *occ_get_priv);
+void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds,
+ u64 resource_id);
+struct devlink_region *
+dsa_devlink_region_create(struct dsa_switch *ds,
+ const struct devlink_region_ops *ops,
+ u32 region_max_snapshots, u64 region_size);
+struct devlink_region *
+dsa_devlink_port_region_create(struct dsa_switch *ds,
+ int port,
+ const struct devlink_port_region_ops *ops,
+ u32 region_max_snapshots, u64 region_size);
+void dsa_devlink_region_destroy(struct devlink_region *region);
+
+struct dsa_port *dsa_port_from_netdev(struct net_device *netdev);
+
+struct dsa_devlink_priv {
+ struct dsa_switch *ds;
+};
+
+static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl)
+{
+ struct dsa_devlink_priv *dl_priv = devlink_priv(dl);
+
+ return dl_priv->ds;
+}
+
+static inline
+struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port)
+{
+ struct devlink *dl = port->devlink;
+ struct dsa_devlink_priv *dl_priv = devlink_priv(dl);
+
+ return dl_priv->ds;
+}
+
+static inline int dsa_devlink_port_to_port(struct devlink_port *port)
+{
+ return port->index;
+}
+
struct dsa_switch_driver {
struct list_head list;
const struct dsa_switch_ops *ops;
@@ -553,7 +724,7 @@
struct net_device *dsa_dev_to_net_device(struct device *dev);
/* Keep inline for faster access in hot path */
-static inline bool netdev_uses_dsa(struct net_device *dev)
+static inline bool netdev_uses_dsa(const struct net_device *dev)
{
#if IS_ENABLED(CONFIG_NET_DSA)
return dev->dsa_ptr && dev->dsa_ptr->rcv;
@@ -570,9 +741,71 @@
return false;
}
-struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n);
+/* All DSA tags that push the EtherType to the right (basically all except tail
+ * tags, which don't break dissection) can be treated the same from the
+ * perspective of the flow dissector.
+ *
+ * We need to return:
+ * - offset: the (B - A) difference between:
+ * A. the position of the real EtherType and
+ * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes
+ * after the normal EtherType was supposed to be)
+ * The offset in bytes is exactly equal to the tagger overhead (and half of
+ * that, in __be16 shorts).
+ *
+ * - proto: the value of the real EtherType.
+ */
+static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb,
+ __be16 *proto, int *offset)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+ const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops;
+ int tag_len = ops->overhead;
+
+ *offset = tag_len;
+ *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1];
+#endif
+}
+
+#if IS_ENABLED(CONFIG_NET_DSA)
+static inline int __dsa_netdevice_ops_check(struct net_device *dev)
+{
+ int err = -EOPNOTSUPP;
+
+ if (!dev->dsa_ptr)
+ return err;
+
+ if (!dev->dsa_ptr->netdev_ops)
+ return err;
+
+ return 0;
+}
+
+static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr,
+ int cmd)
+{
+ const struct dsa_netdevice_ops *ops;
+ int err;
+
+ err = __dsa_netdevice_ops_check(dev);
+ if (err)
+ return err;
+
+ ops = dev->dsa_ptr->netdev_ops;
+
+ return ops->ndo_do_ioctl(dev, ifr, cmd);
+}
+#else
+static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr,
+ int cmd)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
void dsa_unregister_switch(struct dsa_switch *ds);
int dsa_register_switch(struct dsa_switch *ds);
+struct dsa_switch *dsa_switch_find(int tree_index, int sw_index);
#ifdef CONFIG_PM_SLEEP
int dsa_switch_suspend(struct dsa_switch *ds);
int dsa_switch_resume(struct dsa_switch *ds);
diff --git a/include/net/dsfield.h b/include/net/dsfield.h
index 1a245ee..a59a57f 100644
--- a/include/net/dsfield.h
+++ b/include/net/dsfield.h
@@ -21,7 +21,7 @@
static inline __u8 ipv6_get_dsfield(const struct ipv6hdr *ipv6h)
{
- return ntohs(*(const __be16 *)ipv6h) >> 4;
+ return ntohs(*(__force const __be16 *)ipv6h) >> 4;
}
diff --git a/include/net/dst.h b/include/net/dst.h
index 433f7c1..acd15c5 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -35,7 +35,6 @@
int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
unsigned short flags;
-#define DST_HOST 0x0001
#define DST_NOXFRM 0x0002
#define DST_NOPOLICY 0x0004
#define DST_NOCOUNT 0x0008
@@ -215,7 +214,7 @@
static inline int
dst_metric_locked(const struct dst_entry *dst, int metric)
{
- return dst_metric(dst, RTAX_LOCK) & (1<<metric);
+ return dst_metric(dst, RTAX_LOCK) & (1 << metric);
}
static inline void dst_hold(struct dst_entry *dst)
@@ -536,14 +535,15 @@
dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
}
-static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
- struct dst_entry *encap_dst,
- int headroom)
-{
- u32 encap_mtu = dst_mtu(encap_dst);
-
- if (skb->len > encap_mtu - headroom)
- skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom);
-}
+struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie);
+void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb, u32 mtu, bool confirm_neigh);
+void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb);
+u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old);
+struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
+ struct sk_buff *skb,
+ const void *daddr);
+unsigned int dst_blackhole_mtu(const struct dst_entry *dst);
#endif /* _NET_DST_H */
diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h
index 6763467..df6622a 100644
--- a/include/net/dst_cache.h
+++ b/include/net/dst_cache.h
@@ -80,6 +80,17 @@
}
/**
+ * dst_cache_reset_now - invalidate the cache contents immediately
+ * @dst_cache: the cache
+ *
+ * The caller must be sure there are no concurrent users, as this frees
+ * all dst_cache users immediately, rather than waiting for the next
+ * per-cpu usage like dst_cache_reset does. Most callers should use the
+ * higher speed lazily-freed dst_cache_reset function instead.
+ */
+void dst_cache_reset_now(struct dst_cache *dst_cache);
+
+/**
* dst_cache_init - initialize the cache, allocating the required storage
* @dst_cache: the cache
* @gfp: allocation flags
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 14efa0d..adab27b 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -123,8 +123,20 @@
memcpy(&new_md->u.tun_info, &md_dst->u.tun_info,
sizeof(struct ip_tunnel_info) + md_size);
+#ifdef CONFIG_DST_CACHE
+ /* Unclone the dst cache if there is one */
+ if (new_md->u.tun_info.dst_cache.cache) {
+ int ret;
+
+ ret = dst_cache_init(&new_md->u.tun_info.dst_cache, GFP_ATOMIC);
+ if (ret) {
+ metadata_dst_free(new_md);
+ return ERR_PTR(ret);
+ }
+ }
+#endif
+
skb_dst_drop(skb);
- dst_hold(&new_md->dst);
skb_dst_set(skb, &new_md->dst);
return new_md;
}
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 443863c..88ff7bb 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -53,9 +53,11 @@
return percpu_counter_sum_positive(&dst->pcpuc_entries);
}
+#define DST_PERCPU_COUNTER_BATCH 32
static inline void dst_entries_add(struct dst_ops *dst, int val)
{
- percpu_counter_add(&dst->pcpuc_entries, val);
+ percpu_counter_add_batch(&dst->pcpuc_entries, val,
+ DST_PERCPU_COUNTER_BATCH);
}
static inline int dst_entries_init(struct dst_ops *dst)
diff --git a/include/net/erspan.h b/include/net/erspan.h
index b39643e..0d9e86b 100644
--- a/include/net/erspan.h
+++ b/include/net/erspan.h
@@ -2,7 +2,19 @@
#define __LINUX_ERSPAN_H
/*
- * GRE header for ERSPAN encapsulation (8 octets [34:41]) -- 8 bytes
+ * GRE header for ERSPAN type I encapsulation (4 octets [34:37])
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |0|0|0|0|0|00000|000000000|00000| Protocol Type for ERSPAN |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * The Type I ERSPAN frame format is based on the barebones IP + GRE
+ * encapsulation (as described above) on top of the raw mirrored frame.
+ * There is no extra ERSPAN header.
+ *
+ *
+ * GRE header for ERSPAN type II and II encapsulation (8 octets [34:41])
* 0 1 2 3
* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -43,7 +55,7 @@
* | Platform Specific Info |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
- * GRE proto ERSPAN type II = 0x88BE, type III = 0x22EB
+ * GRE proto ERSPAN type I/II = 0x88BE, type III = 0x22EB
*/
#include <uapi/linux/erspan.h>
@@ -139,6 +151,9 @@
static inline int erspan_hdr_len(int version)
{
+ if (version == 0)
+ return 0;
+
return sizeof(struct erspan_base_hdr) +
(version == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE);
}
diff --git a/include/net/esp.h b/include/net/esp.h
index 117652e..90cd02f 100644
--- a/include/net/esp.h
+++ b/include/net/esp.h
@@ -4,6 +4,8 @@
#include <linux/skbuff.h>
+#define ESP_SKB_FRAG_MAXSIZE (PAGE_SIZE << SKB_FRAG_PAGE_ORDER)
+
struct ip_esp_hdr;
static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb)
@@ -11,6 +13,22 @@
return (struct ip_esp_hdr *)skb_transport_header(skb);
}
+static inline void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
+{
+ /* Fill padding... */
+ if (tfclen) {
+ memset(tail, 0, tfclen);
+ tail += tfclen;
+ }
+ do {
+ int i;
+ for (i = 0; i < plen - 2; i++)
+ tail[i] = i + 1;
+ } while (0);
+ tail[plen - 2] = plen - 2;
+ tail[plen - 1] = proto;
+}
+
struct esp_info {
struct ip_esp_hdr *esph;
__be64 seqno;
diff --git a/include/net/espintcp.h b/include/net/espintcp.h
new file mode 100644
index 0000000..0335bbd
--- /dev/null
+++ b/include/net/espintcp.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_ESPINTCP_H
+#define _NET_ESPINTCP_H
+
+#include <net/strparser.h>
+#include <linux/skmsg.h>
+
+void __init espintcp_init(void);
+
+int espintcp_push_skb(struct sock *sk, struct sk_buff *skb);
+int espintcp_queue_out(struct sock *sk, struct sk_buff *skb);
+bool tcp_is_ulp_esp(struct sock *sk);
+
+struct espintcp_msg {
+ struct sk_buff *skb;
+ struct sk_msg skmsg;
+ int offset;
+ int len;
+};
+
+struct espintcp_ctx {
+ struct strparser strp;
+ struct sk_buff_head ike_queue;
+ struct sk_buff_head out_queue;
+ struct espintcp_msg partial;
+ void (*saved_data_ready)(struct sock *sk);
+ void (*saved_write_space)(struct sock *sk);
+ void (*saved_destruct)(struct sock *sk);
+ struct work_struct work;
+ bool tx_running;
+};
+
+static inline struct espintcp_ctx *espintcp_getctx(const struct sock *sk)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ /* RCU is only needed for diag */
+ return (__force void *)icsk->icsk_ulp_data;
+}
+#endif
diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h
index c49d7bf..6d59221 100644
--- a/include/net/fib_notifier.h
+++ b/include/net/fib_notifier.h
@@ -8,7 +8,6 @@
struct module;
struct fib_notifier_info {
- struct net *net;
int family;
struct netlink_ext_ack *extack;
};
@@ -30,19 +29,21 @@
int family;
struct list_head list;
unsigned int (*fib_seq_read)(struct net *net);
- int (*fib_dump)(struct net *net, struct notifier_block *nb);
+ int (*fib_dump)(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack);
struct module *owner;
struct rcu_head rcu;
};
-int call_fib_notifier(struct notifier_block *nb, struct net *net,
+int call_fib_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
struct fib_notifier_info *info);
int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
struct fib_notifier_info *info);
-int register_fib_notifier(struct notifier_block *nb,
- void (*cb)(struct notifier_block *nb));
-int unregister_fib_notifier(struct notifier_block *nb);
+int register_fib_notifier(struct net *net, struct notifier_block *nb,
+ void (*cb)(struct notifier_block *nb),
+ struct netlink_ext_ack *extack);
+int unregister_fib_notifier(struct net *net, struct notifier_block *nb);
struct fib_notifier_ops *
fib_notifier_ops_register(const struct fib_notifier_ops *tmpl, struct net *net);
void fib_notifier_ops_unregister(struct fib_notifier_ops *ops);
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 7fed319..bd07484 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -10,6 +10,7 @@
#include <net/flow.h>
#include <net/rtnetlink.h>
#include <net/fib_notifier.h>
+#include <linux/indirect_call_wrapper.h>
struct fib_kuid_range {
kuid_t start;
@@ -68,7 +69,7 @@
int (*action)(struct fib_rule *,
struct flowi *, int,
struct fib_lookup_arg *);
- bool (*suppress)(struct fib_rule *,
+ bool (*suppress)(struct fib_rule *, int,
struct fib_lookup_arg *);
int (*match)(struct fib_rule *,
struct flowi *, int);
@@ -195,11 +196,31 @@
int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table,
u32 flags);
bool fib_rule_matchall(const struct fib_rule *rule);
-int fib_rules_dump(struct net *net, struct notifier_block *nb, int family);
+int fib_rules_dump(struct net *net, struct notifier_block *nb, int family,
+ struct netlink_ext_ack *extack);
unsigned int fib_rules_seq_read(struct net *net, int family);
int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack);
int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack);
+
+INDIRECT_CALLABLE_DECLARE(int fib6_rule_match(struct fib_rule *rule,
+ struct flowi *fl, int flags));
+INDIRECT_CALLABLE_DECLARE(int fib4_rule_match(struct fib_rule *rule,
+ struct flowi *fl, int flags));
+
+INDIRECT_CALLABLE_DECLARE(int fib6_rule_action(struct fib_rule *rule,
+ struct flowi *flp, int flags,
+ struct fib_lookup_arg *arg));
+INDIRECT_CALLABLE_DECLARE(int fib4_rule_action(struct fib_rule *rule,
+ struct flowi *flp, int flags,
+ struct fib_lookup_arg *arg));
+
+INDIRECT_CALLABLE_DECLARE(bool fib6_rule_suppress(struct fib_rule *rule,
+ int flags,
+ struct fib_lookup_arg *arg));
+INDIRECT_CALLABLE_DECLARE(bool fib4_rule_suppress(struct fib_rule *rule,
+ int flags,
+ struct fib_lookup_arg *arg));
#endif
diff --git a/include/net/flow.h b/include/net/flow.h
index d058e63..b2531df 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -205,24 +205,6 @@
return container_of(fldn, struct flowi, u.dn);
}
-typedef unsigned long flow_compare_t;
-
-static inline unsigned int flow_key_size(u16 family)
-{
- switch (family) {
- case AF_INET:
- BUILD_BUG_ON(sizeof(struct flowi4) % sizeof(flow_compare_t));
- return sizeof(struct flowi4) / sizeof(flow_compare_t);
- case AF_INET6:
- BUILD_BUG_ON(sizeof(struct flowi6) % sizeof(flow_compare_t));
- return sizeof(struct flowi6) / sizeof(flow_compare_t);
- case AF_DECnet:
- BUILD_BUG_ON(sizeof(struct flowidn) % sizeof(flow_compare_t));
- return sizeof(struct flowidn) / sizeof(flow_compare_t);
- }
- return 0;
-}
-
__u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys);
#endif
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 78f6437..cc10b10 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -8,6 +8,10 @@
#include <linux/string.h>
#include <uapi/linux/if_ether.h>
+struct bpf_prog;
+struct net;
+struct sk_buff;
+
/**
* struct flow_dissector_key_control:
* @thoff: Transport header offset
@@ -32,7 +36,6 @@
/**
* struct flow_dissector_key_basic:
- * @thoff: Transport header offset
* @n_proto: Network header protocol (eg. IPv4/IPv6)
* @ip_proto: Transport header protocol (eg. TCP/UDP)
*/
@@ -47,19 +50,36 @@
};
struct flow_dissector_key_vlan {
- u16 vlan_id:12,
- vlan_dei:1,
- vlan_priority:3;
+ union {
+ struct {
+ u16 vlan_id:12,
+ vlan_dei:1,
+ vlan_priority:3;
+ };
+ __be16 vlan_tci;
+ };
__be16 vlan_tpid;
};
-struct flow_dissector_key_mpls {
+struct flow_dissector_mpls_lse {
u32 mpls_ttl:8,
mpls_bos:1,
mpls_tc:3,
mpls_label:20;
};
+#define FLOW_DIS_MPLS_MAX 7
+struct flow_dissector_key_mpls {
+ struct flow_dissector_mpls_lse ls[FLOW_DIS_MPLS_MAX]; /* Label Stack */
+ u8 used_lses; /* One bit set for each Label Stack Entry in use */
+};
+
+static inline void dissector_set_mpls_lse(struct flow_dissector_key_mpls *mpls,
+ int lse_index)
+{
+ mpls->used_lses |= 1 << lse_index;
+}
+
#define FLOW_DIS_TUN_OPTS_MAX 255
/**
* struct flow_dissector_key_enc_opts:
@@ -158,19 +178,16 @@
/**
* flow_dissector_key_icmp:
- * @ports: type and code of ICMP header
- * icmp: ICMP type (high) and code (low)
* type: ICMP type
* code: ICMP code
+ * id: session identifier
*/
struct flow_dissector_key_icmp {
- union {
- __be16 icmp;
- struct {
- u8 type;
- u8 code;
- };
+ struct {
+ u8 type;
+ u8 code;
};
+ u16 id;
};
/**
@@ -205,9 +222,11 @@
/**
* struct flow_dissector_key_meta:
* @ingress_ifindex: ingress ifindex
+ * @ingress_iftype: ingress interface type
*/
struct flow_dissector_key_meta {
int ingress_ifindex;
+ u16 ingress_iftype;
};
/**
@@ -224,6 +243,14 @@
u32 ct_labels[4];
};
+/**
+ * struct flow_dissector_key_hash:
+ * @hash: hash value
+ */
+struct flow_dissector_key_hash {
+ u32 hash;
+};
+
enum flow_dissector_key_id {
FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */
FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
@@ -252,6 +279,7 @@
FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */
FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */
FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */
+ FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */
FLOW_DISSECTOR_KEY_MAX,
};
@@ -285,6 +313,8 @@
struct flow_dissector_key_vlan cvlan;
struct flow_dissector_key_keyid keyid;
struct flow_dissector_key_ports ports;
+ struct flow_dissector_key_icmp icmp;
+ /* 'addrs' must be the last member */
struct flow_dissector_key_addrs addrs;
};
@@ -318,6 +348,9 @@
}
u32 flow_hash_from_keys(struct flow_keys *keys);
+void skb_flow_get_icmp_tci(const struct sk_buff *skb,
+ struct flow_dissector_key_icmp *key_icmp,
+ void *data, int thoff, int hlen);
static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector,
enum flow_dissector_key_id key_id)
@@ -347,4 +380,9 @@
memset(key_basic, 0, sizeof(*key_basic));
}
+#ifdef CONFIG_BPF_SYSCALL
+int flow_dissector_bpf_prog_attach_check(struct net *net,
+ struct bpf_prog *prog);
+#endif /* CONFIG_BPF_SYSCALL */
+
#endif
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index c6f7bd2..010d581 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -3,8 +3,8 @@
#include <linux/kernel.h>
#include <linux/list.h>
+#include <linux/netlink.h>
#include <net/flow_dissector.h>
-#include <linux/rhashtable.h>
struct flow_match {
struct flow_dissector *dissector;
@@ -68,6 +68,10 @@
struct flow_dissector_key_enc_opts *key, *mask;
};
+struct flow_match_ct {
+ struct flow_dissector_key_ct *key, *mask;
+};
+
struct flow_rule;
void flow_rule_match_meta(const struct flow_rule *rule,
@@ -110,6 +114,8 @@
struct flow_match_enc_keyid *out);
void flow_rule_match_enc_opts(const struct flow_rule *rule,
struct flow_match_enc_opts *out);
+void flow_rule_match_ct(const struct flow_rule *rule,
+ struct flow_match_ct *out);
enum flow_action_id {
FLOW_ACTION_ACCEPT = 0,
@@ -130,14 +136,17 @@
FLOW_ACTION_CSUM,
FLOW_ACTION_MARK,
FLOW_ACTION_PTYPE,
+ FLOW_ACTION_PRIORITY,
FLOW_ACTION_WAKE,
FLOW_ACTION_QUEUE,
FLOW_ACTION_SAMPLE,
FLOW_ACTION_POLICE,
FLOW_ACTION_CT,
+ FLOW_ACTION_CT_METADATA,
FLOW_ACTION_MPLS_PUSH,
FLOW_ACTION_MPLS_POP,
FLOW_ACTION_MPLS_MANGLE,
+ FLOW_ACTION_GATE,
NUM_FLOW_ACTIONS,
};
@@ -154,10 +163,40 @@
FLOW_ACT_MANGLE_HDR_TYPE_UDP,
};
+enum flow_action_hw_stats_bit {
+ FLOW_ACTION_HW_STATS_IMMEDIATE_BIT,
+ FLOW_ACTION_HW_STATS_DELAYED_BIT,
+ FLOW_ACTION_HW_STATS_DISABLED_BIT,
+
+ FLOW_ACTION_HW_STATS_NUM_BITS
+};
+
+enum flow_action_hw_stats {
+ FLOW_ACTION_HW_STATS_IMMEDIATE =
+ BIT(FLOW_ACTION_HW_STATS_IMMEDIATE_BIT),
+ FLOW_ACTION_HW_STATS_DELAYED = BIT(FLOW_ACTION_HW_STATS_DELAYED_BIT),
+ FLOW_ACTION_HW_STATS_ANY = FLOW_ACTION_HW_STATS_IMMEDIATE |
+ FLOW_ACTION_HW_STATS_DELAYED,
+ FLOW_ACTION_HW_STATS_DISABLED =
+ BIT(FLOW_ACTION_HW_STATS_DISABLED_BIT),
+ FLOW_ACTION_HW_STATS_DONT_CARE = BIT(FLOW_ACTION_HW_STATS_NUM_BITS) - 1,
+};
+
typedef void (*action_destr)(void *priv);
+struct flow_action_cookie {
+ u32 cookie_len;
+ u8 cookie[];
+};
+
+struct flow_action_cookie *flow_action_cookie_create(void *data,
+ unsigned int len,
+ gfp_t gfp);
+void flow_action_cookie_destroy(struct flow_action_cookie *cookie);
+
struct flow_action_entry {
enum flow_action_id id;
+ enum flow_action_hw_stats hw_stats;
action_destr destructor;
void *destructor_priv;
union {
@@ -168,7 +207,8 @@
__be16 proto;
u8 prio;
} vlan;
- struct { /* FLOW_ACTION_PACKET_EDIT */
+ struct { /* FLOW_ACTION_MANGLE */
+ /* FLOW_ACTION_ADD */
enum flow_action_mangle_base htype;
u32 offset;
u32 mask;
@@ -178,6 +218,7 @@
u32 csum_flags; /* FLOW_ACTION_CSUM */
u32 mark; /* FLOW_ACTION_MARK */
u16 ptype; /* FLOW_ACTION_PTYPE */
+ u32 priority; /* FLOW_ACTION_PRIORITY */
struct { /* FLOW_ACTION_QUEUE */
u32 ctx;
u32 index;
@@ -190,13 +231,21 @@
bool truncate;
} sample;
struct { /* FLOW_ACTION_POLICE */
- s64 burst;
+ u32 index;
+ u32 burst;
u64 rate_bytes_ps;
+ u32 mtu;
} police;
struct { /* FLOW_ACTION_CT */
int action;
u16 zone;
+ struct nf_flowtable *flow_table;
} ct;
+ struct {
+ unsigned long cookie;
+ u32 mark;
+ u32 labels[4];
+ } ct_metadata;
struct { /* FLOW_ACTION_MPLS_PUSH */
u32 label;
__be16 proto;
@@ -213,12 +262,22 @@
u8 bos;
u8 ttl;
} mpls_mangle;
+ struct {
+ u32 index;
+ s32 prio;
+ u64 basetime;
+ u64 cycletime;
+ u64 cycletimeext;
+ u32 num_entries;
+ struct action_gate_entry *entries;
+ } gate;
};
+ struct flow_action_cookie *cookie; /* user defined action cookie */
};
struct flow_action {
unsigned int num_entries;
- struct flow_action_entry entries[0];
+ struct flow_action_entry entries[];
};
static inline bool flow_action_has_entries(const struct flow_action *action)
@@ -238,7 +297,82 @@
}
#define flow_action_for_each(__i, __act, __actions) \
- for (__i = 0, __act = &(__actions)->entries[0]; __i < (__actions)->num_entries; __act = &(__actions)->entries[++__i])
+ for (__i = 0, __act = &(__actions)->entries[0]; \
+ __i < (__actions)->num_entries; \
+ __act = &(__actions)->entries[++__i])
+
+static inline bool
+flow_action_mixed_hw_stats_check(const struct flow_action *action,
+ struct netlink_ext_ack *extack)
+{
+ const struct flow_action_entry *action_entry;
+ u8 last_hw_stats;
+ int i;
+
+ if (flow_offload_has_one_action(action))
+ return true;
+
+ flow_action_for_each(i, action_entry, action) {
+ if (i && action_entry->hw_stats != last_hw_stats) {
+ NL_SET_ERR_MSG_MOD(extack, "Mixing HW stats types for actions is not supported");
+ return false;
+ }
+ last_hw_stats = action_entry->hw_stats;
+ }
+ return true;
+}
+
+static inline const struct flow_action_entry *
+flow_action_first_entry_get(const struct flow_action *action)
+{
+ WARN_ON(!flow_action_has_entries(action));
+ return &action->entries[0];
+}
+
+static inline bool
+__flow_action_hw_stats_check(const struct flow_action *action,
+ struct netlink_ext_ack *extack,
+ bool check_allow_bit,
+ enum flow_action_hw_stats_bit allow_bit)
+{
+ const struct flow_action_entry *action_entry;
+
+ if (!flow_action_has_entries(action))
+ return true;
+ if (!flow_action_mixed_hw_stats_check(action, extack))
+ return false;
+
+ action_entry = flow_action_first_entry_get(action);
+
+ /* Zero is not a legal value for hw_stats, catch anyone passing it */
+ WARN_ON_ONCE(!action_entry->hw_stats);
+
+ if (!check_allow_bit &&
+ ~action_entry->hw_stats & FLOW_ACTION_HW_STATS_ANY) {
+ NL_SET_ERR_MSG_MOD(extack, "Driver supports only default HW stats type \"any\"");
+ return false;
+ } else if (check_allow_bit &&
+ !(action_entry->hw_stats & BIT(allow_bit))) {
+ NL_SET_ERR_MSG_MOD(extack, "Driver does not support selected HW stats type");
+ return false;
+ }
+ return true;
+}
+
+static inline bool
+flow_action_hw_stats_check(const struct flow_action *action,
+ struct netlink_ext_ack *extack,
+ enum flow_action_hw_stats_bit allow_bit)
+{
+ return __flow_action_hw_stats_check(action, extack, true, allow_bit);
+}
+
+static inline bool
+flow_action_basic_hw_stats_check(const struct flow_action *action,
+ struct netlink_ext_ack *extack)
+{
+ return __flow_action_hw_stats_check(action, extack, false, 0);
+}
struct flow_rule {
struct flow_match match;
@@ -256,15 +390,28 @@
struct flow_stats {
u64 pkts;
u64 bytes;
+ u64 drops;
u64 lastused;
+ enum flow_action_hw_stats used_hw_stats;
+ bool used_hw_stats_valid;
};
static inline void flow_stats_update(struct flow_stats *flow_stats,
- u64 bytes, u64 pkts, u64 lastused)
+ u64 bytes, u64 pkts,
+ u64 drops, u64 lastused,
+ enum flow_action_hw_stats used_hw_stats)
{
flow_stats->pkts += pkts;
flow_stats->bytes += bytes;
+ flow_stats->drops += drops;
flow_stats->lastused = max_t(u64, flow_stats->lastused, lastused);
+
+ /* The driver should pass value with a maximum of one bit set.
+ * Passing FLOW_ACTION_HW_STATS_ANY is invalid.
+ */
+ WARN_ON(used_hw_stats == FLOW_ACTION_HW_STATS_ANY);
+ flow_stats->used_hw_stats |= used_hw_stats;
+ flow_stats->used_hw_stats_valid = true;
}
enum flow_block_command {
@@ -276,6 +423,8 @@
FLOW_BLOCK_BINDER_TYPE_UNSPEC,
FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS,
+ FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP,
+ FLOW_BLOCK_BINDER_TYPE_RED_MARK,
};
struct flow_block {
@@ -294,12 +443,26 @@
struct list_head cb_list;
struct list_head *driver_block_list;
struct netlink_ext_ack *extack;
+ struct Qdisc *sch;
+ struct list_head *cb_list_head;
};
enum tc_setup_type;
typedef int flow_setup_cb_t(enum tc_setup_type type, void *type_data,
void *cb_priv);
+struct flow_block_cb;
+
+struct flow_block_indr {
+ struct list_head list;
+ struct net_device *dev;
+ struct Qdisc *sch;
+ enum flow_block_binder_type binder_type;
+ void *data;
+ void *cb_priv;
+ void (*cleanup)(struct flow_block_cb *block_cb);
+};
+
struct flow_block_cb {
struct list_head driver_list;
struct list_head list;
@@ -307,12 +470,21 @@
void *cb_ident;
void *cb_priv;
void (*release)(void *cb_priv);
+ struct flow_block_indr indr;
unsigned int refcnt;
};
struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb,
void *cb_ident, void *cb_priv,
void (*release)(void *cb_priv));
+struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb,
+ void *cb_ident, void *cb_priv,
+ void (*release)(void *cb_priv),
+ struct flow_block_offload *bo,
+ struct net_device *dev,
+ struct Qdisc *sch, void *data,
+ void *indr_cb_priv,
+ void (*cleanup)(struct flow_block_cb *block_cb));
void flow_block_cb_free(struct flow_block_cb *block_cb);
struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block,
@@ -334,6 +506,13 @@
list_move(&block_cb->list, &offload->cb_list);
}
+static inline void flow_indr_block_cb_remove(struct flow_block_cb *block_cb,
+ struct flow_block_offload *offload)
+{
+ list_del(&block_cb->indr.list);
+ list_move(&block_cb->list, &offload->cb_list);
+}
+
bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident,
struct list_head *driver_block_list);
@@ -377,39 +556,17 @@
INIT_LIST_HEAD(&flow_block->cb_list);
}
-typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv,
- enum tc_setup_type type, void *type_data);
+typedef int flow_indr_block_bind_cb_t(struct net_device *dev, struct Qdisc *sch, void *cb_priv,
+ enum tc_setup_type type, void *type_data,
+ void *data,
+ void (*cleanup)(struct flow_block_cb *block_cb));
-typedef void flow_indr_block_cmd_t(struct net_device *dev,
- flow_indr_block_bind_cb_t *cb, void *cb_priv,
- enum flow_block_command command);
-
-struct flow_indr_block_entry {
- flow_indr_block_cmd_t *cb;
- struct list_head list;
-};
-
-void flow_indr_add_block_cb(struct flow_indr_block_entry *entry);
-
-void flow_indr_del_block_cb(struct flow_indr_block_entry *entry);
-
-int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv,
- flow_indr_block_bind_cb_t *cb,
- void *cb_ident);
-
-void __flow_indr_block_cb_unregister(struct net_device *dev,
- flow_indr_block_bind_cb_t *cb,
- void *cb_ident);
-
-int flow_indr_block_cb_register(struct net_device *dev, void *cb_priv,
- flow_indr_block_bind_cb_t *cb, void *cb_ident);
-
-void flow_indr_block_cb_unregister(struct net_device *dev,
- flow_indr_block_bind_cb_t *cb,
- void *cb_ident);
-
-void flow_indr_block_call(struct net_device *dev,
- struct flow_block_offload *bo,
- enum flow_block_command command);
+int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv);
+void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv,
+ void (*release)(void *cb_priv));
+int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch,
+ enum tc_setup_type type, void *data,
+ struct flow_block_offload *bo,
+ void (*cleanup)(struct flow_block_cb *block_cb));
#endif /* _NET_FLOW_OFFLOAD_H */
diff --git a/include/net/fq.h b/include/net/fq.h
index 2ad85e6..e39f3f8 100644
--- a/include/net/fq.h
+++ b/include/net/fq.h
@@ -69,7 +69,6 @@
struct list_head backlogs;
spinlock_t lock;
u32 flows_cnt;
- siphash_key_t perturbation;
u32 limit;
u32 memory_limit;
u32 memory_usage;
diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h
index 38a9a3d..e73d74d 100644
--- a/include/net/fq_impl.h
+++ b/include/net/fq_impl.h
@@ -108,7 +108,7 @@
static u32 fq_flow_idx(struct fq *fq, struct sk_buff *skb)
{
- u32 hash = skb_get_hash_perturb(skb, &fq->perturbation);
+ u32 hash = skb_get_hash(skb);
return reciprocal_scale(hash, fq->flows_cnt);
}
@@ -308,7 +308,6 @@
INIT_LIST_HEAD(&fq->backlogs);
spin_lock_init(&fq->lock);
fq->flows_cnt = max_t(u32, flows_cnt, 1);
- get_random_bytes(&fq->perturbation, sizeof(fq->perturbation));
fq->quantum = 300;
fq->limit = 8192;
fq->memory_limit = 16 << 20; /* 16 MBytes */
diff --git a/include/net/garp.h b/include/net/garp.h
index c41833b..4d9a0c6 100644
--- a/include/net/garp.h
+++ b/include/net/garp.h
@@ -37,7 +37,7 @@
static inline struct garp_skb_cb *garp_cb(struct sk_buff *skb)
{
BUILD_BUG_ON(sizeof(struct garp_skb_cb) >
- FIELD_SIZEOF(struct sk_buff, cb));
+ sizeof_field(struct sk_buff, cb));
return (struct garp_skb_cb *)skb->cb;
}
diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index ca23860..1424e02 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -7,6 +7,12 @@
#include <linux/rtnetlink.h>
#include <linux/pkt_sched.h>
+/* Note: this used to be in include/uapi/linux/gen_stats.h */
+struct gnet_stats_basic_packed {
+ __u64 bytes;
+ __u64 packets;
+};
+
struct gnet_stats_basic_cpu {
struct gnet_stats_basic_packed bstats;
struct u64_stats_sync syncp;
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 2d9e67a..e55ec15 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -35,13 +35,14 @@
* do additional, common, filtering and return an error
* @post_doit: called after an operation's doit callback, it may
* undo operations done by pre_doit, for example release locks
- * @attrbuf: buffer to store parsed attributes (private)
* @mcgrps: multicast groups used by this family
* @n_mcgrps: number of multicast groups
* @mcgrp_offset: starting number of multicast group IDs in this family
* (private)
* @ops: the operations supported by this family
* @n_ops: number of operations supported by this family
+ * @small_ops: the small-struct operations supported by this family
+ * @n_small_ops: number of small-struct operations supported by this family
*/
struct genl_family {
int id; /* private */
@@ -49,8 +50,12 @@
char name[GENL_NAMSIZ];
unsigned int version;
unsigned int maxattr;
- bool netnsok;
- bool parallel_ops;
+ unsigned int mcgrp_offset; /* private */
+ u8 netnsok:1;
+ u8 parallel_ops:1;
+ u8 n_ops;
+ u8 n_small_ops;
+ u8 n_mcgrps;
const struct nla_policy *policy;
int (*pre_doit)(const struct genl_ops *ops,
struct sk_buff *skb,
@@ -58,17 +63,12 @@
void (*post_doit)(const struct genl_ops *ops,
struct sk_buff *skb,
struct genl_info *info);
- struct nlattr ** attrbuf; /* private */
const struct genl_ops * ops;
+ const struct genl_small_ops *small_ops;
const struct genl_multicast_group *mcgrps;
- unsigned int n_ops;
- unsigned int n_mcgrps;
- unsigned int mcgrp_offset; /* private */
struct module *module;
};
-struct nlattr **genl_family_attrbuf(const struct genl_family *family);
-
/**
* struct genl_info - receiving information
* @snd_seq: sending sequence number
@@ -105,14 +105,6 @@
#define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg)
-static inline int genl_err_attr(struct genl_info *info, int err,
- const struct nlattr *attr)
-{
- info->extack->bad_attr = attr;
-
- return err;
-}
-
enum genl_validate_flags {
GENL_DONT_VALIDATE_STRICT = BIT(0),
GENL_DONT_VALIDATE_DUMP = BIT(1),
@@ -120,10 +112,34 @@
};
/**
+ * struct genl_small_ops - generic netlink operations (small version)
+ * @cmd: command identifier
+ * @internal_flags: flags used by the family
+ * @flags: flags
+ * @validate: validation flags from enum genl_validate_flags
+ * @doit: standard command callback
+ * @dumpit: callback for dumpers
+ *
+ * This is a cut-down version of struct genl_ops for users who don't need
+ * most of the ancillary infra and want to save space.
+ */
+struct genl_small_ops {
+ int (*doit)(struct sk_buff *skb, struct genl_info *info);
+ int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb);
+ u8 cmd;
+ u8 internal_flags;
+ u8 flags;
+ u8 validate;
+};
+
+/**
* struct genl_ops - generic netlink operations
* @cmd: command identifier
* @internal_flags: flags used by the family
* @flags: flags
+ * @maxattr: maximum number of attributes supported
+ * @policy: netlink policy (takes precedence over family policy)
+ * @validate: validation flags from enum genl_validate_flags
* @doit: standard command callback
* @start: start callback for dumps
* @dumpit: callback for dumpers
@@ -136,12 +152,32 @@
int (*dumpit)(struct sk_buff *skb,
struct netlink_callback *cb);
int (*done)(struct netlink_callback *cb);
+ const struct nla_policy *policy;
+ unsigned int maxattr;
u8 cmd;
u8 internal_flags;
u8 flags;
u8 validate;
};
+/**
+ * struct genl_info - info that is available during dumpit op call
+ * @family: generic netlink family - for internal genl code usage
+ * @ops: generic netlink ops - for internal genl code usage
+ * @attrs: netlink attributes
+ */
+struct genl_dumpit_info {
+ const struct genl_family *family;
+ struct genl_ops op;
+ struct nlattr **attrs;
+};
+
+static inline const struct genl_dumpit_info *
+genl_dumpit_info(struct netlink_callback *cb)
+{
+ return cb->data;
+}
+
int genl_register_family(struct genl_family *family);
int genl_unregister_family(const struct genl_family *family);
void genl_notify(const struct genl_family *family, struct sk_buff *skb,
diff --git a/include/net/gue.h b/include/net/gue.h
index 3a6595b..e42402f 100644
--- a/include/net/gue.h
+++ b/include/net/gue.h
@@ -21,7 +21,7 @@
* | |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
- * C bit indicates contol message when set, data message when unset.
+ * C bit indicates control message when set, data message when unset.
* For a control message, proto/ctype is interpreted as a type of
* control message. For data messages, proto/ctype is the IP protocol
* of the next header.
diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index 459d355..19c00d1 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -117,6 +117,7 @@
IEEE80211_RADIOTAP_F_TX_CTS = 0x0002,
IEEE80211_RADIOTAP_F_TX_RTS = 0x0004,
IEEE80211_RADIOTAP_F_TX_NOACK = 0x0008,
+ IEEE80211_RADIOTAP_F_TX_NOSEQNO = 0x0010,
};
/* for IEEE80211_RADIOTAP_MCS "have" flags */
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index a01981d..8bf5906 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -78,7 +78,7 @@
struct ip6_sf_socklist {
unsigned int sl_max;
unsigned int sl_count;
- struct in6_addr sl_addr[0];
+ struct in6_addr sl_addr[];
};
#define IP6_SFLSIZE(count) (sizeof(struct ip6_sf_socklist) + \
@@ -190,7 +190,6 @@
int dead;
u32 desync_factor;
- u8 rndid[8];
struct list_head tempaddr_list;
struct in6_addr token;
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index fe96bf2..81b9659 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -85,9 +85,8 @@
int iif, int sdif,
bool *refcounted)
{
- struct sock *sk = skb_steal_sock(skb);
+ struct sock *sk = skb_steal_sock(skb, refcounted);
- *refcounted = true;
if (sk)
return sk;
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index ae2ba89..cb28188 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -35,8 +35,14 @@
int inet_listen(struct socket *sock, int backlog);
void inet_sock_destruct(struct sock *sk);
int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
+/* Don't allocate port at this moment, defer to connect. */
+#define BIND_FORCE_ADDRESS_NO_PORT (1 << 0)
+/* Grab and release socket lock. */
+#define BIND_WITH_LOCK (1 << 1)
+/* Called from BPF program. */
+#define BIND_FROM_BPF (1 << 2)
int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
- bool force_bind_address_no_port, bool with_lock);
+ u32 flags);
int inet_getname(struct socket *sock, struct sockaddr *uaddr,
int peer);
int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 13792c0..0b1864a 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -16,6 +16,7 @@
#include <linux/timer.h>
#include <linux/poll.h>
#include <linux/kernel.h>
+#include <linux/sockptr.h>
#include <net/inet_sock.h>
#include <net/request_sock.h>
@@ -45,17 +46,9 @@
u16 net_frag_header_len;
u16 sockaddr_len;
int (*setsockopt)(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen);
+ sockptr_t optval, unsigned int optlen);
int (*getsockopt)(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
-#ifdef CONFIG_COMPAT
- int (*compat_setsockopt)(struct sock *sk,
- int level, int optname,
- char __user *optval, unsigned int optlen);
- int (*compat_getsockopt)(struct sock *sk,
- int level, int optname,
- char __user *optval, int __user *optlen);
-#endif
void (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
void (*mtu_reduced)(struct sock *sk);
};
@@ -95,6 +88,8 @@
struct timer_list icsk_retransmit_timer;
struct timer_list icsk_delack_timer;
__u32 icsk_rto;
+ __u32 icsk_rto_min;
+ __u32 icsk_delack_max;
__u32 icsk_pmtu_cookie;
const struct tcp_congestion_ops *icsk_ca_ops;
const struct inet_connection_sock_af_ops *icsk_af_ops;
@@ -103,7 +98,8 @@
void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
struct hlist_node icsk_listen_portaddr_node;
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
- __u8 icsk_ca_state:6,
+ __u8 icsk_ca_state:5,
+ icsk_ca_initialized:1,
icsk_ca_setsockopt:1,
icsk_ca_dst_locked:1;
__u8 icsk_retransmits;
@@ -116,7 +112,7 @@
__u8 pending; /* ACK is pending */
__u8 quick; /* Scheduled number of quick acks */
__u8 pingpong; /* The session is interactive */
- __u8 blocked; /* Delayed ACK was blocked by socket lock */
+ __u8 retry; /* Number of attempts */
__u32 ato; /* Predicted tick of soft clock */
unsigned long timeout; /* Currently scheduled timeout */
__u32 lrcvtime; /* timestamp of last received data packet */
@@ -205,7 +201,8 @@
sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
#endif
} else if (what == ICSK_TIME_DACK) {
- icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0;
+ icsk->icsk_ack.pending = 0;
+ icsk->icsk_ack.retry = 0;
#ifdef INET_CSK_CLEAR_TIMERS
sk_stop_timer(sk, &icsk->icsk_delack_timer);
#endif
@@ -290,6 +287,13 @@
bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req);
+static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk)
+{
+ /* The below has to be done to allow calling inet_csk_destroy_sock */
+ sock_set_flag(sk, SOCK_DEAD);
+ this_cpu_inc(*sk->sk_prot->orphan_count);
+}
+
void inet_csk_destroy_sock(struct sock *sk);
void inet_csk_prepare_forced_close(struct sock *sk);
@@ -307,11 +311,6 @@
void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
-int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen);
-int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen);
-
/* update the fast reuse flag when adding a socket */
void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
struct sock *sk);
@@ -342,4 +341,10 @@
if (icsk->icsk_ack.pingpong < U8_MAX)
icsk->icsk_ack.pingpong++;
}
+
+static inline bool inet_csk_has_ulp(struct sock *sk)
+{
+ return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops;
+}
+
#endif /* _INET_CONNECTION_SOCK_H */
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index bac79e8..4cbd413 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -116,8 +116,15 @@
static inline void fqdir_pre_exit(struct fqdir *fqdir)
{
- fqdir->high_thresh = 0; /* prevent creation of new frags */
- fqdir->dead = true;
+ /* Prevent creation of new frags.
+ * Pairs with READ_ONCE() in inet_frag_find().
+ */
+ WRITE_ONCE(fqdir->high_thresh, 0);
+
+ /* Pairs with READ_ONCE() in inet_frag_kill(), ip_expire()
+ * and ip6frag_expire_frag_queue().
+ */
+ WRITE_ONCE(fqdir->dead, true);
}
void fqdir_exit(struct fqdir *fqdir);
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 59802eb..ca6a3ea 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -247,8 +247,9 @@
unsigned long high_limit);
int inet_hashinfo2_init_mod(struct inet_hashinfo *h);
-bool inet_ehash_insert(struct sock *sk, struct sock *osk);
-bool inet_ehash_nolisten(struct sock *sk, struct sock *osk);
+bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk);
+bool inet_ehash_nolisten(struct sock *sk, struct sock *osk,
+ bool *found_dup_sk);
int __inet_hash(struct sock *sk, struct sock *osk);
int inet_hash(struct sock *sk);
void inet_unhash(struct sock *sk);
@@ -385,10 +386,9 @@
const int sdif,
bool *refcounted)
{
- struct sock *sk = skb_steal_sock(skb);
+ struct sock *sk = skb_steal_sock(skb, refcounted);
const struct iphdr *iph = ip_hdr(skb);
- *refcounted = true;
if (sk)
return sk;
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 34c4436..89163ef 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -52,7 +52,7 @@
unsigned char router_alert;
unsigned char cipso;
unsigned char __pad2;
- unsigned char __data[0];
+ unsigned char __data[];
};
struct ip_options_rcu {
@@ -225,6 +225,7 @@
mc_all:1,
nodefrag:1;
__u8 bind_address_no_port:1,
+ recverr_rfc4884:1,
defer_connect:1; /* Indicates that fastopen_connect is set
* and cookie exists so we defer connect
* until first data frame is written
@@ -295,13 +296,6 @@
memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1,
sk_from->sk_prot->obj_size - ancestor_size);
}
-#if !(IS_ENABLED(CONFIG_IPV6))
-static inline void inet_sk_copy_descendant(struct sock *sk_to,
- const struct sock *sk_from)
-{
- __inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock));
-}
-#endif
int inet_sk_rebuild_header(struct sock *sk);
diff --git a/include/net/ip.h b/include/net/ip.h
index 52abfc0..de2dc22 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -23,6 +23,7 @@
#include <linux/in.h>
#include <linux/skbuff.h>
#include <linux/jhash.h>
+#include <linux/sockptr.h>
#include <net/inet_sock.h>
#include <net/route.h>
@@ -151,7 +152,7 @@
int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
__be32 saddr, __be32 daddr,
- struct ip_options_rcu *opt);
+ struct ip_options_rcu *opt, u8 tos);
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
struct net_device *orig_dev);
void ip_list_rcv(struct list_head *head, struct packet_type *pt,
@@ -232,11 +233,7 @@
struct ipcm_cookie *ipc, struct rtable **rtp,
struct inet_cork *cork, unsigned int flags);
-static inline int ip_queue_xmit(struct sock *sk, struct sk_buff *skb,
- struct flowi *fl)
-{
- return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos);
-}
+int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
{
@@ -340,10 +337,10 @@
void inet_get_local_port_range(struct net *net, int *low, int *high);
#ifdef CONFIG_SYSCTL
-static inline int inet_is_local_reserved_port(struct net *net, int port)
+static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
{
if (!net->ipv4.sysctl_local_reserved_ports)
- return 0;
+ return false;
return test_bit(port, net->ipv4.sysctl_local_reserved_ports);
}
@@ -352,20 +349,20 @@
return strcmp(name, "default") != 0 && strcmp(name, "all") != 0;
}
-static inline int inet_prot_sock(struct net *net)
+static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port)
{
- return net->ipv4.sysctl_ip_prot_sock;
+ return port < net->ipv4.sysctl_ip_prot_sock;
}
#else
-static inline int inet_is_local_reserved_port(struct net *net, int port)
+static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
{
- return 0;
+ return false;
}
-static inline int inet_prot_sock(struct net *net)
+static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port)
{
- return PROT_SOCK;
+ return port < PROT_SOCK;
}
#endif
@@ -509,19 +506,18 @@
{
struct iphdr *iph = ip_hdr(skb);
+ /* We had many attacks based on IPID, use the private
+ * generator as much as we can.
+ */
+ if (sk && inet_sk(sk)->inet_daddr) {
+ iph->id = htons(inet_sk(sk)->inet_id);
+ inet_sk(sk)->inet_id += segs;
+ return;
+ }
if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) {
- /* This is only to work around buggy Windows95/2000
- * VJ compression implementations. If the ID field
- * does not change, they drop every other packet in
- * a TCP stream using header compression.
- */
- if (sk && inet_sk(sk)->inet_daddr) {
- iph->id = htons(inet_sk(sk)->inet_id);
- inet_sk(sk)->inet_id += segs;
- } else {
- iph->id = 0;
- }
+ iph->id = 0;
} else {
+ /* Unfortunately we need the big hammer to get a suitable IPID */
__ip_select_ident(net, iph, segs);
}
}
@@ -721,9 +717,7 @@
int ip_options_compile(struct net *net, struct ip_options *opt,
struct sk_buff *skb);
int ip_options_get(struct net *net, struct ip_options_rcu **optp,
- unsigned char *data, int optlen);
-int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
- unsigned char __user *data, int optlen);
+ sockptr_t data, int optlen);
void ip_options_undo(struct ip_options *opt);
void ip_forward_options(struct sk_buff *skb);
int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
@@ -737,14 +731,10 @@
struct sk_buff *skb, int tlen, int offset);
int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
struct ipcm_cookie *ipc, bool allow_ipv6);
-int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
+int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen);
int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
int __user *optlen);
-int compat_ip_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen);
-int compat_ip_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen);
int ip_ra_control(struct sock *sk, unsigned char on,
void (*destructor)(struct sock *));
@@ -775,4 +765,10 @@
return likely(mtu >= IPV4_MIN_MTU);
}
+void ip_sock_set_freebind(struct sock *sk);
+int ip_sock_set_mtu_discover(struct sock *sk, int val);
+void ip_sock_set_pktinfo(struct sock *sk);
+void ip_sock_set_recverr(struct sock *sk);
+void ip_sock_set_tos(struct sock *sk, int val);
+
#endif /* _IP_H */
diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h
index 7bec95d..b3f4eaa 100644
--- a/include/net/ip6_checksum.h
+++ b/include/net/ip6_checksum.h
@@ -76,14 +76,14 @@
}
}
-#if IS_ENABLED(CONFIG_IPV6)
-static inline void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
+static inline void tcp_v6_gso_csum_prep(struct sk_buff *skb)
{
- struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ struct tcphdr *th = tcp_hdr(skb);
- __tcp_v6_send_check(skb, &np->saddr, &sk->sk_v6_daddr);
+ ipv6h->payload_len = 0;
+ th->check = ~tcp_v6_check(0, &ipv6h->saddr, &ipv6h->daddr, 0);
}
-#endif
static inline __sum16 udp_v6_check(int len,
const struct in6_addr *saddr,
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index bd0f159..95d93ec 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -19,6 +19,7 @@
#include <net/netlink.h>
#include <net/inetpeer.h>
#include <net/fib_notifier.h>
+#include <linux/indirect_call_wrapper.h>
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
#define FIB6_TABLE_HASHSZ 256
@@ -65,6 +66,7 @@
struct nl_info fc_nlinfo;
struct nlattr *fc_encap;
u16 fc_encap_type;
+ bool fc_is_fdb;
};
struct fib6_node {
@@ -90,7 +92,32 @@
#ifndef CONFIG_IPV6_SUBTREES
#define FIB6_SUBTREE(fn) NULL
+
+static inline bool fib6_routes_require_src(const struct net *net)
+{
+ return false;
+}
+
+static inline void fib6_routes_require_src_inc(struct net *net) {}
+static inline void fib6_routes_require_src_dec(struct net *net) {}
+
#else
+
+static inline bool fib6_routes_require_src(const struct net *net)
+{
+ return net->ipv6.fib6_routes_require_src > 0;
+}
+
+static inline void fib6_routes_require_src_inc(struct net *net)
+{
+ net->ipv6.fib6_routes_require_src++;
+}
+
+static inline void fib6_routes_require_src_dec(struct net *net)
+{
+ net->ipv6.fib6_routes_require_src--;
+}
+
#define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1))
#endif
@@ -139,7 +166,7 @@
struct fib6_node __rcu *fib6_node;
/* Multipath routes:
- * siblings is a list of fib6_info that have the the same metric/weight,
+ * siblings is a list of fib6_info that have the same metric/weight,
* destination, but not the same gateway. nsiblings is just a cache
* to speed up lookup.
*/
@@ -165,13 +192,14 @@
u8 should_flush:1,
dst_nocount:1,
dst_nopolicy:1,
- dst_host:1,
fib6_destroying:1,
- unused:3;
+ offload:1,
+ trap:1,
+ unused:2;
struct rcu_head rcu;
struct nexthop *nh;
- struct fib6_nh fib6_nh[0];
+ struct fib6_nh fib6_nh[];
};
struct rt6_info {
@@ -213,6 +241,11 @@
return ((struct rt6_info *)dst)->rt6i_idev;
}
+static inline bool fib6_requires_src(const struct fib6_info *rt)
+{
+ return rt->fib6_src.plen > 0;
+}
+
static inline void fib6_clean_expires(struct fib6_info *f6i)
{
f6i->fib6_flags &= ~RTF_EXPIRES;
@@ -247,7 +280,7 @@
fn = rcu_dereference(f6i->fib6_node);
if (fn) {
- *cookie = fn->fn_sernum;
+ *cookie = READ_ONCE(fn->fn_sernum);
/* pairs with smp_wmb() in fib6_update_sernum_upto_root() */
smp_rmb();
status = true;
@@ -303,6 +336,13 @@
call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
}
+static inline void fib6_info_hw_flags_set(struct fib6_info *f6i, bool offload,
+ bool trap)
+{
+ f6i->offload = offload;
+ f6i->trap = trap;
+}
+
enum fib6_walk_state {
#ifdef CONFIG_IPV6_SUBTREES
FWS_S,
@@ -451,6 +491,7 @@
struct fib6_config *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack);
void fib6_nh_release(struct fib6_nh *fib6_nh);
+void fib6_nh_release_dsts(struct fib6_nh *fib6_nh);
int call_fib6_entry_notifiers(struct net *net,
enum fib_event_type event_type,
@@ -461,6 +502,7 @@
struct fib6_info *rt,
unsigned int nsiblings,
struct netlink_ext_ack *extack);
+int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt);
void fib6_rt_update(struct net *net, struct fib6_info *rt,
struct nl_info *info);
void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
@@ -482,7 +524,7 @@
extern const struct seq_operations ipv6_route_seq_ops;
-int call_fib6_notifier(struct notifier_block *nb, struct net *net,
+int call_fib6_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
struct fib_notifier_info *info);
int call_fib6_notifiers(struct net *net, enum fib_event_type event_type,
@@ -492,7 +534,8 @@
void __net_exit fib6_notifier_exit(struct net *net);
unsigned int fib6_tables_seq_read(struct net *net);
-int fib6_tables_dump(struct net *net, struct notifier_block *nb);
+int fib6_tables_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack);
void fib6_update_sernum(struct net *net, struct fib6_info *rt);
void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt);
@@ -504,11 +547,59 @@
return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric));
}
+#if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL)
+struct bpf_iter__ipv6_route {
+ __bpf_md_ptr(struct bpf_iter_meta *, meta);
+ __bpf_md_ptr(struct fib6_info *, rt);
+};
+#endif
+
+INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_output(struct net *net,
+ struct fib6_table *table,
+ struct flowi6 *fl6,
+ const struct sk_buff *skb,
+ int flags));
+INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_input(struct net *net,
+ struct fib6_table *table,
+ struct flowi6 *fl6,
+ const struct sk_buff *skb,
+ int flags));
+INDIRECT_CALLABLE_DECLARE(struct rt6_info *__ip6_route_redirect(struct net *net,
+ struct fib6_table *table,
+ struct flowi6 *fl6,
+ const struct sk_buff *skb,
+ int flags));
+INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_lookup(struct net *net,
+ struct fib6_table *table,
+ struct flowi6 *fl6,
+ const struct sk_buff *skb,
+ int flags));
+static inline struct rt6_info *pol_lookup_func(pol_lookup_t lookup,
+ struct net *net,
+ struct fib6_table *table,
+ struct flowi6 *fl6,
+ const struct sk_buff *skb,
+ int flags)
+{
+ return INDIRECT_CALL_4(lookup,
+ ip6_pol_route_output,
+ ip6_pol_route_input,
+ ip6_pol_route_lookup,
+ __ip6_route_redirect,
+ net, table, fl6, skb, flags);
+}
+
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+static inline bool fib6_has_custom_rules(const struct net *net)
+{
+ return net->ipv6.fib6_has_custom_rules;
+}
+
int fib6_rules_init(void);
void fib6_rules_cleanup(void);
bool fib6_rule_default(const struct fib_rule *rule);
-int fib6_rules_dump(struct net *net, struct notifier_block *nb);
+int fib6_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack);
unsigned int fib6_rules_seq_read(struct net *net);
static inline bool fib6_rules_early_flow_dissect(struct net *net,
@@ -529,6 +620,10 @@
return true;
}
#else
+static inline bool fib6_has_custom_rules(const struct net *net)
+{
+ return false;
+}
static inline int fib6_rules_init(void)
{
return 0;
@@ -541,7 +636,8 @@
{
return true;
}
-static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb)
+static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
return 0;
}
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 2c739fc..44969d0 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -16,7 +16,7 @@
reserved_h:3;
#endif
__be32 lifetime;
- __u8 prefix[0]; /* 0,8 or 16 */
+ __u8 prefix[]; /* 0,8 or 16 */
};
#include <net/addrconf.h>
@@ -118,12 +118,13 @@
int ip6_route_init(void);
void ip6_route_cleanup(void);
-int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg);
+int ipv6_route_ioctl(struct net *net, unsigned int cmd,
+ struct in6_rtmsg *rtmsg);
int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack);
int ip6_ins_rt(struct net *net, struct fib6_info *f6i);
-int ip6_del_rt(struct net *net, struct fib6_info *f6i);
+int ip6_del_rt(struct net *net, struct fib6_info *f6i, bool skip_notify);
void rt6_flush_exceptions(struct fib6_info *f6i);
void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args,
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index ffbae76..088f257 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -153,7 +153,7 @@
bool nh_updated;
struct nexthop *nh;
struct rcu_head rcu;
- struct fib_nh fib_nh[0];
+ struct fib_nh fib_nh[];
};
@@ -204,6 +204,18 @@
#define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev)
#define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif)
+struct fib_rt_info {
+ struct fib_info *fi;
+ u32 tb_id;
+ __be32 dst;
+ int dst_len;
+ u8 tos;
+ u8 type;
+ u8 offload:1,
+ trap:1,
+ unused:6;
+};
+
struct fib_entry_notifier_info {
struct fib_notifier_info info; /* must be first */
u32 dst;
@@ -219,7 +231,7 @@
struct fib_nh *fib_nh;
};
-int call_fib4_notifier(struct notifier_block *nb, struct net *net,
+int call_fib4_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
struct fib_notifier_info *info);
int call_fib4_notifiers(struct net *net, enum fib_event_type event_type,
@@ -229,7 +241,8 @@
void __net_exit fib4_notifier_exit(struct net *net);
void fib_info_notify_update(struct net *net, struct nl_info *info);
-void fib_notify(struct net *net, struct notifier_block *nb);
+int fib_notify(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack);
struct fib_table {
struct hlist_node tb_hlist;
@@ -237,7 +250,7 @@
int tb_num_default;
struct rcu_head rcu;
unsigned long *tb_data;
- unsigned long __data[0];
+ unsigned long __data[];
};
struct fib_dump_filter {
@@ -309,12 +322,18 @@
return err;
}
+static inline bool fib4_has_custom_rules(const struct net *net)
+{
+ return false;
+}
+
static inline bool fib4_rule_default(const struct fib_rule *rule)
{
return true;
}
-static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb)
+static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
return 0;
}
@@ -375,8 +394,14 @@
return err;
}
+static inline bool fib4_has_custom_rules(const struct net *net)
+{
+ return net->ipv4.fib_has_custom_rules;
+}
+
bool fib4_rule_default(const struct fib_rule *rule);
-int fib4_rules_dump(struct net *net, struct notifier_block *nb);
+int fib4_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack);
unsigned int fib4_rules_seq_read(struct net *net);
static inline bool fib4_rules_early_flow_dissect(struct net *net,
@@ -412,7 +437,7 @@
#ifdef CONFIG_IP_ROUTE_CLASSID
static inline int fib_num_tclassid_users(struct net *net)
{
- return net->ipv4.fib_num_tclassid_users;
+ return atomic_read(&net->ipv4.fib_num_tclassid_users);
}
#else
static inline int fib_num_tclassid_users(struct net *net)
@@ -454,14 +479,18 @@
struct fib_config *cfg, int nh_weight,
struct netlink_ext_ack *extack);
void fib_nh_release(struct net *net, struct fib_nh *fib_nh);
-int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *fc_encap,
- u16 fc_encap_type, void *cfg, gfp_t gfp_flags,
+int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc,
+ struct nlattr *fc_encap, u16 fc_encap_type,
+ void *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack);
void fib_nh_common_release(struct fib_nh_common *nhc);
/* Exported by fib_trie.c */
+void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri);
void fib_trie_init(void);
struct fib_table *fib_trie_table(u32 id, struct fib_table *alias);
+bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags,
+ const struct flowi4 *flp);
static inline void fib_combine_itag(u32 *itag, const struct fib_result *res)
{
@@ -524,5 +553,5 @@
int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh,
u8 rt_family, unsigned char *flags, bool skip_oif);
int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh,
- int nh_weight, u8 rt_family);
+ int nh_weight, u8 rt_family, u32 nh_tclassid);
#endif /* _NET_FIB_H */
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 56deb25..6162067 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -33,8 +33,8 @@
/* Used to memset ipv4 address padding. */
#define IP_TUNNEL_KEY_IPV4_PAD offsetofend(struct ip_tunnel_key, u.ipv4.dst)
#define IP_TUNNEL_KEY_IPV4_PAD_LEN \
- (FIELD_SIZEOF(struct ip_tunnel_key, u) - \
- FIELD_SIZEOF(struct ip_tunnel_key, u.ipv4))
+ (sizeof_field(struct ip_tunnel_key, u) - \
+ sizeof_field(struct ip_tunnel_key, u.ipv4))
struct ip_tunnel_key {
__be64 tun_id;
@@ -63,7 +63,7 @@
/* Maximum tunnel options length. */
#define IP_TUNNEL_OPTS_MAX \
- GENMASK((FIELD_SIZEOF(struct ip_tunnel_info, \
+ GENMASK((sizeof_field(struct ip_tunnel_info, \
options_len) * BITS_PER_BYTE) - 1, 0)
struct ip_tunnel_info {
@@ -269,7 +269,8 @@
const struct iphdr *tnl_params, const u8 protocol);
void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const u8 proto, int tunnel_hlen);
-int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
+int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
+int ip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
@@ -289,6 +290,9 @@
struct ip_tunnel_parm *p, __u32 fwmark);
void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);
+extern const struct header_ops ip_tunnel_header_ops;
+__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb);
+
struct ip_tunnel_encap_ops {
size_t (*encap_hlen)(struct ip_tunnel_encap *e);
int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
@@ -416,6 +420,8 @@
u8 tos, u8 ttl, __be16 df, bool xnet);
struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
gfp_t flags);
+int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
+ int headroom, bool reply);
int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask);
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 7c37e3c..d609e95 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -14,6 +14,7 @@
#include <linux/spinlock.h> /* for struct rwlock_t */
#include <linux/atomic.h> /* for struct atomic_t */
#include <linux/refcount.h> /* for struct refcount_t */
+#include <linux/workqueue.h>
#include <linux/compiler.h>
#include <linux/timer.h>
@@ -24,9 +25,6 @@
#include <linux/ip.h>
#include <linux/ipv6.h> /* for struct ipv6hdr */
#include <net/ipv6.h>
-#if IS_ENABLED(CONFIG_IP_VS_IPV6)
-#include <linux/netfilter_ipv6/ip6_tables.h>
-#endif
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <net/netfilter/nf_conntrack.h>
#endif
@@ -874,6 +872,7 @@
struct ip_vs_stats tot_stats; /* Statistics & est. */
int num_services; /* no of virtual services */
+ int num_services6; /* IPv6 virtual services */
/* Trash for destinations */
struct list_head dest_trash;
@@ -885,6 +884,8 @@
atomic_t conn_out_counter;
#ifdef CONFIG_SYSCTL
+ /* delayed work for expiring no dest connections */
+ struct delayed_work expire_nodest_conn_work;
/* 1/rate drop and drop-entry variables */
struct delayed_work defense_work; /* Work handler */
int drop_rate;
@@ -960,6 +961,7 @@
* are not supported when synchronization is enabled.
*/
unsigned int mixed_address_family_dests;
+ unsigned int hooks_afmask; /* &1=AF_INET, &2=AF_INET6 */
};
#define DEFAULT_SYNC_THRESHOLD 3
@@ -1049,6 +1051,11 @@
return ipvs->sysctl_conn_reuse_mode;
}
+static inline int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs)
+{
+ return ipvs->sysctl_expire_nodest_conn;
+}
+
static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs)
{
return ipvs->sysctl_schedule_icmp;
@@ -1136,6 +1143,11 @@
return 1;
}
+static inline int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs)
+{
+ return 0;
+}
+
static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs)
{
return 0;
@@ -1325,7 +1337,7 @@
void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs);
-void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs);
+void ip_vs_service_nets_cleanup(struct list_head *net_list);
/* IPVS application functions
* (from ip_vs_app.c)
@@ -1505,6 +1517,22 @@
static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; }
#endif
+#ifdef CONFIG_SYSCTL
+/* Enqueue delayed work for expiring no dest connections
+ * Only run when sysctl_expire_nodest=1
+ */
+static inline void ip_vs_enqueue_expire_nodest_conns(struct netns_ipvs *ipvs)
+{
+ if (sysctl_expire_nodest_conn(ipvs))
+ queue_delayed_work(system_long_wq,
+ &ipvs->expire_nodest_conn_work, 1);
+}
+
+void ip_vs_expire_nodest_conn_flush(struct netns_ipvs *ipvs);
+#else
+static inline void ip_vs_enqueue_expire_nodest_conns(struct netns_ipvs *ipvs) {}
+#endif
+
#define IP_VS_DFWD_METHOD(dest) (atomic_read(&(dest)->conn_flags) & \
IP_VS_CONN_F_FWD_MASK)
@@ -1668,6 +1696,9 @@
#endif
}
+int ip_vs_register_hooks(struct netns_ipvs *ipvs, unsigned int af);
+void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af);
+
static inline int
ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
{
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index b59b3da..6060189 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -390,23 +390,26 @@
kfree_rcu(opt, rcu);
}
+#if IS_ENABLED(CONFIG_IPV6)
struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label);
extern struct static_key_false_deferred ipv6_flowlabel_exclusive;
static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk,
__be32 label)
{
- if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key))
+ if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key) &&
+ READ_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl))
return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT);
return NULL;
}
+#endif
struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
struct ip6_flowlabel *fl,
struct ipv6_txoptions *fopt);
void fl6_free_socklist(struct sock *sk);
-int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen);
+int ipv6_flowlabel_opt(struct sock *sk, sockptr_t optval, int optlen);
int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
int flags);
int ip6_flowlabel_init(void);
@@ -696,6 +699,11 @@
cpu_to_be32(0x0000ffff))) == 0UL;
}
+static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a)
+{
+ return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]);
+}
+
static inline u32 ipv6_portaddr_hash(const struct net *net,
const struct in6_addr *addr6,
unsigned int port)
@@ -903,7 +911,6 @@
}
}
#else
-static inline void ip6_set_txhash(struct sock *sk) { }
static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
__be32 flowlabel, bool autolabel,
struct flowi6 *fl6)
@@ -1022,6 +1029,12 @@
struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
const struct in6_addr *final_dst,
bool connected);
+struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb,
+ struct net_device *dev,
+ struct net *net, struct socket *sock,
+ struct in6_addr *saddr,
+ const struct ip_tunnel_info *info,
+ u8 protocol, bool use_cache);
struct dst_entry *ip6_blackhole_route(struct net *net,
struct dst_entry *orig_dst);
@@ -1074,14 +1087,10 @@
* socket options (ipv6_sockglue.c)
*/
-int ipv6_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen);
+int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+ unsigned int optlen);
int ipv6_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
-int compat_ipv6_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen);
-int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen);
int __ip6_datagram_connect(struct sock *sk, struct sockaddr *addr,
int addr_len);
@@ -1105,9 +1114,14 @@
int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
int peer);
int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+int inet6_compat_ioctl(struct socket *sock, unsigned int cmd,
+ unsigned long arg);
int inet6_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk);
+int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size);
+int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+ int flags);
/*
* reassembly.c
@@ -1121,9 +1135,10 @@
int ip6_mc_source(int add, int omode, struct sock *sk,
struct group_source_req *pgsr);
-int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf);
+int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf,
+ struct sockaddr_storage *list);
int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
- struct group_filter __user *optval, int __user *optlen);
+ struct sockaddr_storage __user *p);
#ifdef CONFIG_PROC_FS
int ac6_proc_init(struct net *net);
@@ -1161,4 +1176,96 @@
const struct in6_addr *addr, unsigned int mode);
int ipv6_sock_mc_drop(struct sock *sk, int ifindex,
const struct in6_addr *addr);
+
+static inline int ip6_sock_set_v6only(struct sock *sk)
+{
+ if (inet_sk(sk)->inet_num)
+ return -EINVAL;
+ lock_sock(sk);
+ sk->sk_ipv6only = true;
+ release_sock(sk);
+ return 0;
+}
+
+static inline void ip6_sock_set_recverr(struct sock *sk)
+{
+ lock_sock(sk);
+ inet6_sk(sk)->recverr = true;
+ release_sock(sk);
+}
+
+static inline int __ip6_sock_set_addr_preferences(struct sock *sk, int val)
+{
+ unsigned int pref = 0;
+ unsigned int prefmask = ~0;
+
+ /* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */
+ switch (val & (IPV6_PREFER_SRC_PUBLIC |
+ IPV6_PREFER_SRC_TMP |
+ IPV6_PREFER_SRC_PUBTMP_DEFAULT)) {
+ case IPV6_PREFER_SRC_PUBLIC:
+ pref |= IPV6_PREFER_SRC_PUBLIC;
+ prefmask &= ~(IPV6_PREFER_SRC_PUBLIC |
+ IPV6_PREFER_SRC_TMP);
+ break;
+ case IPV6_PREFER_SRC_TMP:
+ pref |= IPV6_PREFER_SRC_TMP;
+ prefmask &= ~(IPV6_PREFER_SRC_PUBLIC |
+ IPV6_PREFER_SRC_TMP);
+ break;
+ case IPV6_PREFER_SRC_PUBTMP_DEFAULT:
+ prefmask &= ~(IPV6_PREFER_SRC_PUBLIC |
+ IPV6_PREFER_SRC_TMP);
+ break;
+ case 0:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* check HOME/COA conflicts */
+ switch (val & (IPV6_PREFER_SRC_HOME | IPV6_PREFER_SRC_COA)) {
+ case IPV6_PREFER_SRC_HOME:
+ prefmask &= ~IPV6_PREFER_SRC_COA;
+ break;
+ case IPV6_PREFER_SRC_COA:
+ pref |= IPV6_PREFER_SRC_COA;
+ break;
+ case 0:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* check CGA/NONCGA conflicts */
+ switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) {
+ case IPV6_PREFER_SRC_CGA:
+ case IPV6_PREFER_SRC_NONCGA:
+ case 0:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ inet6_sk(sk)->srcprefs = (inet6_sk(sk)->srcprefs & prefmask) | pref;
+ return 0;
+}
+
+static inline int ip6_sock_set_addr_preferences(struct sock *sk, bool val)
+{
+ int ret;
+
+ lock_sock(sk);
+ ret = __ip6_sock_set_addr_preferences(sk, val);
+ release_sock(sk);
+ return ret;
+}
+
+static inline void ip6_sock_set_recvpktinfo(struct sock *sk)
+{
+ lock_sock(sk);
+ inet6_sk(sk)->rxopt.bits.rxinfo = true;
+ release_sock(sk);
+}
+
#endif /* _NET_IPV6_H */
diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
index a21e8b1..0a47791 100644
--- a/include/net/ipv6_frag.h
+++ b/include/net/ipv6_frag.h
@@ -67,7 +67,8 @@
struct sk_buff *head;
rcu_read_lock();
- if (fq->q.fqdir->dead)
+ /* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */
+ if (READ_ONCE(fq->q.fqdir->dead))
goto out_rcu_unlock;
spin_lock(&fq->q.lock);
@@ -108,5 +109,35 @@
rcu_read_unlock();
inet_frag_put(&fq->q);
}
+
+/* Check if the upper layer header is truncated in the first fragment. */
+static inline bool
+ipv6frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp)
+{
+ u8 nexthdr = *nexthdrp;
+ __be16 frag_off;
+ int offset;
+
+ offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off);
+ if (offset < 0 || (frag_off & htons(IP6_OFFSET)))
+ return false;
+ switch (nexthdr) {
+ case NEXTHDR_TCP:
+ offset += sizeof(struct tcphdr);
+ break;
+ case NEXTHDR_UDP:
+ offset += sizeof(struct udphdr);
+ break;
+ case NEXTHDR_ICMP:
+ offset += sizeof(struct icmp6hdr);
+ break;
+ default:
+ offset += 1;
+ }
+ if (offset > skb->len)
+ return true;
+ return false;
+}
+
#endif
#endif
diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index 3e7d2c0..14a4311 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -47,8 +47,9 @@
struct fib6_config *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack);
void (*fib6_nh_release)(struct fib6_nh *fib6_nh);
+ void (*fib6_nh_release_dsts)(struct fib6_nh *fib6_nh);
void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt);
- int (*ip6_del_rt)(struct net *net, struct fib6_info *rt);
+ int (*ip6_del_rt)(struct net *net, struct fib6_info *rt, bool skip_notify);
void (*fib6_rt_update)(struct net *net, struct fib6_info *rt,
struct nl_info *info);
@@ -56,14 +57,23 @@
void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr,
const struct in6_addr *solicited_addr,
bool router, bool solicited, bool override, bool inc_opt);
+#if IS_ENABLED(CONFIG_XFRM)
+ void (*xfrm6_local_rxpmtu)(struct sk_buff *skb, u32 mtu);
+ int (*xfrm6_udp_encap_rcv)(struct sock *sk, struct sk_buff *skb);
+ int (*xfrm6_rcv_encap)(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type);
+#endif
struct neigh_table *nd_tbl;
+
+ int (*ipv6_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb,
+ int (*output)(struct net *, struct sock *, struct sk_buff *));
};
extern const struct ipv6_stub *ipv6_stub __read_mostly;
/* A stub used by bpf helpers. Similarly ugly as ipv6_stub */
struct ipv6_bpf_stub {
int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len,
- bool force_bind_address_no_port, bool with_lock);
+ u32 flags);
struct sock *(*udp6_lib_lookup)(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport,
diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h
index 14a4902..9259ce2 100644
--- a/include/net/iucv/af_iucv.h
+++ b/include/net/iucv/af_iucv.h
@@ -158,12 +158,4 @@
atomic_t autobind_name;
};
-__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
- poll_table *wait);
-void iucv_sock_link(struct iucv_sock_list *l, struct sock *s);
-void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *s);
-void iucv_accept_enqueue(struct sock *parent, struct sock *sk);
-void iucv_accept_unlink(struct sock *sk);
-struct sock *iucv_accept_dequeue(struct sock *parent, struct socket *newsock);
-
#endif /* __IUCV_H */
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index e942372..031c661 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -10,6 +10,16 @@
#include <net/dst.h>
#include <net/fib_rules.h>
+enum l3mdev_type {
+ L3MDEV_TYPE_UNSPEC,
+ L3MDEV_TYPE_VRF,
+ __L3MDEV_TYPE_MAX
+};
+
+#define L3MDEV_TYPE_MAX (__L3MDEV_TYPE_MAX - 1)
+
+typedef int (*lookup_by_table_id_t)(struct net *net, u32 table_d);
+
/**
* struct l3mdev_ops - l3mdev operations
*
@@ -37,6 +47,15 @@
#ifdef CONFIG_NET_L3_MASTER_DEV
+int l3mdev_table_lookup_register(enum l3mdev_type l3type,
+ lookup_by_table_id_t fn);
+
+void l3mdev_table_lookup_unregister(enum l3mdev_type l3type,
+ lookup_by_table_id_t fn);
+
+int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net,
+ u32 table_id);
+
int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
struct fib_lookup_arg *arg);
@@ -281,6 +300,26 @@
}
static inline
+int l3mdev_table_lookup_register(enum l3mdev_type l3type,
+ lookup_by_table_id_t fn)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline
+void l3mdev_table_lookup_unregister(enum l3mdev_type l3type,
+ lookup_by_table_id_t fn)
+{
+}
+
+static inline
+int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net,
+ u32 table_id)
+{
+ return -ENODEV;
+}
+
+static inline
int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
struct fib_lookup_arg *arg)
{
diff --git a/include/net/llc.h b/include/net/llc.h
index df282d9..9c10b12 100644
--- a/include/net/llc.h
+++ b/include/net/llc.h
@@ -72,7 +72,9 @@
static inline
struct hlist_head *llc_sk_dev_hash(struct llc_sap *sap, int ifindex)
{
- return &sap->sk_dev_hash[ifindex % LLC_SK_DEV_HASH_ENTRIES];
+ u32 bucket = hash_32(ifindex, LLC_SK_DEV_HASH_BITS);
+
+ return &sap->sk_dev_hash[bucket];
}
static inline
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 5d6c5b1..05cfd6f 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -30,11 +30,11 @@
int (*orig_output)(struct net *net, struct sock *sk, struct sk_buff *skb);
int (*orig_input)(struct sk_buff *);
struct rcu_head rcu;
- __u8 data[0];
+ __u8 data[];
};
struct lwtunnel_encap_ops {
- int (*build_state)(struct nlattr *encap,
+ int (*build_state)(struct net *net, struct nlattr *encap,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack);
@@ -113,7 +113,7 @@
struct netlink_ext_ack *extack);
int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len,
struct netlink_ext_ack *extack);
-int lwtunnel_build_state(u16 encap_type,
+int lwtunnel_build_state(struct net *net, u16 encap_type,
struct nlattr *encap,
unsigned int family, const void *cfg,
struct lwtunnel_state **lws,
@@ -209,7 +209,7 @@
return 0;
}
-static inline int lwtunnel_build_state(u16 encap_type,
+static inline int lwtunnel_build_state(struct net *net, u16 encap_type,
struct nlattr *encap,
unsigned int family, const void *cfg,
struct lwtunnel_state **lws,
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index d9ba9a7..6ff49c1 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -7,7 +7,7 @@
* Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2019 Intel Corporation
+ * Copyright (C) 2018 - 2020 Intel Corporation
*/
#ifndef MAC80211_H
@@ -230,7 +230,7 @@
bool radar_enabled;
- u8 drv_priv[0] __aligned(sizeof(void *));
+ u8 drv_priv[] __aligned(sizeof(void *));
};
/**
@@ -312,10 +312,14 @@
* @BSS_CHANGED_KEEP_ALIVE: keep alive options (idle period or protected
* keep alive) changed.
* @BSS_CHANGED_MCAST_RATE: Multicast Rate setting changed for this interface
- * @BSS_CHANGED_FTM_RESPONDER: fime timing reasurement request responder
+ * @BSS_CHANGED_FTM_RESPONDER: fine timing measurement request responder
* functionality changed for this BSS (AP mode).
* @BSS_CHANGED_TWT: TWT status changed
* @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed.
+ * @BSS_CHANGED_HE_BSS_COLOR: BSS Color has changed
+ * @BSS_CHANGED_FILS_DISCOVERY: FILS discovery status changed.
+ * @BSS_CHANGED_UNSOL_BCAST_PROBE_RESP: Unsolicited broadcast probe response
+ * status changed.
*
*/
enum ieee80211_bss_change {
@@ -348,6 +352,9 @@
BSS_CHANGED_FTM_RESPONDER = 1<<26,
BSS_CHANGED_TWT = 1<<27,
BSS_CHANGED_HE_OBSS_PD = 1<<28,
+ BSS_CHANGED_HE_BSS_COLOR = 1<<29,
+ BSS_CHANGED_FILS_DISCOVERY = 1<<30,
+ BSS_CHANGED_UNSOL_BCAST_PROBE_RESP = 1<<31,
/* when adding here, make sure to change ieee80211_reconfig */
};
@@ -489,12 +496,23 @@
};
/**
+ * struct ieee80211_fils_discovery - FILS discovery parameters from
+ * IEEE Std 802.11ai-2016, Annex C.3 MIB detail.
+ *
+ * @min_interval: Minimum packet interval in TUs (0 - 10000)
+ * @max_interval: Maximum packet interval in TUs (0 - 10000)
+ */
+struct ieee80211_fils_discovery {
+ u32 min_interval;
+ u32 max_interval;
+};
+
+/**
* struct ieee80211_bss_conf - holds the BSS's changing parameters
*
* This structure keeps information about a BSS (and an association
* to that BSS) that can change during the lifetime of the BSS.
*
- * @bss_color: 6-bit value to mark inter-BSS frame, if BSS supports HE
* @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE
* @multi_sta_back_32bit: supports BA bitmap of 32-bits in Multi-STA BACK
* @uora_exists: is the UORA element advertised by AP
@@ -507,6 +525,7 @@
* mode only, set if the AP advertises TWT responder role)
* @twt_responder: does this BSS support TWT requester (relevant for managed
* mode only, set if the AP advertises TWT responder role)
+ * @twt_protected: does this BSS support protected TWT frames
* @assoc: association status
* @ibss_joined: indicates whether this station is part of an IBSS
* or not
@@ -573,7 +592,7 @@
* @ssid: The SSID of the current vif. Valid in AP and IBSS mode.
* @ssid_len: Length of SSID given in @ssid.
* @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode.
- * @txpower: TX power in dBm
+ * @txpower: TX power in dBm. INT_MIN means not configured.
* @txpower_type: TX power adjustment used to control per packet Transmit
* Power Control (TPC) in lower driver for the current vif. In particular
* TPC is enabled if value passed in %txpower_type is
@@ -602,12 +621,18 @@
* nontransmitted BSSIDs
* @profile_periodicity: the least number of beacon frames need to be received
* in order to discover all the nontransmitted BSSIDs in the set.
- * @he_operation: HE operation information of the AP we are connected to
+ * @he_oper: HE operation information of the AP we are connected to
* @he_obss_pd: OBSS Packet Detection parameters.
+ * @he_bss_color: BSS coloring settings, if BSS supports HE
+ * @fils_discovery: FILS discovery configuration
+ * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response
+ * interval.
+ * @s1g: BSS is S1G BSS (affects Association Request format).
+ * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed
+ * to driver when rate control is offloaded to firmware.
*/
struct ieee80211_bss_conf {
const u8 *bssid;
- u8 bss_color;
u8 htc_trig_based_pkt_ext;
bool multi_sta_back_32bit;
bool uora_exists;
@@ -617,6 +642,7 @@
bool he_support;
bool twt_requester;
bool twt_responder;
+ bool twt_protected;
/* association related data */
bool assoc, ibss_joined;
bool ibss_creator;
@@ -665,8 +691,16 @@
u8 bssid_indicator;
bool ema_ap;
u8 profile_periodicity;
- struct ieee80211_he_operation he_operation;
+ struct {
+ u32 params;
+ u16 nss_set;
+ } he_oper;
struct ieee80211_he_obss_pd he_obss_pd;
+ struct cfg80211_he_bss_color he_bss_color;
+ struct ieee80211_fils_discovery fils_discovery;
+ u32 unsol_bcast_probe_resp_interval;
+ bool s1g;
+ struct cfg80211_bitrate_mask beacon_tx_rate;
};
/**
@@ -713,9 +747,8 @@
* @IEEE80211_TX_INTFL_OFFCHAN_TX_OK: Internal to mac80211. Used to indicate
* that a frame can be transmitted while the queues are stopped for
* off-channel operation.
- * @IEEE80211_TX_INTFL_NEED_TXPROCESSING: completely internal to mac80211,
- * used to indicate that a pending frame requires TX processing before
- * it can be sent out.
+ * @IEEE80211_TX_CTL_HW_80211_ENCAP: This frame uses hardware encapsulation
+ * (header conversion)
* @IEEE80211_TX_INTFL_RETRIED: completely internal to mac80211,
* used to indicate that a frame was already retried due to PS
* @IEEE80211_TX_INTFL_DONT_ENCRYPT: completely internal to mac80211,
@@ -784,7 +817,7 @@
IEEE80211_TX_STAT_AMPDU_NO_BACK = BIT(11),
IEEE80211_TX_CTL_RATE_CTRL_PROBE = BIT(12),
IEEE80211_TX_INTFL_OFFCHAN_TX_OK = BIT(13),
- IEEE80211_TX_INTFL_NEED_TXPROCESSING = BIT(14),
+ IEEE80211_TX_CTL_HW_80211_ENCAP = BIT(14),
IEEE80211_TX_INTFL_RETRIED = BIT(15),
IEEE80211_TX_INTFL_DONT_ENCRYPT = BIT(16),
IEEE80211_TX_CTL_NO_PS_BUFFER = BIT(17),
@@ -805,6 +838,8 @@
#define IEEE80211_TX_CTL_STBC_SHIFT 23
+#define IEEE80211_TX_RC_S1G_MCS IEEE80211_TX_RC_VHT_MCS
+
/**
* enum mac80211_tx_control_flags - flags to describe transmit control
*
@@ -816,6 +851,11 @@
* @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame
* @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path
* @IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP: This frame skips mesh path lookup
+ * @IEEE80211_TX_INTCFL_NEED_TXPROCESSING: completely internal to mac80211,
+ * used to indicate that a pending frame requires TX processing before
+ * it can be sent out.
+ * @IEEE80211_TX_CTRL_NO_SEQNO: Do not overwrite the sequence number that
+ * has already been assigned to this frame.
*
* These flags are used in tx_info->control.flags.
*/
@@ -826,6 +866,8 @@
IEEE80211_TX_CTRL_AMSDU = BIT(3),
IEEE80211_TX_CTRL_FAST_XMIT = BIT(4),
IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP = BIT(5),
+ IEEE80211_TX_INTCFL_NEED_TXPROCESSING = BIT(6),
+ IEEE80211_TX_CTRL_NO_SEQNO = BIT(7),
};
/*
@@ -967,6 +1009,7 @@
* @band: the band to transmit on (use for checking for races)
* @hw_queue: HW queue to put the frame on, skb_get_queue_mapping() gives the AC
* @ack_frame_id: internal frame ID for TX status, used internally
+ * @tx_time_est: TX time estimate in units of 4us, used internally
* @control: union part for control data
* @control.rates: TX rates array to try
* @control.rts_cts_rate_idx: rate for RTS or CTS
@@ -988,7 +1031,8 @@
* @status.ampdu_ack_len: AMPDU ack length
* @status.ampdu_len: AMPDU length
* @status.antenna: (legacy, kept only for iwlegacy)
- * @status.tx_time: airtime consumed for transmission
+ * @status.tx_time: airtime consumed for transmission; note this is only
+ * used for WMM AC, not for airtime fairness
* @status.is_valid_ack_signal: ACK signal is valid
* @status.status_driver_data: driver use area
* @ack: union part for pure ACK data
@@ -1003,11 +1047,11 @@
struct ieee80211_tx_info {
/* common information */
u32 flags;
- u8 band;
-
- u8 hw_queue;
-
- u16 ack_frame_id;
+ u32 band:3,
+ ack_frame_id:13,
+ hw_queue:4,
+ tx_time_est:10;
+ /* 2 free bits */
union {
struct {
@@ -1058,19 +1102,37 @@
};
};
+static inline u16
+ieee80211_info_set_tx_time_est(struct ieee80211_tx_info *info, u16 tx_time_est)
+{
+ /* We only have 10 bits in tx_time_est, so store airtime
+ * in increments of 4us and clamp the maximum to 2**12-1
+ */
+ info->tx_time_est = min_t(u16, tx_time_est, 4095) >> 2;
+ return info->tx_time_est << 2;
+}
+
+static inline u16
+ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info)
+{
+ return info->tx_time_est << 2;
+}
+
/**
- * struct ieee80211_tx_status - extended tx staus info for rate control
+ * struct ieee80211_tx_status - extended tx status info for rate control
*
* @sta: Station that the packet was transmitted for
* @info: Basic tx status information
* @skb: Packet skb (can be NULL if not provided by the driver)
* @rate: The TX rate that was used when sending the packet
+ * @free_list: list where processed skbs are stored to be free'd by the driver
*/
struct ieee80211_tx_status {
struct ieee80211_sta *sta;
struct ieee80211_tx_info *info;
struct sk_buff *skb;
struct rate_info *rate;
+ struct list_head *free_list;
};
/**
@@ -1313,6 +1375,7 @@
* @freq: frequency the radio was tuned to when receiving this frame, in MHz
* This field must be set for management frames, but isn't strictly needed
* for data (other) frames - for those it only affects radiotap reporting.
+ * @freq_offset: @freq has a positive offset of 500Khz.
* @signal: signal strength when receiving this frame, either in dBm, in dB or
* unspecified depending on the hardware capabilities flags
* @IEEE80211_HW_SIGNAL_*
@@ -1343,7 +1406,7 @@
u32 device_timestamp;
u32 ampdu_reference;
u32 flag;
- u16 freq;
+ u16 freq: 13, freq_offset: 1;
u8 enc_flags;
u8 encoding:2, bw:3, he_ru:3;
u8 he_gi:2, he_dcm:1;
@@ -1359,6 +1422,13 @@
u8 zero_length_psdu_type;
};
+static inline u32
+ieee80211_rx_status_to_khz(struct ieee80211_rx_status *rx_status)
+{
+ return MHZ_TO_KHZ(rx_status->freq) +
+ (rx_status->freq_offset ? 500 : 0);
+}
+
/**
* struct ieee80211_vendor_radiotap - vendor radiotap data information
* @present: presence bitmap for this vendor namespace
@@ -1568,6 +1638,21 @@
IEEE80211_VIF_GET_NOA_UPDATE = BIT(3),
};
+
+/**
+ * enum ieee80211_offload_flags - virtual interface offload flags
+ *
+ * @IEEE80211_OFFLOAD_ENCAP_ENABLED: tx encapsulation offload is enabled
+ * The driver supports sending frames passed as 802.3 frames by mac80211.
+ * It must also support sending 802.11 packets for the same interface.
+ * @IEEE80211_OFFLOAD_ENCAP_4ADDR: support 4-address mode encapsulation offload
+ */
+
+enum ieee80211_offload_flags {
+ IEEE80211_OFFLOAD_ENCAP_ENABLED = BIT(0),
+ IEEE80211_OFFLOAD_ENCAP_4ADDR = BIT(1),
+};
+
/**
* struct ieee80211_vif - per-interface data
*
@@ -1588,6 +1673,11 @@
* these need to be set (or cleared) when the interface is added
* or, if supported by the driver, the interface type is changed
* at runtime, mac80211 will never touch this field
+ * @offloaad_flags: hardware offload capabilities/flags for this interface.
+ * These are initialized by mac80211 before calling .add_interface,
+ * .change_interface or .update_vif_offload and updated by the driver
+ * within these ops, based on supported features or runtime change
+ * restrictions.
* @hw_queue: hardware queue for each AC
* @cab_queue: content-after-beacon (DTIM beacon really) queue, AP mode only
* @chanctx_conf: The channel context this interface is assigned to, or %NULL
@@ -1600,11 +1690,15 @@
* monitor interface (if that is requested.)
* @probe_req_reg: probe requests should be reported to mac80211 for this
* interface.
+ * @rx_mcast_action_reg: multicast Action frames should be reported to mac80211
+ * for this interface.
* @drv_priv: data area for driver use, will always be aligned to
* sizeof(void \*).
* @txq: the multicast data TX queue (if driver uses the TXQ abstraction)
* @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped,
* protected by fq->lock.
+ * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see
+ * &enum ieee80211_offload_flags.
*/
struct ieee80211_vif {
enum nl80211_iftype type;
@@ -1622,17 +1716,19 @@
struct ieee80211_chanctx_conf __rcu *chanctx_conf;
u32 driver_flags;
+ u32 offload_flags;
#ifdef CONFIG_MAC80211_DEBUGFS
struct dentry *debugfs_dir;
#endif
- unsigned int probe_req_reg;
+ bool probe_req_reg;
+ bool rx_mcast_action_reg;
bool txqs_stopped[IEEE80211_NUM_ACS];
/* must be last */
- u8 drv_priv[0] __aligned(sizeof(void *));
+ u8 drv_priv[] __aligned(sizeof(void *));
};
static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif)
@@ -1702,7 +1798,7 @@
* %IEEE80211_KEY_FLAG_SW_MGMT_TX flag to encrypt such frames in SW.
* @IEEE80211_KEY_FLAG_GENERATE_IV_MGMT: This flag should be set by the
* driver for a CCMP/GCMP key to indicate that is requires IV generation
- * only for managment frames (MFP).
+ * only for management frames (MFP).
* @IEEE80211_KEY_FLAG_RESERVE_TAILROOM: This flag should be set by the
* driver for a key to indicate that sufficient tailroom must always
* be reserved for ICV or MIC, even when HW encryption is enabled.
@@ -1760,7 +1856,7 @@
s8 keyidx;
u16 flags;
u8 keylen;
- u8 key[0];
+ u8 key[];
};
#define IEEE80211_MAX_PN_LEN 16
@@ -1939,6 +2035,7 @@
* @ht_cap: HT capabilities of this STA; restricted to our own capabilities
* @vht_cap: VHT capabilities of this STA; restricted to our own capabilities
* @he_cap: HE capabilities of this STA
+ * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities
* @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU
* that this station is allowed to transmit to us.
* Can be modified by driver.
@@ -1967,6 +2064,7 @@
* @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not.
* @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control.
* @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID
+ * @txpwr: the station tx power configuration
* @txq: per-TID data TX queues (if driver uses the TXQ abstraction); note that
* the last entry (%IEEE80211_NUM_TIDS) is used for non-data frames
*/
@@ -1977,6 +2075,7 @@
struct ieee80211_sta_ht_cap ht_cap;
struct ieee80211_sta_vht_cap vht_cap;
struct ieee80211_sta_he_cap he_cap;
+ struct ieee80211_he_6ghz_capa he_6ghz_capa;
u16 max_rx_aggregation_subframes;
bool wme;
u8 uapsd_queues;
@@ -1998,7 +2097,7 @@
*
* * If the skb is transmitted as part of a BA agreement, the
* A-MSDU maximal size is min(max_amsdu_len, 4065) bytes.
- * * If the skb is not part of a BA aggreement, the A-MSDU maximal
+ * * If the skb is not part of a BA agreement, the A-MSDU maximal
* size is min(max_amsdu_len, 7935) bytes.
*
* Both additional HT limits must be enforced by the low level
@@ -2014,7 +2113,7 @@
struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1];
/* must be last */
- u8 drv_priv[0] __aligned(sizeof(void *));
+ u8 drv_priv[] __aligned(sizeof(void *));
};
/**
@@ -2060,7 +2159,7 @@
u8 ac;
/* must be last */
- u8 drv_priv[0] __aligned(sizeof(void *));
+ u8 drv_priv[] __aligned(sizeof(void *));
};
/**
@@ -2284,6 +2383,9 @@
* aggregating MPDUs with the same keyid, allowing mac80211 to keep Tx
* A-MPDU sessions active while rekeying with Extended Key ID.
*
+ * @IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD: Hardware supports tx encapsulation
+ * offload
+ *
* @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
*/
enum ieee80211_hw_flags {
@@ -2336,6 +2438,7 @@
IEEE80211_HW_SUPPORTS_MULTI_BSSID,
IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID,
IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT,
+ IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD,
/* keep last, obviously */
NUM_IEEE80211_HW_FLAGS
@@ -2626,7 +2729,7 @@
* @hw: the hardware
* @skb: the skb
*
- * Free a transmit skb. Use this funtion when some failure
+ * Free a transmit skb. Use this function when some failure
* to transmit happened and thus status cannot be reported.
*/
void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
@@ -2686,7 +2789,7 @@
* for devices that support offload of data packets (e.g. ARP responses).
*
* Mac80211 drivers should set the @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0 flag
- * when they are able to replace in-use PTK keys according to to following
+ * when they are able to replace in-use PTK keys according to the following
* requirements:
* 1) They do not hand over frames decrypted with the old key to
mac80211 once the call to set_key() with command %DISABLE_KEY has been
@@ -3070,6 +3173,8 @@
* @FIF_PSPOLL: pass PS Poll frames
*
* @FIF_PROBE_REQ: pass probe request frames
+ *
+ * @FIF_MCAST_ACTION: pass multicast Action frames
*/
enum ieee80211_filter_flags {
FIF_ALLMULTI = 1<<1,
@@ -3080,6 +3185,7 @@
FIF_OTHER_BSS = 1<<6,
FIF_PSPOLL = 1<<7,
FIF_PROBE_REQ = 1<<8,
+ FIF_MCAST_ACTION = 1<<9,
};
/**
@@ -3095,7 +3201,12 @@
*
* @IEEE80211_AMPDU_RX_START: start RX aggregation
* @IEEE80211_AMPDU_RX_STOP: stop RX aggregation
- * @IEEE80211_AMPDU_TX_START: start TX aggregation
+ * @IEEE80211_AMPDU_TX_START: start TX aggregation, the driver must either
+ * call ieee80211_start_tx_ba_cb_irqsafe() or
+ * call ieee80211_start_tx_ba_cb_irqsafe() with status
+ * %IEEE80211_AMPDU_TX_START_DELAY_ADDBA to delay addba after
+ * ieee80211_start_tx_ba_cb_irqsafe is called, or just return the special
+ * status %IEEE80211_AMPDU_TX_START_IMMEDIATE.
* @IEEE80211_AMPDU_TX_OPERATIONAL: TX aggregation has become operational
* @IEEE80211_AMPDU_TX_STOP_CONT: stop TX aggregation but continue transmitting
* queued packets, now unaggregated. After all packets are transmitted the
@@ -3119,6 +3230,9 @@
IEEE80211_AMPDU_TX_OPERATIONAL,
};
+#define IEEE80211_AMPDU_TX_START_IMMEDIATE 1
+#define IEEE80211_AMPDU_TX_START_DELAY_ADDBA 2
+
/**
* struct ieee80211_ampdu_params - AMPDU action parameters
*
@@ -3183,13 +3297,13 @@
*
* With the support for multi channel contexts and multi channel operations,
* remain on channel operations might be limited/deferred/aborted by other
- * flows/operations which have higher priority (and vise versa).
+ * flows/operations which have higher priority (and vice versa).
* Specifying the ROC type can be used by devices to prioritize the ROC
* operations compared to other operations/flows.
*
* @IEEE80211_ROC_TYPE_NORMAL: There are no special requirements for this ROC.
* @IEEE80211_ROC_TYPE_MGMT_TX: The remain on channel request is required
- * for sending managment frames offchannel.
+ * for sending management frames offchannel.
*/
enum ieee80211_roc_type {
IEEE80211_ROC_TYPE_NORMAL = 0,
@@ -3197,7 +3311,7 @@
};
/**
- * enum ieee80211_reconfig_complete_type - reconfig type
+ * enum ieee80211_reconfig_type - reconfig type
*
* This enum is used by the reconfig_complete() callback to indicate what
* reconfiguration type was completed.
@@ -3427,6 +3541,10 @@
* in AP mode, this callback will not be called when the flag
* %IEEE80211_HW_AP_LINK_PS is set. Must be atomic.
*
+ * @sta_set_txpwr: Configure the station tx power. This callback set the tx
+ * power for the station.
+ * This callback can sleep.
+ *
* @sta_state: Notifies low level driver about state transition of a
* station (which can be the AP, a client, IBSS/WDS/mesh peer etc.)
* This callback is mutually exclusive with @sta_add/@sta_remove.
@@ -3677,7 +3795,7 @@
* decremented, and when they reach 1 the driver must call
* ieee80211_csa_finish(). Drivers which use ieee80211_beacon_get()
* get the csa counter decremented by mac80211, but must check if it is
- * 1 using ieee80211_csa_is_complete() after the beacon has been
+ * 1 using ieee80211_beacon_counter_is_complete() after the beacon has been
* transmitted and then call ieee80211_csa_finish().
* If the CSA count starts as zero or 1, this function will not be called,
* since there won't be any time to beacon before the switch anyway.
@@ -3752,6 +3870,13 @@
*
* @start_pmsr: start peer measurement (e.g. FTM) (this call can sleep)
* @abort_pmsr: abort peer measurement (this call can sleep)
+ * @set_tid_config: Apply TID specific configurations. This callback may sleep.
+ * @reset_tid_config: Reset TID specific configuration for the peer.
+ * This callback may sleep.
+ * @update_vif_offload: Update virtual interface offload flags
+ * This callback may sleep.
+ * @sta_set_4addr: Called to notify the driver when a station starts/stops using
+ * 4-address mode
*/
struct ieee80211_ops {
void (*tx)(struct ieee80211_hw *hw,
@@ -3896,7 +4021,10 @@
*
* Even ``189`` would be wrong since 1 could be lost again.
*
- * Returns a negative error code on failure.
+ * Returns a negative error code on failure. The driver may return
+ * %IEEE80211_AMPDU_TX_START_IMMEDIATE for %IEEE80211_AMPDU_TX_START
+ * if the session can start immediately.
+ *
* The callback can sleep.
*/
int (*ampdu_action)(struct ieee80211_hw *hw,
@@ -4053,6 +4181,17 @@
struct cfg80211_pmsr_request *request);
void (*abort_pmsr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
struct cfg80211_pmsr_request *request);
+ int (*set_tid_config)(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta,
+ struct cfg80211_tid_config *tid_conf);
+ int (*reset_tid_config)(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta, u8 tids);
+ void (*update_vif_offload)(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif);
+ void (*sta_set_4addr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta, bool enabled);
};
/**
@@ -4289,6 +4428,31 @@
void ieee80211_restart_hw(struct ieee80211_hw *hw);
/**
+ * ieee80211_rx_list - receive frame and store processed skbs in a list
+ *
+ * Use this function to hand received frames to mac80211. The receive
+ * buffer in @skb must start with an IEEE 802.11 header. In case of a
+ * paged @skb is used, the driver is recommended to put the ieee80211
+ * header of the frame on the linear part of the @skb to avoid memory
+ * allocation and/or memcpy by the stack.
+ *
+ * This function may not be called in IRQ context. Calls to this function
+ * for a single hardware must be synchronized against each other. Calls to
+ * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be
+ * mixed for a single hardware. Must not run concurrently with
+ * ieee80211_tx_status() or ieee80211_tx_status_ni().
+ *
+ * This function must be called with BHs disabled and RCU read lock
+ *
+ * @hw: the hardware this frame came in on
+ * @sta: the station the frame was received from, or %NULL
+ * @skb: the buffer to receive, owned by mac80211 after this call
+ * @list: the destination list
+ */
+void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
+ struct sk_buff *skb, struct list_head *list);
+
+/**
* ieee80211_rx_napi - receive frame from NAPI context
*
* Use this function to hand received frames to mac80211. The receive
@@ -4636,6 +4800,26 @@
struct sk_buff *skb);
/**
+ * ieee80211_tx_status_8023 - transmit status callback for 802.3 frame format
+ *
+ * Call this function for all transmitted data frames after their transmit
+ * completion. This callback should only be called for data frames which
+ * are using driver's (or hardware's) offload capability of encap/decap
+ * 802.11 frames.
+ *
+ * This function may not be called in IRQ context. Calls to this function
+ * for a single hardware must be synchronized against each other and all
+ * calls in the same tx status family.
+ *
+ * @hw: the hardware the frame was transmitted by
+ * @vif: the interface for which the frame was transmitted
+ * @skb: the frame that was transmitted, owned by mac80211 after this call
+ */
+void ieee80211_tx_status_8023(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif,
+ struct sk_buff *skb);
+
+/**
* ieee80211_report_low_ack - report non-responding station
*
* When operating in AP-mode, call this function to report a non-responding
@@ -4646,21 +4830,21 @@
*/
void ieee80211_report_low_ack(struct ieee80211_sta *sta, u32 num_packets);
-#define IEEE80211_MAX_CSA_COUNTERS_NUM 2
+#define IEEE80211_MAX_CNTDWN_COUNTERS_NUM 2
/**
* struct ieee80211_mutable_offsets - mutable beacon offsets
* @tim_offset: position of TIM element
* @tim_length: size of TIM element
- * @csa_counter_offs: array of IEEE80211_MAX_CSA_COUNTERS_NUM offsets
- * to CSA counters. This array can contain zero values which
+ * @cntdwn_counter_offs: array of IEEE80211_MAX_CNTDWN_COUNTERS_NUM offsets
+ * to countdown counters. This array can contain zero values which
* should be ignored.
*/
struct ieee80211_mutable_offsets {
u16 tim_offset;
u16 tim_length;
- u16 csa_counter_offs[IEEE80211_MAX_CSA_COUNTERS_NUM];
+ u16 cntdwn_counter_offs[IEEE80211_MAX_CNTDWN_COUNTERS_NUM];
};
/**
@@ -4729,31 +4913,31 @@
}
/**
- * ieee80211_csa_update_counter - request mac80211 to decrement the csa counter
+ * ieee80211_beacon_update_cntdwn - request mac80211 to decrement the beacon countdown
* @vif: &struct ieee80211_vif pointer from the add_interface callback.
*
- * The csa counter should be updated after each beacon transmission.
+ * The beacon counter should be updated after each beacon transmission.
* This function is called implicitly when
* ieee80211_beacon_get/ieee80211_beacon_get_tim are called, however if the
* beacon frames are generated by the device, the driver should call this
- * function after each beacon transmission to sync mac80211's csa counters.
+ * function after each beacon transmission to sync mac80211's beacon countdown.
*
- * Return: new csa counter value
+ * Return: new countdown value
*/
-u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif);
+u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif);
/**
- * ieee80211_csa_set_counter - request mac80211 to set csa counter
+ * ieee80211_beacon_set_cntdwn - request mac80211 to set beacon countdown
* @vif: &struct ieee80211_vif pointer from the add_interface callback.
* @counter: the new value for the counter
*
- * The csa counter can be changed by the device, this API should be
+ * The beacon countdown can be changed by the device, this API should be
* used by the device driver to update csa counter in mac80211.
*
- * It should never be used together with ieee80211_csa_update_counter(),
+ * It should never be used together with ieee80211_beacon_update_cntdwn(),
* as it will cause a race condition around the counter value.
*/
-void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter);
+void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter);
/**
* ieee80211_csa_finish - notify mac80211 about channel switch
@@ -4766,13 +4950,12 @@
void ieee80211_csa_finish(struct ieee80211_vif *vif);
/**
- * ieee80211_csa_is_complete - find out if counters reached 1
+ * ieee80211_beacon_cntdwn_is_complete - find out if countdown reached 1
* @vif: &struct ieee80211_vif pointer from the add_interface callback.
*
- * This function returns whether the channel switch counters reached zero.
+ * This function returns whether the countdown reached zero.
*/
-bool ieee80211_csa_is_complete(struct ieee80211_vif *vif);
-
+bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif);
/**
* ieee80211_proberesp_get - retrieve a Probe Response template
@@ -5227,11 +5410,15 @@
* @IEEE80211_IFACE_ITER_RESUME_ALL: During resume, iterate over all
* interfaces, even if they haven't been re-added to the driver yet.
* @IEEE80211_IFACE_ITER_ACTIVE: Iterate only active interfaces (netdev is up).
+ * @IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER: Skip any interfaces where SDATA
+ * is not in the driver. This may fix crashes during firmware recovery
+ * for instance.
*/
enum ieee80211_interface_iteration_flags {
IEEE80211_IFACE_ITER_NORMAL = 0,
IEEE80211_IFACE_ITER_RESUME_ALL = BIT(0),
IEEE80211_IFACE_ITER_ACTIVE = BIT(1),
+ IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER = BIT(2),
};
/**
@@ -5531,7 +5718,7 @@
/**
* ieee80211_sta_register_airtime - register airtime usage for a sta/tid
*
- * Register airtime usage for a given sta on a given tid. The driver can call
+ * Register airtime usage for a given sta on a given tid. The driver must call
* this function to notify mac80211 that a station used a certain amount of
* airtime. This information will be used by the TXQ scheduler to schedule
* stations in a way that ensures airtime fairness.
@@ -5557,6 +5744,18 @@
u32 tx_airtime, u32 rx_airtime);
/**
+ * ieee80211_txq_airtime_check - check if a txq can send frame to device
+ *
+ * @hw: pointer obtained from ieee80211_alloc_hw()
+ * @txq: pointer obtained from station or virtual interface
+ *
+ * Return true if the AQL's airtime limit has not been reached and the txq can
+ * continue to send more packets to the device. Otherwise return false.
+ */
+bool
+ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq);
+
+/**
* ieee80211_iter_keys - iterate keys programmed into the device
* @hw: pointer obtained from ieee80211_alloc_hw()
* @vif: virtual interface to iterate, may be %NULL for all
@@ -5609,7 +5808,7 @@
/**
* ieee80211_iter_chan_contexts_atomic - iterate channel contexts
- * @hw: pointre obtained from ieee80211_alloc_hw().
+ * @hw: pointer obtained from ieee80211_alloc_hw().
* @iter: iterator function
* @iter_data: data passed to iterator function
*
@@ -6135,6 +6334,20 @@
int band, struct ieee80211_sta **sta);
/**
+ * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header
+ * of injected frames.
+ *
+ * To accurately parse and take into account rate and retransmission fields,
+ * you must initialize the chandef field in the ieee80211_tx_info structure
+ * of the skb before calling this function.
+ *
+ * @skb: packet injected by userspace
+ * @dev: the &struct device of this 802.11 device
+ */
+bool ieee80211_parse_tx_radiotap(struct sk_buff *skb,
+ struct net_device *dev);
+
+/**
* struct ieee80211_noa_data - holds temporary data for tracking P2P NoA state
*
* @next_tsf: TSF timestamp of the next absent state change
@@ -6182,7 +6395,7 @@
void ieee80211_update_p2p_noa(struct ieee80211_noa_data *data, u32 tsf);
/**
- * ieee80211_tdls_oper - request userspace to perform a TDLS operation
+ * ieee80211_tdls_oper_request - request userspace to perform a TDLS operation
* @vif: virtual interface
* @peer: the peer's destination address
* @oper: the requested TDLS operation
@@ -6243,7 +6456,7 @@
*
* Note that this must be called in an rcu_read_lock() critical section,
* which can only be released after the SKB was handled. Some pointers in
- * skb->cb, e.g. the key pointer, are protected by by RCU and thus the
+ * skb->cb, e.g. the key pointer, are protected by RCU and thus the
* critical section must persist not just for the duration of this call
* but for the duration of the frame handling.
* However, also note that while in the wake_tx_queue() method,
@@ -6359,7 +6572,7 @@
* again.
*
* The API ieee80211_txq_may_transmit() also ensures that TXQ list will be
- * aligned aginst driver's own round-robin scheduler list. i.e it rotates
+ * aligned against driver's own round-robin scheduler list. i.e it rotates
* the TXQ list till it makes the requested node becomes the first entry
* in TXQ list. Thus both the TXQ list and driver's list are in sync. If this
* function returns %true, the driver is expected to schedule packets
@@ -6417,4 +6630,69 @@
struct cfg80211_nan_match_params *match,
gfp_t gfp);
+/**
+ * ieee80211_calc_rx_airtime - calculate estimated transmission airtime for RX.
+ *
+ * This function calculates the estimated airtime usage of a frame based on the
+ * rate information in the RX status struct and the frame length.
+ *
+ * @hw: pointer as obtained from ieee80211_alloc_hw()
+ * @status: &struct ieee80211_rx_status containing the transmission rate
+ * information.
+ * @len: frame length in bytes
+ */
+u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw,
+ struct ieee80211_rx_status *status,
+ int len);
+
+/**
+ * ieee80211_calc_tx_airtime - calculate estimated transmission airtime for TX.
+ *
+ * This function calculates the estimated airtime usage of a frame based on the
+ * rate information in the TX info struct and the frame length.
+ *
+ * @hw: pointer as obtained from ieee80211_alloc_hw()
+ * @info: &struct ieee80211_tx_info of the frame.
+ * @len: frame length in bytes
+ */
+u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw,
+ struct ieee80211_tx_info *info,
+ int len);
+/**
+ * ieee80211_set_hw_80211_encap - enable hardware encapsulation offloading.
+ *
+ * This function is used to notify mac80211 that a vif can be passed raw 802.3
+ * frames. The driver needs to then handle the 802.11 encapsulation inside the
+ * hardware or firmware.
+ *
+ * @vif: &struct ieee80211_vif pointer from the add_interface callback.
+ * @enable: indicate if the feature should be turned on or off
+ */
+bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable);
+
+/**
+ * ieee80211_get_fils_discovery_tmpl - Get FILS discovery template.
+ * @hw: pointer obtained from ieee80211_alloc_hw().
+ * @vif: &struct ieee80211_vif pointer from the add_interface callback.
+ *
+ * The driver is responsible for freeing the returned skb.
+ *
+ * Return: FILS discovery template. %NULL on error.
+ */
+struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif);
+
+/**
+ * ieee80211_get_unsol_bcast_probe_resp_tmpl - Get unsolicited broadcast
+ * probe response template.
+ * @hw: pointer obtained from ieee80211_alloc_hw().
+ * @vif: &struct ieee80211_vif pointer from the add_interface callback.
+ *
+ * The driver is responsible for freeing the returned skb.
+ *
+ * Return: Unsolicited broadcast probe response template. %NULL on error.
+ */
+struct sk_buff *
+ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif);
#endif /* MAC80211_H */
diff --git a/include/net/macsec.h b/include/net/macsec.h
new file mode 100644
index 0000000..d6fa6b9
--- /dev/null
+++ b/include/net/macsec.h
@@ -0,0 +1,293 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * MACsec netdev header, used for h/w accelerated implementations.
+ *
+ * Copyright (c) 2015 Sabrina Dubroca <sd@queasysnail.net>
+ */
+#ifndef _NET_MACSEC_H_
+#define _NET_MACSEC_H_
+
+#include <linux/u64_stats_sync.h>
+#include <uapi/linux/if_link.h>
+#include <uapi/linux/if_macsec.h>
+
+#define MACSEC_DEFAULT_PN_LEN 4
+#define MACSEC_XPN_PN_LEN 8
+
+#define MACSEC_SALT_LEN 12
+#define MACSEC_NUM_AN 4 /* 2 bits for the association number */
+
+typedef u64 __bitwise sci_t;
+typedef u32 __bitwise ssci_t;
+
+typedef union salt {
+ struct {
+ u32 ssci;
+ u64 pn;
+ } __packed;
+ u8 bytes[MACSEC_SALT_LEN];
+} __packed salt_t;
+
+typedef union pn {
+ struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ u32 lower;
+ u32 upper;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ u32 upper;
+ u32 lower;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+ };
+ u64 full64;
+} pn_t;
+
+/**
+ * struct macsec_key - SA key
+ * @id: user-provided key identifier
+ * @tfm: crypto struct, key storage
+ * @salt: salt used to generate IV in XPN cipher suites
+ */
+struct macsec_key {
+ u8 id[MACSEC_KEYID_LEN];
+ struct crypto_aead *tfm;
+ salt_t salt;
+};
+
+struct macsec_rx_sc_stats {
+ __u64 InOctetsValidated;
+ __u64 InOctetsDecrypted;
+ __u64 InPktsUnchecked;
+ __u64 InPktsDelayed;
+ __u64 InPktsOK;
+ __u64 InPktsInvalid;
+ __u64 InPktsLate;
+ __u64 InPktsNotValid;
+ __u64 InPktsNotUsingSA;
+ __u64 InPktsUnusedSA;
+};
+
+struct macsec_rx_sa_stats {
+ __u32 InPktsOK;
+ __u32 InPktsInvalid;
+ __u32 InPktsNotValid;
+ __u32 InPktsNotUsingSA;
+ __u32 InPktsUnusedSA;
+};
+
+struct macsec_tx_sa_stats {
+ __u32 OutPktsProtected;
+ __u32 OutPktsEncrypted;
+};
+
+struct macsec_tx_sc_stats {
+ __u64 OutPktsProtected;
+ __u64 OutPktsEncrypted;
+ __u64 OutOctetsProtected;
+ __u64 OutOctetsEncrypted;
+};
+
+struct macsec_dev_stats {
+ __u64 OutPktsUntagged;
+ __u64 InPktsUntagged;
+ __u64 OutPktsTooLong;
+ __u64 InPktsNoTag;
+ __u64 InPktsBadTag;
+ __u64 InPktsUnknownSCI;
+ __u64 InPktsNoSCI;
+ __u64 InPktsOverrun;
+};
+
+/**
+ * struct macsec_rx_sa - receive secure association
+ * @active:
+ * @next_pn: packet number expected for the next packet
+ * @lock: protects next_pn manipulations
+ * @key: key structure
+ * @ssci: short secure channel identifier
+ * @stats: per-SA stats
+ */
+struct macsec_rx_sa {
+ struct macsec_key key;
+ ssci_t ssci;
+ spinlock_t lock;
+ union {
+ pn_t next_pn_halves;
+ u64 next_pn;
+ };
+ refcount_t refcnt;
+ bool active;
+ struct macsec_rx_sa_stats __percpu *stats;
+ struct macsec_rx_sc *sc;
+ struct rcu_head rcu;
+};
+
+struct pcpu_rx_sc_stats {
+ struct macsec_rx_sc_stats stats;
+ struct u64_stats_sync syncp;
+};
+
+struct pcpu_tx_sc_stats {
+ struct macsec_tx_sc_stats stats;
+ struct u64_stats_sync syncp;
+};
+
+/**
+ * struct macsec_rx_sc - receive secure channel
+ * @sci: secure channel identifier for this SC
+ * @active: channel is active
+ * @sa: array of secure associations
+ * @stats: per-SC stats
+ */
+struct macsec_rx_sc {
+ struct macsec_rx_sc __rcu *next;
+ sci_t sci;
+ bool active;
+ struct macsec_rx_sa __rcu *sa[MACSEC_NUM_AN];
+ struct pcpu_rx_sc_stats __percpu *stats;
+ refcount_t refcnt;
+ struct rcu_head rcu_head;
+};
+
+/**
+ * struct macsec_tx_sa - transmit secure association
+ * @active:
+ * @next_pn: packet number to use for the next packet
+ * @lock: protects next_pn manipulations
+ * @key: key structure
+ * @ssci: short secure channel identifier
+ * @stats: per-SA stats
+ */
+struct macsec_tx_sa {
+ struct macsec_key key;
+ ssci_t ssci;
+ spinlock_t lock;
+ union {
+ pn_t next_pn_halves;
+ u64 next_pn;
+ };
+ refcount_t refcnt;
+ bool active;
+ struct macsec_tx_sa_stats __percpu *stats;
+ struct rcu_head rcu;
+};
+
+/**
+ * struct macsec_tx_sc - transmit secure channel
+ * @active:
+ * @encoding_sa: association number of the SA currently in use
+ * @encrypt: encrypt packets on transmit, or authenticate only
+ * @send_sci: always include the SCI in the SecTAG
+ * @end_station:
+ * @scb: single copy broadcast flag
+ * @sa: array of secure associations
+ * @stats: stats for this TXSC
+ */
+struct macsec_tx_sc {
+ bool active;
+ u8 encoding_sa;
+ bool encrypt;
+ bool send_sci;
+ bool end_station;
+ bool scb;
+ struct macsec_tx_sa __rcu *sa[MACSEC_NUM_AN];
+ struct pcpu_tx_sc_stats __percpu *stats;
+};
+
+/**
+ * struct macsec_secy - MACsec Security Entity
+ * @netdev: netdevice for this SecY
+ * @n_rx_sc: number of receive secure channels configured on this SecY
+ * @sci: secure channel identifier used for tx
+ * @key_len: length of keys used by the cipher suite
+ * @icv_len: length of ICV used by the cipher suite
+ * @validate_frames: validation mode
+ * @xpn: enable XPN for this SecY
+ * @operational: MAC_Operational flag
+ * @protect_frames: enable protection for this SecY
+ * @replay_protect: enable packet number checks on receive
+ * @replay_window: size of the replay window
+ * @tx_sc: transmit secure channel
+ * @rx_sc: linked list of receive secure channels
+ */
+struct macsec_secy {
+ struct net_device *netdev;
+ unsigned int n_rx_sc;
+ sci_t sci;
+ u16 key_len;
+ u16 icv_len;
+ enum macsec_validation_type validate_frames;
+ bool xpn;
+ bool operational;
+ bool protect_frames;
+ bool replay_protect;
+ u32 replay_window;
+ struct macsec_tx_sc tx_sc;
+ struct macsec_rx_sc __rcu *rx_sc;
+};
+
+/**
+ * struct macsec_context - MACsec context for hardware offloading
+ */
+struct macsec_context {
+ union {
+ struct net_device *netdev;
+ struct phy_device *phydev;
+ };
+ enum macsec_offload offload;
+
+ struct macsec_secy *secy;
+ struct macsec_rx_sc *rx_sc;
+ struct {
+ unsigned char assoc_num;
+ u8 key[MACSEC_MAX_KEY_LEN];
+ union {
+ struct macsec_rx_sa *rx_sa;
+ struct macsec_tx_sa *tx_sa;
+ };
+ } sa;
+ union {
+ struct macsec_tx_sc_stats *tx_sc_stats;
+ struct macsec_tx_sa_stats *tx_sa_stats;
+ struct macsec_rx_sc_stats *rx_sc_stats;
+ struct macsec_rx_sa_stats *rx_sa_stats;
+ struct macsec_dev_stats *dev_stats;
+ } stats;
+
+ u8 prepare:1;
+};
+
+/**
+ * struct macsec_ops - MACsec offloading operations
+ */
+struct macsec_ops {
+ /* Device wide */
+ int (*mdo_dev_open)(struct macsec_context *ctx);
+ int (*mdo_dev_stop)(struct macsec_context *ctx);
+ /* SecY */
+ int (*mdo_add_secy)(struct macsec_context *ctx);
+ int (*mdo_upd_secy)(struct macsec_context *ctx);
+ int (*mdo_del_secy)(struct macsec_context *ctx);
+ /* Security channels */
+ int (*mdo_add_rxsc)(struct macsec_context *ctx);
+ int (*mdo_upd_rxsc)(struct macsec_context *ctx);
+ int (*mdo_del_rxsc)(struct macsec_context *ctx);
+ /* Security associations */
+ int (*mdo_add_rxsa)(struct macsec_context *ctx);
+ int (*mdo_upd_rxsa)(struct macsec_context *ctx);
+ int (*mdo_del_rxsa)(struct macsec_context *ctx);
+ int (*mdo_add_txsa)(struct macsec_context *ctx);
+ int (*mdo_upd_txsa)(struct macsec_context *ctx);
+ int (*mdo_del_txsa)(struct macsec_context *ctx);
+ /* Statistics */
+ int (*mdo_get_dev_stats)(struct macsec_context *ctx);
+ int (*mdo_get_tx_sc_stats)(struct macsec_context *ctx);
+ int (*mdo_get_tx_sa_stats)(struct macsec_context *ctx);
+ int (*mdo_get_rx_sc_stats)(struct macsec_context *ctx);
+ int (*mdo_get_rx_sa_stats)(struct macsec_context *ctx);
+};
+
+void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa);
+
+#endif /* _NET_MACSEC_H_ */
diff --git a/include/net/mip6.h b/include/net/mip6.h
index f1c2897..67cd7e5 100644
--- a/include/net/mip6.h
+++ b/include/net/mip6.h
@@ -25,7 +25,7 @@
__u8 ip6mh_reserved;
__u16 ip6mh_cksum;
/* Followed by type specific messages */
- __u8 data[0];
+ __u8 data[];
} __packed;
#define IP6_MH_TYPE_BRR 0 /* Binding Refresh Request */
diff --git a/include/net/mld.h b/include/net/mld.h
index b0f5b31..496bddb 100644
--- a/include/net/mld.h
+++ b/include/net/mld.h
@@ -24,12 +24,12 @@
__u8 grec_auxwords;
__be16 grec_nsrcs;
struct in6_addr grec_mca;
- struct in6_addr grec_src[0];
+ struct in6_addr grec_src[];
};
struct mld2_report {
struct icmp6hdr mld2r_hdr;
- struct mld2_grec mld2r_grec[0];
+ struct mld2_grec mld2r_grec[];
};
#define mld2r_type mld2r_hdr.icmp6_type
@@ -55,7 +55,7 @@
#endif
__u8 mld2q_qqic;
__be16 mld2q_nsrcs;
- struct in6_addr mld2q_srcs[0];
+ struct in6_addr mld2q_srcs[];
};
#define mld2q_type mld2q_hdr.icmp6_type
diff --git a/include/net/mpls.h b/include/net/mpls.h
index ccaf238e..0bb7944 100644
--- a/include/net/mpls.h
+++ b/include/net/mpls.h
@@ -8,6 +8,7 @@
#include <linux/if_ether.h>
#include <linux/netdevice.h>
+#include <linux/mpls.h>
#define MPLS_HLEN 4
@@ -25,4 +26,20 @@
{
return (struct mpls_shim_hdr *)skb_network_header(skb);
}
+
+static inline struct mpls_shim_hdr mpls_entry_encode(u32 label,
+ unsigned int ttl,
+ unsigned int tc,
+ bool bos)
+{
+ struct mpls_shim_hdr result;
+
+ result.label_stack_entry =
+ cpu_to_be32((label << MPLS_LS_LABEL_SHIFT) |
+ (tc << MPLS_LS_TC_SHIFT) |
+ (bos ? (1 << MPLS_LS_S_SHIFT) : 0) |
+ (ttl << MPLS_LS_TTL_SHIFT));
+ return result;
+}
+
#endif
diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h
index 6b4759e..9deb3a3 100644
--- a/include/net/mpls_iptunnel.h
+++ b/include/net/mpls_iptunnel.h
@@ -11,7 +11,7 @@
u8 ttl_propagate;
u8 default_ttl;
u8 reserved1;
- u32 label[0];
+ u32 label[];
};
static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate)
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
new file mode 100644
index 0000000..753ba7e
--- /dev/null
+++ b/include/net/mptcp.h
@@ -0,0 +1,221 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Multipath TCP
+ *
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ */
+
+#ifndef __NET_MPTCP_H
+#define __NET_MPTCP_H
+
+#include <linux/skbuff.h>
+#include <linux/tcp.h>
+#include <linux/types.h>
+
+struct seq_file;
+
+/* MPTCP sk_buff extension data */
+struct mptcp_ext {
+ union {
+ u64 data_ack;
+ u32 data_ack32;
+ };
+ u64 data_seq;
+ u32 subflow_seq;
+ u16 data_len;
+ u8 use_map:1,
+ dsn64:1,
+ data_fin:1,
+ use_ack:1,
+ ack64:1,
+ mpc_map:1,
+ __unused:2;
+ /* one byte hole */
+};
+
+struct mptcp_out_options {
+#if IS_ENABLED(CONFIG_MPTCP)
+ u16 suboptions;
+ u64 sndr_key;
+ u64 rcvr_key;
+ union {
+ struct in_addr addr;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+ struct in6_addr addr6;
+#endif
+ };
+ u8 addr_id;
+ u64 ahmac;
+ u8 rm_id;
+ u8 join_id;
+ u8 backup;
+ u32 nonce;
+ u64 thmac;
+ u32 token;
+ u8 hmac[20];
+ struct mptcp_ext ext_copy;
+#endif
+};
+
+#ifdef CONFIG_MPTCP
+extern struct request_sock_ops mptcp_subflow_request_sock_ops;
+
+void mptcp_init(void);
+
+static inline bool sk_is_mptcp(const struct sock *sk)
+{
+ return tcp_sk(sk)->is_mptcp;
+}
+
+static inline bool rsk_is_mptcp(const struct request_sock *req)
+{
+ return tcp_rsk(req)->is_mptcp;
+}
+
+static inline bool rsk_drop_req(const struct request_sock *req)
+{
+ return tcp_rsk(req)->is_mptcp && tcp_rsk(req)->drop_req;
+}
+
+void mptcp_space(const struct sock *ssk, int *space, int *full_space);
+bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
+ unsigned int *size, struct mptcp_out_options *opts);
+bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
+ struct mptcp_out_options *opts);
+bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
+ unsigned int *size, unsigned int remaining,
+ struct mptcp_out_options *opts);
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
+
+void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);
+
+/* move the skb extension owership, with the assumption that 'to' is
+ * newly allocated
+ */
+static inline void mptcp_skb_ext_move(struct sk_buff *to,
+ struct sk_buff *from)
+{
+ if (!skb_ext_exist(from, SKB_EXT_MPTCP))
+ return;
+
+ if (WARN_ON_ONCE(to->active_extensions))
+ skb_ext_put(to);
+
+ to->active_extensions = from->active_extensions;
+ to->extensions = from->extensions;
+ from->active_extensions = 0;
+}
+
+static inline bool mptcp_ext_matches(const struct mptcp_ext *to_ext,
+ const struct mptcp_ext *from_ext)
+{
+ /* MPTCP always clears the ext when adding it to the skb, so
+ * holes do not bother us here
+ */
+ return !from_ext ||
+ (to_ext && from_ext &&
+ !memcmp(from_ext, to_ext, sizeof(struct mptcp_ext)));
+}
+
+/* check if skbs can be collapsed.
+ * MPTCP collapse is allowed if neither @to or @from carry an mptcp data
+ * mapping, or if the extension of @to is the same as @from.
+ * Collapsing is not possible if @to lacks an extension, but @from carries one.
+ */
+static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
+ const struct sk_buff *from)
+{
+ return mptcp_ext_matches(skb_ext_find(to, SKB_EXT_MPTCP),
+ skb_ext_find(from, SKB_EXT_MPTCP));
+}
+
+void mptcp_seq_show(struct seq_file *seq);
+int mptcp_subflow_init_cookie_req(struct request_sock *req,
+ const struct sock *sk_listener,
+ struct sk_buff *skb);
+#else
+
+static inline void mptcp_init(void)
+{
+}
+
+static inline bool sk_is_mptcp(const struct sock *sk)
+{
+ return false;
+}
+
+static inline bool rsk_is_mptcp(const struct request_sock *req)
+{
+ return false;
+}
+
+static inline bool rsk_drop_req(const struct request_sock *req)
+{
+ return false;
+}
+
+static inline void mptcp_parse_option(const struct sk_buff *skb,
+ const unsigned char *ptr, int opsize,
+ struct tcp_options_received *opt_rx)
+{
+}
+
+static inline bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
+ unsigned int *size,
+ struct mptcp_out_options *opts)
+{
+ return false;
+}
+
+static inline bool mptcp_synack_options(const struct request_sock *req,
+ unsigned int *size,
+ struct mptcp_out_options *opts)
+{
+ return false;
+}
+
+static inline bool mptcp_established_options(struct sock *sk,
+ struct sk_buff *skb,
+ unsigned int *size,
+ unsigned int remaining,
+ struct mptcp_out_options *opts)
+{
+ return false;
+}
+
+static inline void mptcp_incoming_options(struct sock *sk,
+ struct sk_buff *skb)
+{
+}
+
+static inline void mptcp_skb_ext_move(struct sk_buff *to,
+ const struct sk_buff *from)
+{
+}
+
+static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
+ const struct sk_buff *from)
+{
+ return true;
+}
+
+static inline void mptcp_space(const struct sock *ssk, int *s, int *fs) { }
+static inline void mptcp_seq_show(struct seq_file *seq) { }
+
+static inline int mptcp_subflow_init_cookie_req(struct request_sock *req,
+ const struct sock *sk_listener,
+ struct sk_buff *skb)
+{
+ return 0; /* TCP fallback */
+}
+#endif /* CONFIG_MPTCP */
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+int mptcpv6_init(void);
+void mptcpv6_handle_mapped(struct sock *sk, bool mapped);
+#elif IS_ENABLED(CONFIG_IPV6)
+static inline int mptcpv6_init(void) { return 0; }
+static inline void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { }
+#endif
+
+#endif /* __NET_MPTCP_H */
diff --git a/include/net/mrp.h b/include/net/mrp.h
index ef58b4a..1c308c0 100644
--- a/include/net/mrp.h
+++ b/include/net/mrp.h
@@ -39,7 +39,7 @@
static inline struct mrp_skb_cb *mrp_cb(struct sk_buff *skb)
{
BUILD_BUG_ON(sizeof(struct mrp_skb_cb) >
- FIELD_SIZEOF(struct sk_buff, cb));
+ sizeof_field(struct sk_buff, cb));
return (struct mrp_skb_cb *)skb->cb;
}
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index b5ebeb3..38e4094 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -41,6 +41,7 @@
ND_OPT_DNSSL = 31, /* RFC6106 */
ND_OPT_6CO = 34, /* RFC6775 */
ND_OPT_CAPTIVE_PORTAL = 37, /* RFC7710 */
+ ND_OPT_PREF64 = 38, /* RFC8781 */
__ND_OPT_MAX
};
@@ -80,12 +81,12 @@
struct nd_msg {
struct icmp6hdr icmph;
struct in6_addr target;
- __u8 opt[0];
+ __u8 opt[];
};
struct rs_msg {
struct icmp6hdr icmph;
- __u8 opt[0];
+ __u8 opt[];
};
struct ra_msg {
@@ -98,7 +99,7 @@
struct icmp6hdr icmph;
struct in6_addr target;
struct in6_addr dest;
- __u8 opt[0];
+ __u8 opt[];
};
struct nd_opt_hdr {
@@ -493,7 +494,7 @@
#ifdef CONFIG_SYSCTL
int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos);
+ void *buffer, size_t *lenp, loff_t *ppos);
int ndisc_ifinfo_sysctl_strategy(struct ctl_table *ctl,
void __user *oldval, size_t __user *oldlenp,
void __user *newval, size_t newlen);
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 2be8d6b..d5767e2 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -174,7 +174,7 @@
struct net_device *dev;
u8 flags;
u8 protocol;
- u8 key[0];
+ u8 key[];
};
/*
@@ -253,6 +253,7 @@
#define NEIGH_UPDATE_F_OVERRIDE 0x00000001
#define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002
#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER 0x00000004
+#define NEIGH_UPDATE_F_USE 0x10000000
#define NEIGH_UPDATE_F_EXT_LEARNED 0x20000000
#define NEIGH_UPDATE_F_ISROUTER 0x40000000
#define NEIGH_UPDATE_F_ADMIN 0x80000000
@@ -393,13 +394,12 @@
void neigh_seq_stop(struct seq_file *, void *);
int neigh_proc_dointvec(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos);
+ void *buffer, size_t *lenp, loff_t *ppos);
int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write,
- void __user *buffer,
+ void *buffer,
size_t *lenp, loff_t *ppos);
int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write,
- void __user *buffer,
- size_t *lenp, loff_t *ppos);
+ void *buffer, size_t *lenp, loff_t *ppos);
int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
proc_handler *proc_handler);
@@ -505,10 +505,15 @@
{
const struct hh_cache *hh = &n->hh;
- if ((n->nud_state & NUD_CONNECTED) && hh->hh_len && !skip_cache)
+ /* n->nud_state and hh->hh_len could be changed under us.
+ * neigh_hh_output() is taking care of the race later.
+ */
+ if (!skip_cache &&
+ (READ_ONCE(n->nud_state) & NUD_CONNECTED) &&
+ READ_ONCE(hh->hh_len))
return neigh_hh_output(hh, skb);
- else
- return n->output(n, skb);
+
+ return n->output(n, skb);
}
static inline struct neighbour *
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 167e390..eb0e773 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -33,9 +33,11 @@
#include <net/netns/mpls.h>
#include <net/netns/can.h>
#include <net/netns/xdp.h>
+#include <net/netns/bpf.h>
#include <linux/ns_common.h>
#include <linux/idr.h>
#include <linux/skbuff.h>
+#include <linux/notifier.h>
struct user_namespace;
struct proc_dir_entry;
@@ -104,6 +106,8 @@
struct hlist_head *dev_name_head;
struct hlist_head *dev_index_head;
+ struct raw_notifier_head netdev_chain;
+
/* Note that @hash_mix can be read millions times per second,
* it is critical that it is on a read_mostly cache line.
*/
@@ -159,12 +163,16 @@
#endif
struct net_generic __rcu *gen;
- struct bpf_prog __rcu *flow_dissector_prog;
+ /* Used to store attached BPF programs */
+ struct netns_bpf bpf;
/* Note : following structs are cache line aligned */
#ifdef CONFIG_XFRM
struct netns_xfrm xfrm;
#endif
+
+ atomic64_t net_cookie; /* written once */
+
#if IS_ENABLED(CONFIG_IP_VS)
struct netns_ipvs *ipvs;
#endif
@@ -229,6 +237,8 @@
struct net *get_net_ns_by_pid(pid_t pid);
struct net *get_net_ns_by_fd(int fd);
+u64 __net_gen_cookie(struct net *net);
+
#ifdef CONFIG_SYSCTL
void ipx_register_sysctl(void);
void ipx_unregister_sysctl(void);
@@ -333,7 +343,8 @@
/* Protected by net_rwsem */
#define for_each_net(VAR) \
list_for_each_entry(VAR, &net_namespace_list, list)
-
+#define for_each_net_continue_reverse(VAR) \
+ list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list)
#define for_each_net_rcu(VAR) \
list_for_each_entry_rcu(VAR, &net_namespace_list, list)
@@ -350,9 +361,9 @@
#endif
int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp);
-int peernet2id(struct net *net, struct net *peer);
-bool peernet_has_id(struct net *net, struct net *peer);
-struct net *get_net_ns_by_id(struct net *net, int id);
+int peernet2id(const struct net *net, struct net *peer);
+bool peernet_has_id(const struct net *net, struct net *peer);
+struct net *get_net_ns_by_id(const struct net *net, int id);
struct pernet_operations {
struct list_head list;
@@ -430,7 +441,7 @@
}
#endif
-static inline int rt_genid_ipv4(struct net *net)
+static inline int rt_genid_ipv4(const struct net *net)
{
return atomic_read(&net->ipv4.rt_genid);
}
@@ -469,7 +480,7 @@
rt_genid_bump_ipv6(net);
}
-static inline int fnhe_genid(struct net *net)
+static inline int fnhe_genid(const struct net *net)
{
return atomic_read(&net->fnhe_genid);
}
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 90690e3..5cf23a2 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -262,14 +262,14 @@
/* jiffies until ct expires, 0 if already expired */
static inline unsigned long nf_ct_expires(const struct nf_conn *ct)
{
- s32 timeout = ct->timeout - nfct_time_stamp;
+ s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp;
return timeout > 0 ? timeout : 0;
}
static inline bool nf_ct_is_expired(const struct nf_conn *ct)
{
- return (__s32)(ct->timeout - nfct_time_stamp) <= 0;
+ return (__s32)(READ_ONCE(ct->timeout) - nfct_time_stamp) <= 0;
}
/* use after obtaining a reference count */
@@ -279,6 +279,18 @@
!nf_ct_is_dying(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);
@@ -286,7 +298,7 @@
extern struct hlist_nulls_head *nf_conntrack_hash;
extern unsigned int nf_conntrack_htable_size;
-extern seqcount_t nf_conntrack_generation;
+extern seqcount_spinlock_t nf_conntrack_generation;
extern unsigned int nf_conntrack_max;
/* must be called with rcu read lock held */
diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h
index f7a060c..7f44a77 100644
--- a/include/net/netfilter/nf_conntrack_acct.h
+++ b/include/net/netfilter/nf_conntrack_acct.h
@@ -65,6 +65,17 @@
#endif
}
+void nf_ct_acct_add(struct nf_conn *ct, u32 dir, unsigned int packets,
+ unsigned int bytes);
+
+static inline void nf_ct_acct_update(struct nf_conn *ct, u32 dir,
+ unsigned int bytes)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ nf_ct_acct_add(ct, dir, 1, bytes);
+#endif
+}
+
void nf_conntrack_acct_pernet_init(struct net *net);
int nf_conntrack_acct_init(void);
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 112a6f4..e1e5883 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -43,10 +43,9 @@
/* Extensions: optional stuff which isn't permanently in struct. */
struct nf_ct_ext {
- struct rcu_head rcu;
u8 offset[NF_CT_EXT_NUM];
u8 len;
- char data[0];
+ char data[];
};
static inline bool __nf_ct_ext_exist(const struct nf_ct_ext *ext, u8 id)
@@ -72,15 +71,6 @@
/* Destroy all relationships */
void nf_ct_ext_destroy(struct nf_conn *ct);
-/* Free operation. If you want to free a object referred from private area,
- * please implement __nf_ct_ext_free() and call it.
- */
-static inline void nf_ct_ext_free(struct nf_conn *ct)
-{
- if (ct->ext)
- kfree_rcu(ct->ext, rcu);
-}
-
/* Add this type, returns pointer to data or NULL. */
void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp);
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 44b5a00..37f0fbe 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -81,7 +81,7 @@
};
#define NF_CT_HELPER_BUILD_BUG_ON(structsize) \
- BUILD_BUG_ON((structsize) > FIELD_SIZEOF(struct nf_conn_help, data))
+ BUILD_BUG_ON((structsize) > sizeof_field(struct nf_conn_help, data))
struct nf_conntrack_helper *__nf_conntrack_helper_find(const char *name,
u16 l3num, u8 protonum);
diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index 4cad1f0..88186b9 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -42,7 +42,8 @@
/* Calculate tuple nlattr size */
unsigned int (*nlattr_tuple_size)(void);
int (*nlattr_to_tuple)(struct nlattr *tb[],
- struct nf_conntrack_tuple *t);
+ struct nf_conntrack_tuple *t,
+ u_int32_t flags);
const struct nla_policy *nla_policy;
struct {
@@ -152,7 +153,8 @@
int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
const struct nf_conntrack_tuple *tuple);
int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[],
- struct nf_conntrack_tuple *t);
+ struct nf_conntrack_tuple *t,
+ u_int32_t flags);
unsigned int nf_ct_port_nlattr_tuple_size(void);
extern const struct nla_policy nf_ct_port_nla_policy[];
diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index 6dd7239..659b0ea 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -14,7 +14,7 @@
struct nf_ct_timeout {
__u16 l3num;
const struct nf_conntrack_l4proto *l4proto;
- char data[0];
+ char data[];
};
struct ctnl_timeout {
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index b37a7d6..b338638 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -8,26 +8,81 @@
#include <linux/rcupdate.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_conntrack_tuple_common.h>
+#include <net/flow_offload.h>
#include <net/dst.h>
struct nf_flowtable;
+struct nf_flow_rule;
+struct flow_offload;
+enum flow_offload_tuple_dir;
+
+struct nf_flow_key {
+ struct flow_dissector_key_meta meta;
+ struct flow_dissector_key_control control;
+ struct flow_dissector_key_control enc_control;
+ struct flow_dissector_key_basic basic;
+ union {
+ struct flow_dissector_key_ipv4_addrs ipv4;
+ struct flow_dissector_key_ipv6_addrs ipv6;
+ };
+ struct flow_dissector_key_keyid enc_key_id;
+ union {
+ struct flow_dissector_key_ipv4_addrs enc_ipv4;
+ struct flow_dissector_key_ipv6_addrs enc_ipv6;
+ };
+ struct flow_dissector_key_tcp tcp;
+ struct flow_dissector_key_ports tp;
+} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
+
+struct nf_flow_match {
+ struct flow_dissector dissector;
+ struct nf_flow_key key;
+ struct nf_flow_key mask;
+};
+
+struct nf_flow_rule {
+ struct nf_flow_match match;
+ struct flow_rule *rule;
+};
struct nf_flowtable_type {
struct list_head list;
int family;
int (*init)(struct nf_flowtable *ft);
+ int (*setup)(struct nf_flowtable *ft,
+ struct net_device *dev,
+ enum flow_block_command cmd);
+ int (*action)(struct net *net,
+ const struct flow_offload *flow,
+ enum flow_offload_tuple_dir dir,
+ struct nf_flow_rule *flow_rule);
void (*free)(struct nf_flowtable *ft);
nf_hookfn *hook;
struct module *owner;
};
+enum nf_flowtable_flags {
+ NF_FLOWTABLE_HW_OFFLOAD = 0x1, /* NFT_FLOWTABLE_HW_OFFLOAD */
+ NF_FLOWTABLE_COUNTER = 0x2, /* NFT_FLOWTABLE_COUNTER */
+};
+
struct nf_flowtable {
struct list_head list;
struct rhashtable rhashtable;
+ int priority;
const struct nf_flowtable_type *type;
struct delayed_work gc_work;
+ unsigned int flags;
+ struct flow_block flow_block;
+ struct rw_semaphore flow_block_lock; /* Guards flow_block */
+ possible_net_t net;
};
+static inline bool nf_flowtable_hw_offload(struct nf_flowtable *flowtable)
+{
+ return flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD;
+}
+
enum flow_offload_tuple_dir {
FLOW_OFFLOAD_DIR_ORIGINAL = IP_CT_DIR_ORIGINAL,
FLOW_OFFLOAD_DIR_REPLY = IP_CT_DIR_REPLY,
@@ -64,21 +119,37 @@
struct flow_offload_tuple tuple;
};
-#define FLOW_OFFLOAD_SNAT 0x1
-#define FLOW_OFFLOAD_DNAT 0x2
-#define FLOW_OFFLOAD_DYING 0x4
-#define FLOW_OFFLOAD_TEARDOWN 0x8
+enum nf_flow_flags {
+ NF_FLOW_SNAT,
+ NF_FLOW_DNAT,
+ NF_FLOW_TEARDOWN,
+ NF_FLOW_HW,
+ NF_FLOW_HW_DYING,
+ NF_FLOW_HW_DEAD,
+ NF_FLOW_HW_PENDING,
+};
+
+enum flow_offload_type {
+ NF_FLOW_OFFLOAD_UNSPEC = 0,
+ NF_FLOW_OFFLOAD_ROUTE,
+};
struct flow_offload {
struct flow_offload_tuple_rhash tuplehash[FLOW_OFFLOAD_DIR_MAX];
- u32 flags;
- union {
- /* Your private driver data here. */
- u32 timeout;
- };
+ struct nf_conn *ct;
+ unsigned long flags;
+ u16 type;
+ u32 timeout;
+ struct rcu_head rcu_head;
};
#define NF_FLOW_TIMEOUT (30 * HZ)
+#define nf_flowtable_time_stamp (u32)jiffies
+
+static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
+{
+ return (__s32)(timeout - nf_flowtable_time_stamp);
+}
struct nf_flow_route {
struct {
@@ -86,23 +157,72 @@
} tuple[FLOW_OFFLOAD_DIR_MAX];
};
-struct flow_offload *flow_offload_alloc(struct nf_conn *ct,
- struct nf_flow_route *route);
+struct flow_offload *flow_offload_alloc(struct nf_conn *ct);
void flow_offload_free(struct flow_offload *flow);
+static inline int
+nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table,
+ flow_setup_cb_t *cb, void *cb_priv)
+{
+ struct flow_block *block = &flow_table->flow_block;
+ struct flow_block_cb *block_cb;
+ int err = 0;
+
+ down_write(&flow_table->flow_block_lock);
+ block_cb = flow_block_cb_lookup(block, cb, cb_priv);
+ if (block_cb) {
+ err = -EEXIST;
+ goto unlock;
+ }
+
+ block_cb = flow_block_cb_alloc(cb, cb_priv, cb_priv, NULL);
+ if (IS_ERR(block_cb)) {
+ err = PTR_ERR(block_cb);
+ goto unlock;
+ }
+
+ list_add_tail(&block_cb->list, &block->cb_list);
+
+unlock:
+ up_write(&flow_table->flow_block_lock);
+ return err;
+}
+
+static inline void
+nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
+ flow_setup_cb_t *cb, void *cb_priv)
+{
+ struct flow_block *block = &flow_table->flow_block;
+ struct flow_block_cb *block_cb;
+
+ down_write(&flow_table->flow_block_lock);
+ block_cb = flow_block_cb_lookup(block, cb, cb_priv);
+ if (block_cb) {
+ list_del(&block_cb->list);
+ flow_block_cb_free(block_cb);
+ } else {
+ WARN_ON(true);
+ }
+ up_write(&flow_table->flow_block_lock);
+}
+
+int flow_offload_route_init(struct flow_offload *flow,
+ const struct nf_flow_route *route);
+
int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow);
+void flow_offload_refresh(struct nf_flowtable *flow_table,
+ struct flow_offload *flow);
+
struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table,
struct flow_offload_tuple *tuple);
+void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable,
+ struct net_device *dev);
void nf_flow_table_cleanup(struct net_device *dev);
int nf_flow_table_init(struct nf_flowtable *flow_table);
void nf_flow_table_free(struct nf_flowtable *flow_table);
void flow_offload_teardown(struct flow_offload *flow);
-static inline void flow_offload_dead(struct flow_offload *flow)
-{
- flow->flags |= FLOW_OFFLOAD_DYING;
-}
int nf_flow_snat_port(const struct flow_offload *flow,
struct sk_buff *skb, unsigned int thoff,
@@ -123,4 +243,25 @@
#define MODULE_ALIAS_NF_FLOWTABLE(family) \
MODULE_ALIAS("nf-flowtable-" __stringify(family))
+void nf_flow_offload_add(struct nf_flowtable *flowtable,
+ struct flow_offload *flow);
+void nf_flow_offload_del(struct nf_flowtable *flowtable,
+ struct flow_offload *flow);
+void nf_flow_offload_stats(struct nf_flowtable *flowtable,
+ struct flow_offload *flow);
+
+void nf_flow_table_offload_flush(struct nf_flowtable *flowtable);
+int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
+ struct net_device *dev,
+ enum flow_block_command cmd);
+int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow,
+ enum flow_offload_tuple_dir dir,
+ struct nf_flow_rule *flow_rule);
+int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow,
+ enum flow_offload_tuple_dir dir,
+ struct nf_flow_rule *flow_rule);
+
+int nf_flow_table_offload_init(void);
+void nf_flow_table_offload_exit(void);
+
#endif /* _NF_FLOW_TABLE_H */
diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index 4708808..b1d4389 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -14,7 +14,10 @@
struct sk_buff *skb;
unsigned int id;
unsigned int hook_index; /* index in hook_entries->hook[] */
-
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+ struct net_device *physin;
+ struct net_device *physout;
+#endif
struct nf_hook_state state;
u16 size; /* sizeof(entry) + saved route keys */
@@ -34,8 +37,8 @@
void nf_unregister_queue_handler(struct net *net);
void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict);
-void nf_queue_entry_get_refs(struct nf_queue_entry *entry);
-void nf_queue_entry_release_refs(struct nf_queue_entry *entry);
+bool nf_queue_entry_get_refs(struct nf_queue_entry *entry);
+void nf_queue_entry_free(struct nf_queue_entry *entry);
static inline void init_hashrandom(u32 *jhash_initval)
{
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index f694f08..76bfb6c 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -14,6 +14,8 @@
#include <net/netlink.h>
#include <net/flow_offload.h>
+#define NFT_MAX_HOOKS (NF_INET_INGRESS + 1)
+
struct module;
#define NFT_JUMP_STACK_SIZE 16
@@ -114,7 +116,7 @@
*(u8 *)dreg = val;
}
-static inline u8 nft_reg_load8(u32 *sreg)
+static inline u8 nft_reg_load8(const u32 *sreg)
{
return *(u8 *)sreg;
}
@@ -125,7 +127,7 @@
*(u16 *)dreg = val;
}
-static inline u16 nft_reg_load16(u32 *sreg)
+static inline u16 nft_reg_load16(const u32 *sreg)
{
return *(u16 *)sreg;
}
@@ -135,7 +137,7 @@
put_unaligned(val, (u64 *)dreg);
}
-static inline u64 nft_reg_load64(u32 *sreg)
+static inline u64 nft_reg_load64(const u32 *sreg)
{
return get_unaligned((u64 *)sreg);
}
@@ -148,13 +150,6 @@
memcpy(dst, src, len);
}
-static inline void nft_data_debug(const struct nft_data *data)
-{
- pr_debug("data[0]=%x data[1]=%x data[2]=%x data[3]=%x\n",
- data->data[0], data->data[1],
- data->data[2], data->data[3]);
-}
-
/**
* struct nft_ctx - nf_tables rule/set context
*
@@ -226,13 +221,14 @@
*/
struct nft_userdata {
u8 len;
- unsigned char data[0];
+ unsigned char data[];
};
/**
* struct nft_set_elem - generic representation of set elements
*
* @key: element key
+ * @key_end: closing element key
* @priv: element private data and extensions
*/
struct nft_set_elem {
@@ -240,6 +236,14 @@
u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
struct nft_data val;
} key;
+ union {
+ u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
+ struct nft_data val;
+ } key_end;
+ union {
+ u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
+ struct nft_data val;
+ } data;
void *priv;
};
@@ -261,11 +265,17 @@
* @klen: key length
* @dlen: data length
* @size: number of set elements
+ * @field_len: length of each field in concatenation, bytes
+ * @field_count: number of concatenated fields in element
+ * @expr: set must support for expressions
*/
struct nft_set_desc {
unsigned int klen;
unsigned int dlen;
unsigned int size;
+ u8 field_len[NFT_REG32_COUNT];
+ u8 field_count;
+ bool expr;
};
/**
@@ -378,21 +388,14 @@
* struct nft_set_type - nf_tables set type
*
* @ops: set ops for this type
- * @list: used internally
- * @owner: module reference
* @features: features supported by the implementation
*/
struct nft_set_type {
const struct nft_set_ops ops;
- struct list_head list;
- struct module *owner;
u32 features;
};
#define to_set_type(o) container_of(o, struct nft_set_type, ops)
-int nft_register_set(struct nft_set_type *type);
-void nft_unregister_set(struct nft_set_type *type);
-
/**
* struct nft_set - nf_tables set instance
*
@@ -406,6 +409,8 @@
* @dtype: data type (verdict or numeric type defined by userspace)
* @objtype: object type (see NFT_OBJECT_* definitions)
* @size: maximum set size
+ * @field_len: length of each field in concatenation, bytes
+ * @field_count: number of concatenated fields in element
* @use: number of rules references to this set
* @nelems: number of elements
* @ndeact: number of deactivated elements queued for removal
@@ -414,6 +419,7 @@
* @policy: set parameterization (see enum nft_set_policies)
* @udlen: user data length
* @udata: user data
+ * @expr: stateful expression
* @ops: set ops
* @flags: set flags
* @genmask: generation mask
@@ -432,6 +438,8 @@
u32 dtype;
u32 objtype;
u32 size;
+ u8 field_len[NFT_REG32_COUNT];
+ u8 field_count;
u32 use;
atomic_t nelems;
u32 ndeact;
@@ -440,6 +448,7 @@
u16 policy;
u16 udlen;
unsigned char *udata;
+ struct nft_expr *expr;
/* runtime data below here */
const struct nft_set_ops *ops ____cacheline_aligned;
u16 flags:14,
@@ -504,6 +513,7 @@
* enum nft_set_extensions - set extension type IDs
*
* @NFT_SET_EXT_KEY: element key
+ * @NFT_SET_EXT_KEY_END: upper bound element key, for ranges
* @NFT_SET_EXT_DATA: mapping data
* @NFT_SET_EXT_FLAGS: element flags
* @NFT_SET_EXT_TIMEOUT: element timeout
@@ -515,6 +525,7 @@
*/
enum nft_set_extensions {
NFT_SET_EXT_KEY,
+ NFT_SET_EXT_KEY_END,
NFT_SET_EXT_DATA,
NFT_SET_EXT_FLAGS,
NFT_SET_EXT_TIMEOUT,
@@ -559,7 +570,7 @@
struct nft_set_ext {
u8 genmask;
u8 offset[NFT_SET_EXT_NUM];
- char data[0];
+ char data[];
};
static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl)
@@ -608,6 +619,11 @@
return nft_set_ext(ext, NFT_SET_EXT_KEY);
}
+static inline struct nft_data *nft_set_ext_key_end(const struct nft_set_ext *ext)
+{
+ return nft_set_ext(ext, NFT_SET_EXT_KEY_END);
+}
+
static inline struct nft_data *nft_set_ext_data(const struct nft_set_ext *ext)
{
return nft_set_ext(ext, NFT_SET_EXT_DATA);
@@ -655,9 +671,13 @@
return nft_set_ext(ext, NFT_SET_EXT_OBJREF);
}
+struct nft_expr *nft_set_elem_expr_alloc(const struct nft_ctx *ctx,
+ const struct nft_set *set,
+ const struct nlattr *attr);
+
void *nft_set_elem_init(const struct nft_set *set,
const struct nft_set_ext_tmpl *tmpl,
- const u32 *key, const u32 *data,
+ const u32 *key, const u32 *key_end, const u32 *data,
u64 timeout, u64 expiration, gfp_t gfp);
void nft_set_elem_destroy(const struct nft_set *set, void *elem,
bool destroy_expr);
@@ -805,7 +825,7 @@
int (*offload)(struct nft_offload_ctx *ctx,
struct nft_flow_rule *flow,
const struct nft_expr *expr);
- u32 offload_flags;
+ bool (*offload_action)(const struct nft_expr *expr);
const struct nft_expr_type *type;
void *data;
};
@@ -831,8 +851,7 @@
return (void *)expr->data;
}
-struct nft_expr *nft_expr_init(const struct nft_ctx *ctx,
- const struct nlattr *nla);
+int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src);
void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr);
int nft_expr_dump(struct sk_buff *skb, unsigned int attr,
const struct nft_expr *expr);
@@ -883,6 +902,20 @@
return (void *)&rule->data[rule->dlen];
}
+void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule);
+
+static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_expr *expr;
+
+ if (__nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) {
+ expr = nft_set_ext_expr(ext);
+ expr->ops->eval(expr, regs, pkt);
+ }
+}
+
/*
* The last pointer isn't really necessary, but the compiler isn't able to
* determine that the result of nft_expr_last() is always the same since it
@@ -893,11 +926,6 @@
(expr) != (last); \
(expr) = nft_expr_next(expr))
-enum nft_chain_flags {
- NFT_BASE_CHAIN = 0x1,
- NFT_CHAIN_HW_OFFLOAD = 0x2,
-};
-
#define NFT_CHAIN_POLICY_UNSET U8_MAX
/**
@@ -921,9 +949,12 @@
struct nft_table *table;
u64 handle;
u32 use;
- u8 flags:6,
+ u8 flags:5,
+ bound:1,
genmask:2;
char *name;
+ u16 udlen;
+ u8 *udata;
/* Only used during control plane commit phase: */
struct nft_rule **rules_next;
@@ -956,7 +987,7 @@
int family;
struct module *owner;
unsigned int hook_mask;
- nf_hookfn *hooks[NF_MAX_HOOKS];
+ nf_hookfn *hooks[NFT_MAX_HOOKS];
int (*ops_register)(struct net *net, const struct nf_hook_ops *ops);
void (*ops_unregister)(struct net *net, const struct nf_hook_ops *ops);
};
@@ -966,31 +997,46 @@
int nft_chain_validate_hooks(const struct nft_chain *chain,
unsigned int hook_flags);
+static inline bool nft_chain_is_bound(struct nft_chain *chain)
+{
+ return (chain->flags & NFT_CHAIN_BINDING) && chain->bound;
+}
+
+void nft_chain_del(struct nft_chain *chain);
+void nf_tables_chain_destroy(struct nft_ctx *ctx);
+
struct nft_stats {
u64 bytes;
u64 pkts;
struct u64_stats_sync syncp;
};
+struct nft_hook {
+ struct list_head list;
+ bool inactive;
+ struct nf_hook_ops ops;
+ struct rcu_head rcu;
+};
+
/**
* struct nft_base_chain - nf_tables base chain
*
* @ops: netfilter hook ops
+ * @hook_list: list of netfilter hooks (for NFPROTO_NETDEV family)
* @type: chain type
* @policy: default policy
* @stats: per-cpu chain stats
* @chain: the chain
- * @dev_name: device name that this base chain is attached to (if any)
* @flow_block: flow block (for hardware offload)
*/
struct nft_base_chain {
struct nf_hook_ops ops;
+ struct list_head hook_list;
const struct nft_chain_type *type;
u8 policy;
u8 flags;
struct nft_stats __percpu *stats;
struct nft_chain chain;
- char dev_name[IFNAMSIZ];
struct flow_block flow_block;
};
@@ -1001,7 +1047,7 @@
static inline bool nft_is_base_chain(const struct nft_chain *chain)
{
- return chain->flags & NFT_BASE_CHAIN;
+ return chain->flags & NFT_CHAIN_BASE;
}
int __nft_release_basechain(struct nft_ctx *ctx);
@@ -1039,8 +1085,16 @@
flags:8,
genmask:2;
char *name;
+ u16 udlen;
+ u8 *udata;
};
+static inline bool nft_base_chain_netdev(int family, u32 hooknum)
+{
+ return family == NFPROTO_NETDEV ||
+ (family == NFPROTO_INET && hooknum == NF_INET_INGRESS);
+}
+
void nft_register_chain_type(const struct nft_chain_type *);
void nft_unregister_chain_type(const struct nft_chain_type *);
@@ -1080,6 +1134,8 @@
u32 genmask:2,
use:30;
u64 handle;
+ u16 udlen;
+ u8 *udata;
/* runtime data below here */
const struct nft_object_ops *ops ____cacheline_aligned;
unsigned char data[]
@@ -1155,7 +1211,7 @@
int nft_register_obj(struct nft_object_type *obj_type);
void nft_unregister_obj(struct nft_object_type *obj_type);
-#define NFT_FLOWTABLE_DEVICE_MAX 8
+#define NFT_NETDEVICE_MAX 256
/**
* struct nft_flowtable - nf_tables flow table
@@ -1164,7 +1220,6 @@
* @table: the table the flow table is contained in
* @name: name of this flow table
* @hooknum: hook number
- * @priority: hook priority
* @ops_len: number of hooks in array
* @genmask: generation mask
* @use: number of references to this flow table
@@ -1178,13 +1233,12 @@
struct nft_table *table;
char *name;
int hooknum;
- int priority;
int ops_len;
u32 genmask:2,
use:30;
u64 handle;
/* runtime data below here */
- struct nf_hook_ops *ops ____cacheline_aligned;
+ struct list_head hook_list ____cacheline_aligned;
struct nf_flowtable data;
};
@@ -1237,9 +1291,6 @@
#define MODULE_ALIAS_NFT_EXPR(name) \
MODULE_ALIAS("nft-expr-" name)
-#define MODULE_ALIAS_NFT_SET() \
- MODULE_ALIAS("nft-set")
-
#define MODULE_ALIAS_NFT_OBJ(type) \
MODULE_ALIAS("nft-obj-" __stringify(type))
@@ -1369,7 +1420,7 @@
int msg_type;
bool put_net;
struct nft_ctx ctx;
- char data[0];
+ char data[];
};
struct nft_trans_rule {
@@ -1403,6 +1454,7 @@
char *name;
struct nft_stats __percpu *stats;
u8 policy;
+ u32 chain_id;
};
#define nft_trans_chain_update(trans) \
@@ -1413,6 +1465,8 @@
(((struct nft_trans_chain *)trans->data)->stats)
#define nft_trans_chain_policy(trans) \
(((struct nft_trans_chain *)trans->data)->policy)
+#define nft_trans_chain_id(trans) \
+ (((struct nft_trans_chain *)trans->data)->chain_id)
struct nft_trans_table {
bool update;
@@ -1452,10 +1506,19 @@
struct nft_trans_flowtable {
struct nft_flowtable *flowtable;
+ bool update;
+ struct list_head hook_list;
+ u32 flags;
};
#define nft_trans_flowtable(trans) \
(((struct nft_trans_flowtable *)trans->data)->flowtable)
+#define nft_trans_flowtable_update(trans) \
+ (((struct nft_trans_flowtable *)trans->data)->update)
+#define nft_trans_flowtable_hooks(trans) \
+ (((struct nft_trans_flowtable *)trans->data)->hook_list)
+#define nft_trans_flowtable_flags(trans) \
+ (((struct nft_trans_flowtable *)trans->data)->flags)
int __init nft_chain_filter_init(void);
void nft_chain_filter_fini(void);
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 7281895..8657e68 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -23,10 +23,19 @@
int nf_tables_core_module_init(void);
void nf_tables_core_module_exit(void);
+struct nft_bitwise_fast_expr {
+ u32 mask;
+ u32 xor;
+ enum nft_registers sreg:8;
+ enum nft_registers dreg:8;
+};
+
struct nft_cmp_fast_expr {
u32 data;
+ u32 mask;
enum nft_registers sreg:8;
u8 len;
+ bool inv;
};
struct nft_immediate_expr {
@@ -41,7 +50,7 @@
*/
static inline u32 nft_cmp_fast_mask(unsigned int len)
{
- return cpu_to_le32(~0U >> (FIELD_SIZEOF(struct nft_cmp_fast_expr,
+ return cpu_to_le32(~0U >> (sizeof_field(struct nft_cmp_fast_expr,
data) * BITS_PER_BYTE - len));
}
@@ -66,14 +75,18 @@
extern const struct nft_expr_ops nft_payload_fast_ops;
+extern const struct nft_expr_ops nft_bitwise_fast_ops;
+
extern struct static_key_false nft_counters_enabled;
extern struct static_key_false nft_trace_enabled;
-extern struct nft_set_type nft_set_rhash_type;
-extern struct nft_set_type nft_set_hash_type;
-extern struct nft_set_type nft_set_hash_fast_type;
-extern struct nft_set_type nft_set_rbtree_type;
-extern struct nft_set_type nft_set_bitmap_type;
+extern const struct nft_set_type nft_set_rhash_type;
+extern const struct nft_set_type nft_set_hash_type;
+extern const struct nft_set_type nft_set_hash_fast_type;
+extern const struct nft_set_type nft_set_rbtree_type;
+extern const struct nft_set_type nft_set_bitmap_type;
+extern const struct nft_set_type nft_set_pipapo_type;
+extern const struct nft_set_type nft_set_pipapo_avx2_type;
struct nft_expr;
struct nft_regs;
diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
index ed7b511..1f7bea3 100644
--- a/include/net/netfilter/nf_tables_ipv4.h
+++ b/include/net/netfilter/nf_tables_ipv4.h
@@ -53,4 +53,37 @@
nft_set_pktinfo_unspec(pkt, skb);
}
+static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt,
+ struct sk_buff *skb)
+{
+ struct iphdr *iph;
+ u32 len, thoff;
+
+ if (!pskb_may_pull(skb, sizeof(*iph)))
+ return -1;
+
+ iph = ip_hdr(skb);
+ if (iph->ihl < 5 || iph->version != 4)
+ goto inhdr_error;
+
+ len = ntohs(iph->tot_len);
+ thoff = iph->ihl * 4;
+ if (skb->len < len) {
+ __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS);
+ return -1;
+ } else if (len < thoff) {
+ goto inhdr_error;
+ }
+
+ pkt->tprot_set = true;
+ pkt->tprot = iph->protocol;
+ pkt->xt.thoff = thoff;
+ pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET;
+
+ return 0;
+
+inhdr_error:
+ __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INHDRERRORS);
+ return -1;
+}
#endif
diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h
index d0f1c53..867de29 100644
--- a/include/net/netfilter/nf_tables_ipv6.h
+++ b/include/net/netfilter/nf_tables_ipv6.h
@@ -70,4 +70,50 @@
nft_set_pktinfo_unspec(pkt, skb);
}
+static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt,
+ struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ unsigned int flags = IP6_FH_F_AUTH;
+ unsigned short frag_off;
+ unsigned int thoff = 0;
+ struct inet6_dev *idev;
+ struct ipv6hdr *ip6h;
+ int protohdr;
+ u32 pkt_len;
+
+ if (!pskb_may_pull(skb, sizeof(*ip6h)))
+ return -1;
+
+ ip6h = ipv6_hdr(skb);
+ if (ip6h->version != 6)
+ goto inhdr_error;
+
+ pkt_len = ntohs(ip6h->payload_len);
+ if (pkt_len + sizeof(*ip6h) > skb->len) {
+ idev = __in6_dev_get(nft_in(pkt));
+ __IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INTRUNCATEDPKTS);
+ return -1;
+ }
+
+ protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags);
+ if (protohdr < 0)
+ goto inhdr_error;
+
+ pkt->tprot_set = true;
+ pkt->tprot = protohdr;
+ pkt->xt.thoff = thoff;
+ pkt->xt.fragoff = frag_off;
+
+ return 0;
+
+inhdr_error:
+ idev = __in6_dev_get(nft_in(pkt));
+ __IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INHDRERRORS);
+ return -1;
+#else
+ return -1;
+#endif
+}
+
#endif
diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h
index d0bb9e3..7a453a3 100644
--- a/include/net/netfilter/nf_tables_offload.h
+++ b/include/net/netfilter/nf_tables_offload.h
@@ -4,11 +4,16 @@
#include <net/flow_offload.h>
#include <net/netfilter/nf_tables.h>
+enum nft_offload_reg_flags {
+ NFT_OFFLOAD_F_NETWORK2HOST = (1 << 0),
+};
+
struct nft_offload_reg {
u32 key;
u32 len;
u32 base_offset;
u32 offset;
+ u32 flags;
struct nft_data data;
struct nft_data mask;
};
@@ -45,7 +50,9 @@
struct flow_dissector_key_ports tp;
struct flow_dissector_key_ip ip;
struct flow_dissector_key_vlan vlan;
+ struct flow_dissector_key_vlan cvlan;
struct flow_dissector_key_eth_addrs eth_addrs;
+ struct flow_dissector_key_meta meta;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
struct nft_flow_match {
@@ -60,8 +67,6 @@
struct flow_rule *rule;
};
-#define NFT_OFFLOAD_F_ACTION (1 << 0)
-
void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow,
enum flow_dissector_key_id addr_type);
@@ -70,13 +75,20 @@
void nft_flow_rule_destroy(struct nft_flow_rule *flow);
int nft_flow_rule_offload_commit(struct net *net);
-#define NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \
+#define NFT_OFFLOAD_MATCH_FLAGS(__key, __base, __field, __len, __reg, __flags) \
(__reg)->base_offset = \
offsetof(struct nft_flow_key, __base); \
(__reg)->offset = \
offsetof(struct nft_flow_key, __base.__field); \
(__reg)->len = __len; \
(__reg)->key = __key; \
+ (__reg)->flags = __flags;
+
+#define NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \
+ NFT_OFFLOAD_MATCH_FLAGS(__key, __base, __field, __len, __reg, 0)
+
+#define NFT_OFFLOAD_MATCH_EXACT(__key, __base, __field, __len, __reg) \
+ NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \
memset(&(__reg)->mask, 0xff, (__reg)->len);
int nft_chain_offload_priority(struct nft_base_chain *basechain);
diff --git a/include/net/netlink.h b/include/net/netlink.h
index b140c8f..7356f41 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -181,19 +181,27 @@
NLA_S64,
NLA_BITFIELD32,
NLA_REJECT,
- NLA_EXACT_LEN,
- NLA_EXACT_LEN_WARN,
- NLA_MIN_LEN,
__NLA_TYPE_MAX,
};
#define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1)
+struct netlink_range_validation {
+ u64 min, max;
+};
+
+struct netlink_range_validation_signed {
+ s64 min, max;
+};
+
enum nla_policy_validation {
NLA_VALIDATE_NONE,
NLA_VALIDATE_RANGE,
+ NLA_VALIDATE_RANGE_WARN_TOO_LONG,
NLA_VALIDATE_MIN,
NLA_VALIDATE_MAX,
+ NLA_VALIDATE_MASK,
+ NLA_VALIDATE_RANGE_PTR,
NLA_VALIDATE_FUNCTION,
};
@@ -213,11 +221,11 @@
* NLA_NUL_STRING Maximum length of string (excluding NUL)
* NLA_FLAG Unused
* NLA_BINARY Maximum length of attribute payload
- * NLA_MIN_LEN Minimum length of attribute payload
+ * (but see also below with the validation type)
* NLA_NESTED,
* NLA_NESTED_ARRAY Length verification is done by checking len of
* nested header (or empty); len field is used if
- * validation_data is also used, for the max attr
+ * nested_policy is also used, for the max attr
* number in the nested policy.
* NLA_U8, NLA_U16,
* NLA_U32, NLA_U64,
@@ -228,34 +236,27 @@
* just like "All other"
* NLA_BITFIELD32 Unused
* NLA_REJECT Unused
- * NLA_EXACT_LEN Attribute must have exactly this length, otherwise
- * it is rejected.
- * NLA_EXACT_LEN_WARN Attribute should have exactly this length, a warning
- * is logged if it is longer, shorter is rejected.
- * NLA_MIN_LEN Minimum length of attribute payload
* All other Minimum length of attribute payload
*
- * Meaning of `validation_data' field:
+ * Meaning of validation union:
* NLA_BITFIELD32 This is a 32-bit bitmap/bitselector attribute and
- * validation data must point to a u32 value of valid
- * flags
- * NLA_REJECT This attribute is always rejected and validation data
+ * `bitfield32_valid' is the u32 value of valid flags
+ * NLA_REJECT This attribute is always rejected and `reject_message'
* may point to a string to report as the error instead
* of the generic one in extended ACK.
- * NLA_NESTED Points to a nested policy to validate, must also set
- * `len' to the max attribute number.
+ * NLA_NESTED `nested_policy' to a nested policy to validate, must
+ * also set `len' to the max attribute number. Use the
+ * provided NLA_POLICY_NESTED() macro.
* Note that nla_parse() will validate, but of course not
* parse, the nested sub-policies.
- * NLA_NESTED_ARRAY Points to a nested policy to validate, must also set
- * `len' to the max attribute number. The difference to
- * NLA_NESTED is the structure - NLA_NESTED has the
- * nested attributes directly inside, while an array has
- * the nested attributes at another level down and the
- * attributes directly in the nesting don't matter.
- * All other Unused - but note that it's a union
- *
- * Meaning of `min' and `max' fields, use via NLA_POLICY_MIN, NLA_POLICY_MAX
- * and NLA_POLICY_RANGE:
+ * NLA_NESTED_ARRAY `nested_policy' points to a nested policy to validate,
+ * must also set `len' to the max attribute number. Use
+ * the provided NLA_POLICY_NESTED_ARRAY() macro.
+ * The difference to NLA_NESTED is the structure:
+ * NLA_NESTED has the nested attributes directly inside
+ * while an array has the nested attributes at another
+ * level down and the attribute types directly in the
+ * nesting don't matter.
* NLA_U8,
* NLA_U16,
* NLA_U32,
@@ -263,29 +264,52 @@
* NLA_S8,
* NLA_S16,
* NLA_S32,
- * NLA_S64 These are used depending on the validation_type
- * field, if that is min/max/range then the minimum,
- * maximum and both are used (respectively) to check
+ * NLA_S64 The `min' and `max' fields are used depending on the
+ * validation_type field, if that is min/max/range then
+ * the min, max or both are used (respectively) to check
* the value of the integer attribute.
* Note that in the interest of code simplicity and
* struct size both limits are s16, so you cannot
* enforce a range that doesn't fall within the range
* of s16 - do that as usual in the code instead.
+ * Use the NLA_POLICY_MIN(), NLA_POLICY_MAX() and
+ * NLA_POLICY_RANGE() macros.
+ * NLA_U8,
+ * NLA_U16,
+ * NLA_U32,
+ * NLA_U64 If the validation_type field instead is set to
+ * NLA_VALIDATE_RANGE_PTR, `range' must be a pointer
+ * to a struct netlink_range_validation that indicates
+ * the min/max values.
+ * Use NLA_POLICY_FULL_RANGE().
+ * NLA_S8,
+ * NLA_S16,
+ * NLA_S32,
+ * NLA_S64 If the validation_type field instead is set to
+ * NLA_VALIDATE_RANGE_PTR, `range_signed' must be a
+ * pointer to a struct netlink_range_validation_signed
+ * that indicates the min/max values.
+ * Use NLA_POLICY_FULL_RANGE_SIGNED().
+ *
+ * NLA_BINARY If the validation type is like the ones for integers
+ * above, then the min/max length (not value like for
+ * integers) of the attribute is enforced.
+ *
* All other Unused - but note that it's a union
*
* Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN:
- * NLA_BINARY Validation function called for the attribute,
- * not compatible with use of the validation_data
- * as in NLA_BITFIELD32, NLA_REJECT, NLA_NESTED and
- * NLA_NESTED_ARRAY.
+ * NLA_BINARY Validation function called for the attribute.
* All other Unused - but note that it's a union
*
* Example:
+ *
+ * static const u32 myvalidflags = 0xff231023;
+ *
* static const struct nla_policy my_policy[ATTR_MAX+1] = {
* [ATTR_FOO] = { .type = NLA_U16 },
* [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ },
- * [ATTR_BAZ] = { .type = NLA_EXACT_LEN, .len = sizeof(struct mystruct) },
- * [ATTR_GOO] = { .type = NLA_BITFIELD32, .validation_data = &myvalidflags },
+ * [ATTR_BAZ] = NLA_POLICY_EXACT_LEN(sizeof(struct mystruct)),
+ * [ATTR_GOO] = NLA_POLICY_BITFIELD32(myvalidflags),
* };
*/
struct nla_policy {
@@ -293,7 +317,12 @@
u8 validation_type;
u16 len;
union {
- const void *validation_data;
+ const u32 bitfield32_valid;
+ const u32 mask;
+ const char *reject_message;
+ const struct nla_policy *nested_policy;
+ struct netlink_range_validation *range;
+ struct netlink_range_validation_signed *range_signed;
struct {
s16 min, max;
};
@@ -306,9 +335,10 @@
* nesting validation starts here.
*
* Additionally, it means that NLA_UNSPEC is actually NLA_REJECT
- * for any types >= this, so need to use NLA_MIN_LEN to get the
- * previous pure { .len = xyz } behaviour. The advantage of this
- * is that types not specified in the policy will be rejected.
+ * for any types >= this, so need to use NLA_POLICY_MIN_LEN() to
+ * get the previous pure { .len = xyz } behaviour. The advantage
+ * of this is that types not specified in the policy will be
+ * rejected.
*
* For completely new families it should be set to 1 so that the
* validation is enforced for all attributes. For existing ones
@@ -320,29 +350,39 @@
};
};
-#define NLA_POLICY_EXACT_LEN(_len) { .type = NLA_EXACT_LEN, .len = _len }
-#define NLA_POLICY_EXACT_LEN_WARN(_len) { .type = NLA_EXACT_LEN_WARN, \
- .len = _len }
-#define NLA_POLICY_MIN_LEN(_len) { .type = NLA_MIN_LEN, .len = _len }
-
#define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN)
#define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN)
#define _NLA_POLICY_NESTED(maxattr, policy) \
- { .type = NLA_NESTED, .validation_data = policy, .len = maxattr }
+ { .type = NLA_NESTED, .nested_policy = policy, .len = maxattr }
#define _NLA_POLICY_NESTED_ARRAY(maxattr, policy) \
- { .type = NLA_NESTED_ARRAY, .validation_data = policy, .len = maxattr }
+ { .type = NLA_NESTED_ARRAY, .nested_policy = policy, .len = maxattr }
#define NLA_POLICY_NESTED(policy) \
_NLA_POLICY_NESTED(ARRAY_SIZE(policy) - 1, policy)
#define NLA_POLICY_NESTED_ARRAY(policy) \
_NLA_POLICY_NESTED_ARRAY(ARRAY_SIZE(policy) - 1, policy)
+#define NLA_POLICY_BITFIELD32(valid) \
+ { .type = NLA_BITFIELD32, .bitfield32_valid = valid }
+
+#define __NLA_IS_UINT_TYPE(tp) \
+ (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || tp == NLA_U64)
+#define __NLA_IS_SINT_TYPE(tp) \
+ (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64)
#define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition))
-#define NLA_ENSURE_INT_TYPE(tp) \
- (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_U8 || \
- tp == NLA_S16 || tp == NLA_U16 || \
- tp == NLA_S32 || tp == NLA_U32 || \
- tp == NLA_S64 || tp == NLA_U64) + tp)
+#define NLA_ENSURE_UINT_TYPE(tp) \
+ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp)) + tp)
+#define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp) \
+ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \
+ tp == NLA_MSECS || \
+ tp == NLA_BINARY) + tp)
+#define NLA_ENSURE_SINT_TYPE(tp) \
+ (__NLA_ENSURE(__NLA_IS_SINT_TYPE(tp)) + tp)
+#define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \
+ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \
+ __NLA_IS_SINT_TYPE(tp) || \
+ tp == NLA_MSECS || \
+ tp == NLA_BINARY) + tp)
#define NLA_ENSURE_NO_VALIDATION_PTR(tp) \
(__NLA_ENSURE(tp != NLA_BITFIELD32 && \
tp != NLA_REJECT && \
@@ -350,24 +390,42 @@
tp != NLA_NESTED_ARRAY) + tp)
#define NLA_POLICY_RANGE(tp, _min, _max) { \
- .type = NLA_ENSURE_INT_TYPE(tp), \
+ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \
.validation_type = NLA_VALIDATE_RANGE, \
.min = _min, \
.max = _max \
}
+#define NLA_POLICY_FULL_RANGE(tp, _range) { \
+ .type = NLA_ENSURE_UINT_OR_BINARY_TYPE(tp), \
+ .validation_type = NLA_VALIDATE_RANGE_PTR, \
+ .range = _range, \
+}
+
+#define NLA_POLICY_FULL_RANGE_SIGNED(tp, _range) { \
+ .type = NLA_ENSURE_SINT_TYPE(tp), \
+ .validation_type = NLA_VALIDATE_RANGE_PTR, \
+ .range_signed = _range, \
+}
+
#define NLA_POLICY_MIN(tp, _min) { \
- .type = NLA_ENSURE_INT_TYPE(tp), \
+ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \
.validation_type = NLA_VALIDATE_MIN, \
.min = _min, \
}
#define NLA_POLICY_MAX(tp, _max) { \
- .type = NLA_ENSURE_INT_TYPE(tp), \
+ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \
.validation_type = NLA_VALIDATE_MAX, \
.max = _max, \
}
+#define NLA_POLICY_MASK(tp, _mask) { \
+ .type = NLA_ENSURE_UINT_TYPE(tp), \
+ .validation_type = NLA_VALIDATE_MASK, \
+ .mask = _mask, \
+}
+
#define NLA_POLICY_VALIDATE_FN(tp, fn, ...) { \
.type = NLA_ENSURE_NO_VALIDATION_PTR(tp), \
.validation_type = NLA_VALIDATE_FUNCTION, \
@@ -375,6 +433,15 @@
.len = __VA_ARGS__ + 0, \
}
+#define NLA_POLICY_EXACT_LEN(_len) NLA_POLICY_RANGE(NLA_BINARY, _len, _len)
+#define NLA_POLICY_EXACT_LEN_WARN(_len) { \
+ .type = NLA_BINARY, \
+ .validation_type = NLA_VALIDATE_RANGE_WARN_TOO_LONG, \
+ .min = _len, \
+ .max = _len \
+}
+#define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len)
+
/**
* struct nl_info - netlink source information
* @nlh: Netlink message header of original request
@@ -674,7 +741,6 @@
* @hdrlen: length of family specific header
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
- * @validate: validation strictness
* @extack: extended ACK report struct
*
* See nla_parse()
@@ -772,7 +838,6 @@
* @len: length of attribute stream
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
- * @validate: validation strictness
* @extack: extended ACK report struct
*
* Validates all attributes in the specified attribute stream against the
@@ -1466,6 +1531,21 @@
}
/**
+ * nla_put_bitfield32 - Add a bitfield32 netlink attribute to a socket buffer
+ * @skb: socket buffer to add attribute to
+ * @attrtype: attribute type
+ * @value: value carrying bits
+ * @selector: selector of valid bits
+ */
+static inline int nla_put_bitfield32(struct sk_buff *skb, int attrtype,
+ __u32 value, __u32 selector)
+{
+ struct nla_bitfield32 tmp = { value, selector, };
+
+ return nla_put(skb, attrtype, sizeof(tmp), &tmp);
+}
+
+/**
* nla_get_u32 - return payload of u32 attribute
* @nla: u32 netlink attribute
*/
@@ -1735,7 +1815,7 @@
}
/**
- * nla_validate_nested - Validate a stream of nested attributes
+ * __nla_validate_nested - Validate a stream of nested attributes
* @start: container attribute
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
@@ -1758,9 +1838,9 @@
}
static inline int
-nl80211_validate_nested(const struct nlattr *start, int maxtype,
- const struct nla_policy *policy,
- struct netlink_ext_ack *extack)
+nla_validate_nested(const struct nlattr *start, int maxtype,
+ const struct nla_policy *policy,
+ struct netlink_ext_ack *extack)
{
return __nla_validate_nested(start, maxtype, policy,
NL_VALIDATE_STRICT, extack);
@@ -1861,4 +1941,26 @@
return nla->nla_len == rem;
}
+void nla_get_range_unsigned(const struct nla_policy *pt,
+ struct netlink_range_validation *range);
+void nla_get_range_signed(const struct nla_policy *pt,
+ struct netlink_range_validation_signed *range);
+
+struct netlink_policy_dump_state;
+
+int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
+ const struct nla_policy *policy,
+ unsigned int maxtype);
+int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state,
+ const struct nla_policy *policy,
+ unsigned int maxtype);
+bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state);
+int netlink_policy_dump_write(struct sk_buff *skb,
+ struct netlink_policy_dump_state *state);
+int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt);
+int netlink_policy_dump_write_attr(struct sk_buff *skb,
+ const struct nla_policy *pt,
+ int nestattr);
+void netlink_policy_dump_free(struct netlink_policy_dump_state *state);
+
#endif
diff --git a/include/net/netns/bpf.h b/include/net/netns/bpf.h
new file mode 100644
index 0000000..0ca6a1b
--- /dev/null
+++ b/include/net/netns/bpf.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * BPF programs attached to network namespace
+ */
+
+#ifndef __NETNS_BPF_H__
+#define __NETNS_BPF_H__
+
+#include <linux/bpf-netns.h>
+
+struct bpf_prog;
+struct bpf_prog_array;
+
+struct netns_bpf {
+ /* Array of programs to run compiled from progs or links */
+ struct bpf_prog_array __rcu *run_array[MAX_NETNS_BPF_ATTACH_TYPE];
+ struct bpf_prog *progs[MAX_NETNS_BPF_ATTACH_TYPE];
+ struct list_head links[MAX_NETNS_BPF_ATTACH_TYPE];
+};
+
+#endif /* __NETNS_BPF_H__ */
diff --git a/include/net/netns/can.h b/include/net/netns/can.h
index b6ab7d1..52fbd82 100644
--- a/include/net/netns/can.h
+++ b/include/net/netns/can.h
@@ -15,7 +15,6 @@
struct netns_can {
#if IS_ENABLED(CONFIG_PROC_FS)
struct proc_dir_entry *proc_dir;
- struct proc_dir_entry *pde_version;
struct proc_dir_entry *pde_stats;
struct proc_dir_entry *pde_reset_stats;
struct proc_dir_entry *pde_rcvlist_all;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index c0c0791..75484f4 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -61,7 +61,7 @@
#endif
bool fib_has_custom_local_routes;
#ifdef CONFIG_IP_ROUTE_CLASSID
- int fib_num_tclassid_users;
+ atomic_t fib_num_tclassid_users;
#endif
struct hlist_head *fib_table_hash;
bool fib_offload_disabled;
@@ -101,6 +101,7 @@
int sysctl_ip_fwd_use_pmtu;
int sysctl_ip_fwd_update_priority;
int sysctl_ip_nonlocal_bind;
+ int sysctl_ip_autobind_reuse;
/* Shall we try to damage output packets if routing dev changes? */
int sysctl_ip_dynaddr;
int sysctl_ip_early_demux;
@@ -110,6 +111,8 @@
int sysctl_tcp_early_demux;
int sysctl_udp_early_demux;
+ int sysctl_nexthop_compat_mode;
+
int sysctl_fwmark_reflect;
int sysctl_tcp_fwmark_accept;
#ifdef CONFIG_NET_L3_MASTER_DEV
@@ -154,6 +157,7 @@
int sysctl_tcp_adv_win_scale;
int sysctl_tcp_frto;
int sysctl_tcp_nometrics_save;
+ int sysctl_tcp_no_ssthresh_metrics_save;
int sysctl_tcp_moderate_rcvbuf;
int sysctl_tcp_tso_win_divisor;
int sysctl_tcp_workaround_signed_windows;
@@ -169,6 +173,7 @@
int sysctl_tcp_rmem[3];
int sysctl_tcp_comp_sack_nr;
unsigned long sysctl_tcp_comp_sack_delay_ns;
+ unsigned long sysctl_tcp_comp_sack_slack_ns;
struct inet_timewait_death_row tcp_death_row;
int sysctl_max_syn_backlog;
int sysctl_tcp_fastopen;
@@ -178,6 +183,7 @@
unsigned int sysctl_tcp_fastopen_blackhole_timeout;
atomic_t tfo_active_disable_times;
unsigned long tfo_active_disable_stamp;
+ int sysctl_tcp_reflect_tos;
int sysctl_udp_wmem_min;
int sysctl_udp_rmem_min;
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 022a0fd..1c0fbe3 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -80,9 +80,13 @@
spinlock_t fib6_gc_lock;
unsigned int ip6_rt_gc_expire;
unsigned long ip6_rt_last_gc;
+ unsigned char flowlabel_has_excl;
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
- unsigned int fib6_rules_require_fldissect;
bool fib6_has_custom_rules;
+ unsigned int fib6_rules_require_fldissect;
+#ifdef CONFIG_IPV6_SUBTREES
+ unsigned int fib6_routes_require_src;
+#endif
struct rt6_info *ip6_prohibit_entry;
struct rt6_info *ip6_blk_hole_entry;
struct fib6_table *fib6_local_tbl;
diff --git a/include/net/netns/mib.h b/include/net/netns/mib.h
index 830bdf3..59b2c3a 100644
--- a/include/net/netns/mib.h
+++ b/include/net/netns/mib.h
@@ -24,6 +24,12 @@
#ifdef CONFIG_XFRM_STATISTICS
DEFINE_SNMP_STAT(struct linux_xfrm_mib, xfrm_statistics);
#endif
+#if IS_ENABLED(CONFIG_TLS)
+ DEFINE_SNMP_STAT(struct linux_tls_mib, tls_statistics);
+#endif
+#ifdef CONFIG_MPTCP
+ DEFINE_SNMP_STAT(struct mptcp_mib, mptcp_statistics);
+#endif
};
#endif
diff --git a/include/net/netns/nexthop.h b/include/net/netns/nexthop.h
index c712ee5..1849e77 100644
--- a/include/net/netns/nexthop.h
+++ b/include/net/netns/nexthop.h
@@ -14,5 +14,6 @@
unsigned int seq; /* protected by rtnl_mutex */
u32 last_id_allocated;
+ struct blocking_notifier_head notifier_chain;
};
#endif
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index a1a8d45..6c0806b 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -8,6 +8,7 @@
struct list_head tables;
struct list_head commit_list;
struct list_head module_list;
+ struct list_head notify_list;
struct mutex commit_mutex;
unsigned int base_seq;
u8 gencursor;
diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h
index bdc0f27..d8d02e4 100644
--- a/include/net/netns/sctp.h
+++ b/include/net/netns/sctp.h
@@ -89,6 +89,12 @@
*/
int pf_retrans;
+ /* Primary.Switchover.Max.Retrans sysctl value
+ * taken from:
+ * https://tools.ietf.org/html/rfc7829
+ */
+ int ps_retrans;
+
/*
* Disable Potentially-Failed feature, the feature is enabled by default
* pf_enable - 0 : disable pf
@@ -97,6 +103,14 @@
int pf_enable;
/*
+ * Disable Potentially-Failed state exposure, ignored by default
+ * pf_expose - 0 : compatible with old applications (by default)
+ * - 1 : disable pf state exposure
+ * - 2 : enable pf state exposure
+ */
+ int pf_expose;
+
+ /*
* Policy for preforming sctp/socket accounting
* 0 - do socket level accounting, all assocs share sk_sndbuf
* 1 - do sctp accounting, each asoc may use sk_sndbuf bytes
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index b59d73d..22e1bc7 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -74,6 +74,7 @@
#endif
spinlock_t xfrm_state_lock;
seqcount_t xfrm_state_hash_generation;
+ seqcount_spinlock_t xfrm_policy_hash_generation;
spinlock_t xfrm_policy_lock;
struct mutex xfrm_cfg_mutex;
diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h
index cfc9441..dec7522 100644
--- a/include/net/netprio_cgroup.h
+++ b/include/net/netprio_cgroup.h
@@ -26,7 +26,7 @@
rcu_read_lock();
css = task_css(p, net_prio_cgrp_id);
- idx = css->cgroup->id;
+ idx = css->id;
rcu_read_unlock();
return idx;
}
diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index 18a5aca..fd87d72 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -10,6 +10,7 @@
#define __LINUX_NEXTHOP_H
#include <linux/netdevice.h>
+#include <linux/notifier.h>
#include <linux/route.h>
#include <linux/types.h>
#include <net/ip_fib.h>
@@ -26,6 +27,7 @@
u8 nh_family;
u8 nh_protocol;
u8 nh_blackhole;
+ u8 nh_fdb;
u32 nh_flags;
int nh_ifindex;
@@ -52,6 +54,7 @@
u8 family;
bool reject_nh;
+ bool fdb_nh;
union {
struct fib_nh_common fib_nhc;
@@ -73,14 +76,16 @@
struct nh_group *spare; /* spare group for removals */
u16 num_nh;
bool mpath;
+ bool fdb_nh;
bool has_v4;
- struct nh_grp_entry nh_entries[0];
+ struct nh_grp_entry nh_entries[];
};
struct nexthop {
struct rb_node rb_node; /* entry on netns rbtree */
struct list_head fi_list; /* v4 entries using nh */
struct list_head f6i_list; /* v6 entries using nh */
+ struct list_head fdb_list; /* fdb entries using this nh */
struct list_head grp_list; /* nh group entries using this nh */
struct net *net;
@@ -99,6 +104,13 @@
};
};
+enum nexthop_event_type {
+ NEXTHOP_EVENT_DEL
+};
+
+int register_nexthop_notifier(struct net *net, struct notifier_block *nb);
+int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb);
+
/* caller is holding rcu or rtnl; no reference taken to nexthop */
struct nexthop *nexthop_find_by_id(struct net *net, u32 id);
void nexthop_free_rcu(struct rcu_head *head);
@@ -120,6 +132,32 @@
return nh1 == nh2;
}
+static inline bool nexthop_is_fdb(const struct nexthop *nh)
+{
+ if (nh->is_group) {
+ const struct nh_group *nh_grp;
+
+ nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+ return nh_grp->fdb_nh;
+ } else {
+ const struct nh_info *nhi;
+
+ nhi = rcu_dereference_rtnl(nh->nh_info);
+ return nhi->fdb_nh;
+ }
+}
+
+static inline bool nexthop_has_v4(const struct nexthop *nh)
+{
+ if (nh->is_group) {
+ struct nh_group *nh_grp;
+
+ nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+ return nh_grp->has_v4;
+ }
+ return false;
+}
+
static inline bool nexthop_is_multipath(const struct nexthop *nh)
{
if (nh->is_group) {
@@ -173,7 +211,7 @@
struct fib_nh_common *nhc = &nhi->fib_nhc;
int weight = nhg->nh_entries[i].weight;
- if (fib_add_nexthop(skb, nhc, weight, rt_family) < 0)
+ if (fib_add_nexthop(skb, nhc, weight, rt_family, 0) < 0)
return -EMSGSIZE;
}
@@ -233,6 +271,39 @@
return &nhi->fib_nhc;
}
+/* called from fib_table_lookup with rcu_lock */
+static inline
+struct fib_nh_common *nexthop_get_nhc_lookup(const struct nexthop *nh,
+ int fib_flags,
+ const struct flowi4 *flp,
+ int *nhsel)
+{
+ struct nh_info *nhi;
+
+ if (nh->is_group) {
+ struct nh_group *nhg = rcu_dereference(nh->nh_grp);
+ int i;
+
+ for (i = 0; i < nhg->num_nh; i++) {
+ struct nexthop *nhe = nhg->nh_entries[i].nh;
+
+ nhi = rcu_dereference(nhe->nh_info);
+ if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) {
+ *nhsel = i;
+ return &nhi->fib_nhc;
+ }
+ }
+ } else {
+ nhi = rcu_dereference(nh->nh_info);
+ if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) {
+ *nhsel = 0;
+ return &nhi->fib_nhc;
+ }
+ }
+
+ return NULL;
+}
+
static inline bool nexthop_uses_dev(const struct nexthop *nh,
const struct net_device *dev)
{
@@ -363,4 +434,32 @@
int nexthop_for_each_fib6_nh(struct nexthop *nh,
int (*cb)(struct fib6_nh *nh, void *arg),
void *arg);
+
+static inline int nexthop_get_family(struct nexthop *nh)
+{
+ struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info);
+
+ return nhi->family;
+}
+
+static inline
+struct fib_nh_common *nexthop_fdb_nhc(struct nexthop *nh)
+{
+ struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info);
+
+ return &nhi->fib_nhc;
+}
+
+static inline struct fib_nh_common *nexthop_path_fdb_result(struct nexthop *nh,
+ int hash)
+{
+ struct nh_info *nhi;
+ struct nexthop *nhp;
+
+ nhp = nexthop_select_path(nh, hash);
+ if (unlikely(!nhp))
+ return NULL;
+ nhi = rcu_dereference(nhp->nh_info);
+ return &nhi->fib_nhc;
+}
#endif
diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index 6ab5a83..0550e03 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -244,13 +244,13 @@
struct core_conn_create_dest_spec_params {
__u8 type;
__u8 length;
- __u8 value[0];
+ __u8 value[];
} __packed;
struct nci_core_conn_create_cmd {
__u8 destination_type;
__u8 number_destination_params;
- struct core_conn_create_dest_spec_params params[0];
+ struct core_conn_create_dest_spec_params params[];
} __packed;
#define NCI_OP_CORE_CONN_CLOSE_CMD nci_opcode_pack(NCI_GID_CORE, 0x05)
@@ -321,7 +321,7 @@
__u8 status;
__le32 nfcc_features;
__u8 num_supported_rf_interfaces;
- __u8 supported_rf_interfaces[0]; /* variable size array */
+ __u8 supported_rf_interfaces[]; /* variable size array */
/* continuted in nci_core_init_rsp_2 */
} __packed;
@@ -338,7 +338,7 @@
struct nci_core_set_config_rsp {
__u8 status;
__u8 num_params;
- __u8 params_id[0]; /* variable size array */
+ __u8 params_id[]; /* variable size array */
} __packed;
#define NCI_OP_CORE_CONN_CREATE_RSP nci_opcode_pack(NCI_GID_CORE, 0x04)
@@ -501,18 +501,18 @@
__u8 nfcee_id;
__u8 trigger;
__u8 supported_data_length;
- __u8 supported_data[0];
+ __u8 supported_data[];
} __packed;
#define NCI_OP_NFCEE_DISCOVER_NTF nci_opcode_pack(NCI_GID_NFCEE_MGMT, 0x00)
struct nci_nfcee_supported_protocol {
__u8 num_protocol;
- __u8 supported_protocol[0];
+ __u8 supported_protocol[];
} __packed;
struct nci_nfcee_information_tlv {
__u8 num_tlv;
- __u8 information_tlv[0];
+ __u8 information_tlv[];
} __packed;
struct nci_nfcee_discover_ntf {
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 3397901..004e49f 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -30,6 +30,7 @@
NCI_UP,
NCI_DATA_EXCHANGE,
NCI_DATA_EXCHANGE_TO,
+ NCI_UNREG,
};
/* NCI device states */
diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index 5d277d6..2cd3a26 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -146,7 +146,7 @@
u32 aid_len;
u8 aid[NFC_MAX_AID_LENGTH];
u8 params_len;
- u8 params[0];
+ u8 params[];
} __packed;
struct nfc_genl_data {
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index ddcee12..145acb8 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -19,6 +19,8 @@
*
*/
+#include <linux/types.h>
+
#define NL802154_GENL_NAME "nl802154"
enum nl802154_commands {
@@ -150,10 +152,9 @@
};
enum nl802154_iftype {
- /* for backwards compatibility TODO */
- NL802154_IFTYPE_UNSPEC = -1,
+ NL802154_IFTYPE_UNSPEC = (~(__u32)0),
- NL802154_IFTYPE_NODE,
+ NL802154_IFTYPE_NODE = 0,
NL802154_IFTYPE_MONITOR,
NL802154_IFTYPE_COORD,
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index cf086e1..b139e7b 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -34,8 +34,18 @@
#include <linux/ptr_ring.h>
#include <linux/dma-direction.h>
-#define PP_FLAG_DMA_MAP 1 /* Should page_pool do the DMA map/unmap */
-#define PP_FLAG_ALL PP_FLAG_DMA_MAP
+#define PP_FLAG_DMA_MAP BIT(0) /* Should page_pool do the DMA
+ * map/unmap
+ */
+#define PP_FLAG_DMA_SYNC_DEV BIT(1) /* If set all pages that the driver gets
+ * from page_pool will be
+ * DMA-synced-for-device according to
+ * the length provided by the device
+ * driver.
+ * Please note DMA-sync-for-CPU is still
+ * device driver responsibility
+ */
+#define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV)
/*
* Fast allocation side cache array/stack
@@ -65,6 +75,8 @@
int nid; /* Numa node id to allocate from pages from */
struct device *dev; /* device, for DMA pre-mapping purposes */
enum dma_data_direction dma_dir; /* DMA mapping direction */
+ unsigned int max_len; /* max DMA sync memory size */
+ unsigned int offset; /* DMA addr offset */
};
struct page_pool {
@@ -112,6 +124,8 @@
* refcnt serves purpose is to simplify drivers error handling.
*/
refcount_t user_cnt;
+
+ u64 destroy_cnt;
};
struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
@@ -137,6 +151,7 @@
#ifdef CONFIG_PAGE_POOL
void page_pool_destroy(struct page_pool *pool);
void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *));
+void page_pool_release_page(struct page_pool *pool, struct page *page);
#else
static inline void page_pool_destroy(struct page_pool *pool)
{
@@ -146,41 +161,32 @@
void (*disconnect)(void *))
{
}
+static inline void page_pool_release_page(struct page_pool *pool,
+ struct page *page)
+{
+}
#endif
-/* Never call this directly, use helpers below */
-void __page_pool_put_page(struct page_pool *pool,
- struct page *page, bool allow_direct);
+void page_pool_put_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size, bool allow_direct);
-static inline void page_pool_put_page(struct page_pool *pool,
- struct page *page, bool allow_direct)
+/* Same as above but will try to sync the entire area pool->max_len */
+static inline void page_pool_put_full_page(struct page_pool *pool,
+ struct page *page, bool allow_direct)
{
/* When page_pool isn't compiled-in, net/core/xdp.c doesn't
* allow registering MEM_TYPE_PAGE_POOL, but shield linker.
*/
#ifdef CONFIG_PAGE_POOL
- __page_pool_put_page(pool, page, allow_direct);
+ page_pool_put_page(pool, page, -1, allow_direct);
#endif
}
-/* Very limited use-cases allow recycle direct */
+
+/* Same as above but the caller must guarantee safe context. e.g NAPI */
static inline void page_pool_recycle_direct(struct page_pool *pool,
struct page *page)
{
- __page_pool_put_page(pool, page, true);
-}
-
-/* Disconnects a page (from a page_pool). API users can have a need
- * to disconnect a page (from a page_pool), to allow it to be used as
- * a regular page (that will eventually be returned to the normal
- * page-allocator via put_page).
- */
-void page_pool_unmap_page(struct page_pool *pool, struct page *page);
-static inline void page_pool_release_page(struct page_pool *pool,
- struct page *page)
-{
-#ifdef CONFIG_PAGE_POOL
- page_pool_unmap_page(pool, page);
-#endif
+ page_pool_put_full_page(pool, page, true);
}
static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
@@ -212,4 +218,11 @@
return refcount_dec_and_test(&pool->user_cnt);
}
+/* Caller must provide appropriate safe context, e.g. NAPI. */
+void page_pool_update_nid(struct page_pool *pool, int new_nid);
+static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid)
+{
+ if (unlikely(pool->p.nid != new_nid))
+ page_pool_update_nid(pool, new_nid);
+}
#endif /* _NET_PAGE_POOL_H */
diff --git a/include/net/pie.h b/include/net/pie.h
new file mode 100644
index 0000000..3fe2361
--- /dev/null
+++ b/include/net/pie.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __NET_SCHED_PIE_H
+#define __NET_SCHED_PIE_H
+
+#include <linux/ktime.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <net/inet_ecn.h>
+#include <net/pkt_sched.h>
+
+#define MAX_PROB (U64_MAX >> BITS_PER_BYTE)
+#define DTIME_INVALID U64_MAX
+#define QUEUE_THRESHOLD 16384
+#define DQCOUNT_INVALID -1
+#define PIE_SCALE 8
+
+/**
+ * struct pie_params - contains pie parameters
+ * @target: target delay in pschedtime
+ * @tudpate: interval at which drop probability is calculated
+ * @limit: total number of packets that can be in the queue
+ * @alpha: parameter to control drop probability
+ * @beta: parameter to control drop probability
+ * @ecn: is ECN marking of packets enabled
+ * @bytemode: is drop probability scaled based on pkt size
+ * @dq_rate_estimator: is Little's law used for qdelay calculation
+ */
+struct pie_params {
+ psched_time_t target;
+ u32 tupdate;
+ u32 limit;
+ u32 alpha;
+ u32 beta;
+ u8 ecn;
+ u8 bytemode;
+ u8 dq_rate_estimator;
+};
+
+/**
+ * struct pie_vars - contains pie variables
+ * @qdelay: current queue delay
+ * @qdelay_old: queue delay in previous qdelay calculation
+ * @burst_time: burst time allowance
+ * @dq_tstamp: timestamp at which dq rate was last calculated
+ * @prob: drop probability
+ * @accu_prob: accumulated drop probability
+ * @dq_count: number of bytes dequeued in a measurement cycle
+ * @avg_dq_rate: calculated average dq rate
+ * @backlog_old: queue backlog during previous qdelay calculation
+ */
+struct pie_vars {
+ psched_time_t qdelay;
+ psched_time_t qdelay_old;
+ psched_time_t burst_time;
+ psched_time_t dq_tstamp;
+ u64 prob;
+ u64 accu_prob;
+ u64 dq_count;
+ u32 avg_dq_rate;
+ u32 backlog_old;
+};
+
+/**
+ * struct pie_stats - contains pie stats
+ * @packets_in: total number of packets enqueued
+ * @dropped: packets dropped due to pie action
+ * @overlimit: packets dropped due to lack of space in queue
+ * @ecn_mark: packets marked with ECN
+ * @maxq: maximum queue size
+ */
+struct pie_stats {
+ u32 packets_in;
+ u32 dropped;
+ u32 overlimit;
+ u32 ecn_mark;
+ u32 maxq;
+};
+
+/**
+ * struct pie_skb_cb - contains private skb vars
+ * @enqueue_time: timestamp when the packet is enqueued
+ * @mem_usage: size of the skb during enqueue
+ */
+struct pie_skb_cb {
+ psched_time_t enqueue_time;
+ u32 mem_usage;
+};
+
+static inline void pie_params_init(struct pie_params *params)
+{
+ params->target = PSCHED_NS2TICKS(15 * NSEC_PER_MSEC); /* 15 ms */
+ params->tupdate = usecs_to_jiffies(15 * USEC_PER_MSEC); /* 15 ms */
+ params->limit = 1000;
+ params->alpha = 2;
+ params->beta = 20;
+ params->ecn = false;
+ params->bytemode = false;
+ params->dq_rate_estimator = false;
+}
+
+static inline void pie_vars_init(struct pie_vars *vars)
+{
+ vars->burst_time = PSCHED_NS2TICKS(150 * NSEC_PER_MSEC); /* 150 ms */
+ vars->dq_tstamp = DTIME_INVALID;
+ vars->accu_prob = 0;
+ vars->dq_count = DQCOUNT_INVALID;
+ vars->avg_dq_rate = 0;
+}
+
+static inline struct pie_skb_cb *get_pie_cb(const struct sk_buff *skb)
+{
+ qdisc_cb_private_validate(skb, sizeof(struct pie_skb_cb));
+ return (struct pie_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+static inline psched_time_t pie_get_enqueue_time(const struct sk_buff *skb)
+{
+ return get_pie_cb(skb)->enqueue_time;
+}
+
+static inline void pie_set_enqueue_time(struct sk_buff *skb)
+{
+ get_pie_cb(skb)->enqueue_time = psched_get_time();
+}
+
+bool pie_drop_early(struct Qdisc *sch, struct pie_params *params,
+ struct pie_vars *vars, u32 backlog, u32 packet_size);
+
+void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params,
+ struct pie_vars *vars, u32 backlog);
+
+void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
+ u32 backlog);
+
+#endif
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 9976ad2..b608be5 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -32,6 +32,12 @@
u32 block_index;
};
+struct tcf_qevent {
+ struct tcf_block *block;
+ struct tcf_block_ext_info info;
+ struct tcf_proto __rcu *filter_chain;
+};
+
struct tcf_block_cb;
bool tcf_queue_work(struct rcu_work *rwork, work_func_t func);
@@ -72,6 +78,10 @@
int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res, bool compat_mode);
+int tcf_classify_ingress(struct sk_buff *skb,
+ const struct tcf_block *ingress_block,
+ const struct tcf_proto *tp, struct tcf_result *res,
+ bool compat_mode);
#else
static inline bool tcf_block_shared(struct tcf_block *block)
@@ -133,6 +143,15 @@
{
return TC_ACT_UNSPEC;
}
+
+static inline int tcf_classify_ingress(struct sk_buff *skb,
+ const struct tcf_block *ingress_block,
+ const struct tcf_proto *tp,
+ struct tcf_result *res, bool compat_mode)
+{
+ return TC_ACT_UNSPEC;
+}
+
#endif
static inline unsigned long
@@ -249,7 +268,8 @@
static inline void
tcf_exts_stats_update(const struct tcf_exts *exts,
- u64 bytes, u64 packets, u64 lastuse)
+ u64 bytes, u64 packets, u64 drops, u64 lastuse,
+ u8 used_hw_stats, bool used_hw_stats_valid)
{
#ifdef CONFIG_NET_CLS_ACT
int i;
@@ -259,7 +279,10 @@
for (i = 0; i < exts->nr_actions; i++) {
struct tc_action *a = exts->actions[i];
- tcf_action_stats_update(a, bytes, packets, lastuse, true);
+ tcf_action_stats_update(a, bytes, packets, drops,
+ lastuse, true);
+ a->used_hw_stats = used_hw_stats;
+ a->used_hw_stats_valid = used_hw_stats_valid;
}
preempt_enable();
@@ -309,6 +332,7 @@
void tcf_exts_destroy(struct tcf_exts *exts);
void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src);
int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts);
+int tcf_exts_terse_dump(struct sk_buff *skb, struct tcf_exts *exts);
int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts);
/**
@@ -489,12 +513,16 @@
struct net_device *dev;
if (nla_strlcpy(indev, indev_tlv, IFNAMSIZ) >= IFNAMSIZ) {
- NL_SET_ERR_MSG(extack, "Interface name too long");
+ NL_SET_ERR_MSG_ATTR(extack, indev_tlv,
+ "Interface name too long");
return -EINVAL;
}
dev = __dev_get_by_name(net, indev);
- if (!dev)
+ if (!dev) {
+ NL_SET_ERR_MSG_ATTR(extack, indev_tlv,
+ "Network device not found");
return -ENODEV;
+ }
return dev->ifindex;
}
@@ -509,7 +537,7 @@
}
int tc_setup_flow_action(struct flow_action *flow_action,
- const struct tcf_exts *exts, bool rtnl_held);
+ const struct tcf_exts *exts);
void tc_cleanup_flow_action(struct flow_action *flow_action);
int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
@@ -531,6 +559,49 @@
void *cb_priv, u32 *flags, unsigned int *in_hw_count);
unsigned int tcf_exts_num_actions(struct tcf_exts *exts);
+#ifdef CONFIG_NET_CLS_ACT
+int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch,
+ enum flow_block_binder_type binder_type,
+ struct nlattr *block_index_attr,
+ struct netlink_ext_ack *extack);
+void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch);
+int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr,
+ struct netlink_ext_ack *extack);
+struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb,
+ struct sk_buff **to_free, int *ret);
+int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe);
+#else
+static inline int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch,
+ enum flow_block_binder_type binder_type,
+ struct nlattr *block_index_attr,
+ struct netlink_ext_ack *extack)
+{
+ return 0;
+}
+
+static inline void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch)
+{
+}
+
+static inline int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr,
+ struct netlink_ext_ack *extack)
+{
+ return 0;
+}
+
+static inline struct sk_buff *
+tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb,
+ struct sk_buff **to_free, int *ret)
+{
+ return skb;
+}
+
+static inline int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe)
+{
+ return 0;
+}
+#endif
+
struct tc_cls_u32_knode {
struct tcf_exts *exts;
struct tcf_result *res;
@@ -638,6 +709,17 @@
cls_common->extack = extack;
}
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb)
+{
+ struct tc_skb_ext *tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT);
+
+ if (tc_skb_ext)
+ memset(tc_skb_ext, 0, sizeof(*tc_skb_ext));
+ return tc_skb_ext;
+}
+#endif
+
enum tc_matchall_command {
TC_CLSMATCHALL_REPLACE,
TC_CLSMATCHALL_DESTROY,
@@ -727,6 +809,7 @@
u32 limit;
bool is_ecn;
bool is_harddrop;
+ bool is_nodrop;
struct gnet_stats_queue *qstats;
};
@@ -796,9 +879,8 @@
struct tc_prio_qopt_offload_params {
int bands;
u8 priomap[TC_PRIO_MAX + 1];
- /* In case that a prio qdisc is offloaded and now is changed to a
- * non-offloadedable config, it needs to update the backlog & qlen
- * values to negate the HW backlog & qlen values (and only them).
+ /* At the point of un-offloading the Qdisc, the reported backlog and
+ * qlen need to be reduced by the portion that is in HW.
*/
struct gnet_stats_queue *qstats;
};
@@ -829,4 +911,72 @@
bool ingress;
};
+enum tc_ets_command {
+ TC_ETS_REPLACE,
+ TC_ETS_DESTROY,
+ TC_ETS_STATS,
+ TC_ETS_GRAFT,
+};
+
+struct tc_ets_qopt_offload_replace_params {
+ unsigned int bands;
+ u8 priomap[TC_PRIO_MAX + 1];
+ unsigned int quanta[TCQ_ETS_MAX_BANDS]; /* 0 for strict bands. */
+ unsigned int weights[TCQ_ETS_MAX_BANDS];
+ struct gnet_stats_queue *qstats;
+};
+
+struct tc_ets_qopt_offload_graft_params {
+ u8 band;
+ u32 child_handle;
+};
+
+struct tc_ets_qopt_offload {
+ enum tc_ets_command command;
+ u32 handle;
+ u32 parent;
+ union {
+ struct tc_ets_qopt_offload_replace_params replace_params;
+ struct tc_qopt_offload_stats stats;
+ struct tc_ets_qopt_offload_graft_params graft_params;
+ };
+};
+
+enum tc_tbf_command {
+ TC_TBF_REPLACE,
+ TC_TBF_DESTROY,
+ TC_TBF_STATS,
+};
+
+struct tc_tbf_qopt_offload_replace_params {
+ struct psched_ratecfg rate;
+ u32 max_size;
+ struct gnet_stats_queue *qstats;
+};
+
+struct tc_tbf_qopt_offload {
+ enum tc_tbf_command command;
+ u32 handle;
+ u32 parent;
+ union {
+ struct tc_tbf_qopt_offload_replace_params replace_params;
+ struct tc_qopt_offload_stats stats;
+ };
+};
+
+enum tc_fifo_command {
+ TC_FIFO_REPLACE,
+ TC_FIFO_DESTROY,
+ TC_FIFO_STATS,
+};
+
+struct tc_fifo_qopt_offload {
+ enum tc_fifo_command command;
+ u32 handle;
+ u32 parent;
+ union {
+ struct tc_qopt_offload_stats stats;
+ };
+};
+
#endif
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index b16f923..7e58b44 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -11,6 +11,7 @@
#include <uapi/linux/pkt_sched.h>
#define DEFAULT_TX_QUEUE_LEN 1000
+#define STAB_SIZE_LOG_MAX 30
struct qdisc_walker {
int stop;
@@ -19,12 +20,9 @@
int (*fn)(struct Qdisc *, unsigned long cl, struct qdisc_walker *);
};
-#define QDISC_ALIGNTO 64
-#define QDISC_ALIGN(len) (((len) + QDISC_ALIGNTO-1) & ~(QDISC_ALIGNTO-1))
-
static inline void *qdisc_priv(struct Qdisc *q)
{
- return (char *) q + QDISC_ALIGN(sizeof(struct Qdisc));
+ return &q->privdata;
}
/*
@@ -75,7 +73,15 @@
void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc,
clockid_t clockid);
void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc);
-void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires);
+
+void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires,
+ u64 delta_ns);
+
+static inline void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd,
+ u64 expires)
+{
+ return qdisc_watchdog_schedule_range_ns(wd, expires, 0ULL);
+}
static inline void qdisc_watchdog_schedule(struct qdisc_watchdog *wd,
psched_time_t expires)
@@ -165,7 +171,7 @@
u64 cycle_time_extension;
size_t num_entries;
- struct tc_taprio_sched_entry entries[0];
+ struct tc_taprio_sched_entry entries[];
};
/* Reference counting */
diff --git a/include/net/red.h b/include/net/red.h
index ff07a7c..cc9f6b0 100644
--- a/include/net/red.h
+++ b/include/net/red.h
@@ -189,6 +189,44 @@
return true;
}
+static inline int red_get_flags(unsigned char qopt_flags,
+ unsigned char historic_mask,
+ struct nlattr *flags_attr,
+ unsigned char supported_mask,
+ struct nla_bitfield32 *p_flags,
+ unsigned char *p_userbits,
+ struct netlink_ext_ack *extack)
+{
+ struct nla_bitfield32 flags;
+
+ if (qopt_flags && flags_attr) {
+ NL_SET_ERR_MSG_MOD(extack, "flags should be passed either through qopt, or through a dedicated attribute");
+ return -EINVAL;
+ }
+
+ if (flags_attr) {
+ flags = nla_get_bitfield32(flags_attr);
+ } else {
+ flags.selector = historic_mask;
+ flags.value = qopt_flags & historic_mask;
+ }
+
+ *p_flags = flags;
+ *p_userbits = qopt_flags & ~historic_mask;
+ return 0;
+}
+
+static inline int red_validate_flags(unsigned char flags,
+ struct netlink_ext_ack *extack)
+{
+ if ((flags & TC_RED_NODROP) && !(flags & TC_RED_ECN)) {
+ NL_SET_ERR_MSG_MOD(extack, "nodrop mode is only meaningful with ECN");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static inline void red_set_parms(struct red_parms *p,
u32 qth_min, u32 qth_max, u8 Wlog, u8 Plog,
u8 Scell_log, u8 *stab, u32 max_P)
diff --git a/include/net/regulatory.h b/include/net/regulatory.h
index 3469750..47f06f6 100644
--- a/include/net/regulatory.h
+++ b/include/net/regulatory.h
@@ -44,7 +44,7 @@
* and potentially inform users of which devices specifically
* cased the conflicts.
* @initiator: indicates who sent this request, could be any of
- * of those set in nl80211_reg_initiator (%NL80211_REGDOM_SET_BY_*)
+ * those set in nl80211_reg_initiator (%NL80211_REGDOM_SET_BY_*)
* @alpha2: the ISO / IEC 3166 alpha2 country code of the requested
* regulatory domain. We have a few special codes:
* 00 - World regulatory domain
@@ -231,13 +231,6 @@
struct ieee80211_reg_rule reg_rules[];
};
-#define MHZ_TO_KHZ(freq) ((freq) * 1000)
-#define KHZ_TO_MHZ(freq) ((freq) / 1000)
-#define DBI_TO_MBI(gain) ((gain) * 100)
-#define MBI_TO_DBI(gain) ((gain) / 100)
-#define DBM_TO_MBM(gain) ((gain) * 100)
-#define MBM_TO_DBM(gain) ((gain) / 100)
-
#define REG_RULE_EXT(start, end, bw, gain, eirp, dfs_cac, reg_flags) \
{ \
.freq_range.start_freq_khz = MHZ_TO_KHZ(start), \
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index cf8b332..29e41ff 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -41,6 +41,13 @@
int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req);
+struct saved_syn {
+ u32 mac_hdrlen;
+ u32 network_hdrlen;
+ u32 tcp_hdrlen;
+ u8 data[];
+};
+
/* struct request_sock - mini sock to represent a connection request
*/
struct request_sock {
@@ -54,13 +61,13 @@
struct request_sock *dl_next;
u16 mss;
u8 num_retrans; /* number of retransmits */
- u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */
+ u8 syncookie:1; /* syncookie: encode tcpopts in timestamp */
u8 num_timeout:7; /* number of timeouts */
u32 ts_recent;
struct timer_list rsk_timer;
const struct request_sock_ops *rsk_ops;
struct sock *sk;
- u32 *saved_syn;
+ struct saved_syn *saved_syn;
u32 secid;
u32 peer_secid;
};
diff --git a/include/net/route.h b/include/net/route.h
index 6c51684..a07c277 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -128,6 +128,12 @@
struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
const struct sock *sk);
+struct rtable *ip_route_output_tunnel(struct sk_buff *skb,
+ struct net_device *dev,
+ struct net *net, __be32 *saddr,
+ const struct ip_tunnel_info *info,
+ u8 protocol, bool use_cache);
+
struct dst_entry *ipv4_blackhole_route(struct net *net,
struct dst_entry *dst_orig);
@@ -185,6 +191,10 @@
u8 tos, struct net_device *devin,
struct fib_result *res);
+int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src,
+ u8 tos, struct net_device *devin,
+ const struct sk_buff *hint);
+
static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
u8 tos, struct net_device *devin)
{
@@ -221,7 +231,7 @@
void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
struct rtable *rt_dst_alloc(struct net_device *dev,
unsigned int flags, u16 type,
- bool nopolicy, bool noxfrm, bool will_cache);
+ bool nopolicy, bool noxfrm);
struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt);
struct in_ifaddr;
@@ -359,7 +369,7 @@
{
struct neighbour *neigh;
- neigh = __ipv4_neigh_lookup_noref(dev, daddr);
+ neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)daddr);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &daddr, dev, false);
diff --git a/include/net/rpl.h b/include/net/rpl.h
new file mode 100644
index 0000000..308ef0a
--- /dev/null
+++ b/include/net/rpl.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * RPL implementation
+ *
+ * Author:
+ * (C) 2020 Alexander Aring <alex.aring@gmail.com>
+ */
+
+#ifndef _NET_RPL_H
+#define _NET_RPL_H
+
+#include <linux/rpl.h>
+
+#if IS_ENABLED(CONFIG_IPV6_RPL_LWTUNNEL)
+extern int rpl_init(void);
+extern void rpl_exit(void);
+#else
+static inline int rpl_init(void)
+{
+ return 0;
+}
+
+static inline void rpl_exit(void) {}
+#endif
+
+/* Worst decompression memory usage ipv6 address (16) + pad 7 */
+#define IPV6_RPL_SRH_WORST_SWAP_SIZE (sizeof(struct in6_addr) + 7)
+
+size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri,
+ unsigned char cmpre);
+
+void ipv6_rpl_srh_decompress(struct ipv6_rpl_sr_hdr *outhdr,
+ const struct ipv6_rpl_sr_hdr *inhdr,
+ const struct in6_addr *daddr, unsigned char n);
+
+void ipv6_rpl_srh_compress(struct ipv6_rpl_sr_hdr *outhdr,
+ const struct ipv6_rpl_sr_hdr *inhdr,
+ const struct in6_addr *daddr, unsigned char n);
+
+#endif /* _NET_RPL_H */
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 0cb0a4b..1042c44 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -92,7 +92,7 @@
struct net_rate_estimator __rcu *rate_est;
struct gnet_stats_basic_cpu __percpu *cpu_bstats;
struct gnet_stats_queue __percpu *cpu_qstats;
- int padded;
+ int pad;
refcount_t refcnt;
/*
@@ -113,6 +113,9 @@
/* for NOLOCK qdisc, true if there are no enqueued skbs */
bool empty;
struct rcu_head rcu;
+
+ /* private data */
+ long privdata[] ____cacheline_aligned;
};
static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
@@ -299,6 +302,8 @@
struct netlink_ext_ack *extack);
void (*attach)(struct Qdisc *sch);
int (*change_tx_queue_len)(struct Qdisc *, unsigned int);
+ void (*change_real_num_tx)(struct Qdisc *sch,
+ unsigned int new_real_tx);
int (*dump)(struct Qdisc *, struct sk_buff *);
int (*dump_stats)(struct Qdisc *, struct gnet_dump *);
@@ -375,6 +380,10 @@
int (*dump)(struct net*, struct tcf_proto*, void *,
struct sk_buff *skb, struct tcmsg*,
bool);
+ int (*terse_dump)(struct net *net,
+ struct tcf_proto *tp, void *fh,
+ struct sk_buff *skb,
+ struct tcmsg *t, bool rtnl_held);
int (*tmplt_dump)(struct sk_buff *skb,
struct net *net,
void *tmplt_priv);
@@ -425,6 +434,7 @@
};
#define QDISC_CB_PRIV_LEN 20
unsigned char data[QDISC_CB_PRIV_LEN];
+ u16 mru;
};
typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
@@ -504,7 +514,7 @@
{
struct qdisc_skb_cb *qcb;
- BUILD_BUG_ON(sizeof(skb->cb) < offsetof(struct qdisc_skb_cb, data) + sz);
+ BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*qcb));
BUILD_BUG_ON(sizeof(qcb->data) < sz);
}
@@ -675,6 +685,8 @@
void qdisc_class_hash_destroy(struct Qdisc_class_hash *);
int dev_qdisc_change_tx_queue_len(struct net_device *dev);
+void dev_qdisc_change_real_num_tx(struct net_device *dev,
+ unsigned int new_real_tx);
void dev_init_scheduler(struct net_device *dev);
void dev_shutdown(struct net_device *dev);
void dev_activate(struct net_device *dev);
@@ -756,11 +768,6 @@
}
}
-static inline void qdisc_reset_all_tx(struct net_device *dev)
-{
- qdisc_reset_all_tx_gt(dev, 0);
-}
-
/* Are all TX queues of the device empty? */
static inline bool qdisc_all_tx_empty(const struct net_device *dev)
{
@@ -1092,12 +1099,6 @@
return 0;
}
-static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch,
- struct sk_buff **to_free)
-{
- return __qdisc_queue_drop_head(sch, &sch->q, to_free);
-}
-
static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch)
{
const struct qdisc_skb_head *qh = &sch->q;
@@ -1260,6 +1261,7 @@
u64 rate_bytes_ps; /* bytes per second */
u32 mult;
u16 overhead;
+ u16 mpu;
u8 linklayer;
u8 shift;
};
@@ -1269,6 +1271,9 @@
{
len += r->overhead;
+ if (len < r->mpu)
+ len = r->mpu;
+
if (unlikely(r->linklayer == TC_LINKLAYER_ATM))
return ((u64)(DIV_ROUND_UP(len,48)*53) * r->mult) >> r->shift;
@@ -1291,6 +1296,7 @@
res->rate = min_t(u64, r->rate_bytes_ps, ~0U);
res->overhead = r->overhead;
+ res->mpu = r->mpu;
res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
}
@@ -1299,6 +1305,7 @@
*/
struct mini_Qdisc {
struct tcf_proto *filter_list;
+ struct tcf_block *block;
struct gnet_stats_basic_cpu __percpu *cpu_bstats;
struct gnet_stats_queue __percpu *cpu_qstats;
struct rcu_head rcu;
@@ -1325,18 +1332,12 @@
struct tcf_proto *tp_head);
void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
struct mini_Qdisc __rcu **p_miniq);
+void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp,
+ struct tcf_block *block);
-static inline void skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res)
+static inline int skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res)
{
- struct gnet_stats_queue *stats = res->qstats;
- int ret;
-
- if (res->ingress)
- ret = netif_receive_skb(skb);
- else
- ret = dev_queue_xmit(skb);
- if (ret && stats)
- qstats_overlimit_inc(res->qstats);
+ return res->ingress ? netif_receive_skb(skb) : dev_queue_xmit(skb);
}
#endif
diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 8c6b04f..1ad049a 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -286,6 +286,18 @@
* functions simpler to write.
*/
+/* These are the values for pf exposure, UNUSED is to keep compatible with old
+ * applications by default.
+ */
+enum {
+ SCTP_PF_EXPOSE_UNSET,
+ SCTP_PF_EXPOSE_DISABLE,
+ SCTP_PF_EXPOSE_ENABLE,
+};
+#define SCTP_PF_EXPOSE_MAX SCTP_PF_EXPOSE_ENABLE
+
+#define SCTP_PS_RETRANS_MAX 0xffff
+
/* These return values describe the success or failure of a number of
* routines which form the lower interface to SCTP_outqueue.
*/
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 3ab5c6b..33475d0 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -103,6 +103,7 @@
int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *);
struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *);
+typedef int (*sctp_callback_t)(struct sctp_endpoint *, struct sctp_transport *, void *);
void sctp_transport_walk_start(struct rhashtable_iter *iter);
void sctp_transport_walk_stop(struct rhashtable_iter *iter);
struct sctp_transport *sctp_transport_get_next(struct net *net,
@@ -113,9 +114,8 @@
struct net *net,
const union sctp_addr *laddr,
const union sctp_addr *paddr, void *p);
-int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
- int (*cb_done)(struct sctp_transport *, void *),
- struct net *net, int *pos, void *p);
+int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done,
+ struct net *net, int *pos, void *p);
int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p);
int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
struct sctp_info *info);
@@ -291,7 +291,7 @@
#define SCTP_DBG_OBJCNT(name) \
atomic_t sctp_dbg_objcnt_## name = ATOMIC_INIT(0)
-/* Macro to help create new entries in in the global array of
+/* Macro to help create new entries in the global array of
* objcnt counters.
*/
#define SCTP_DBG_OBJCNT_ENTRY(name) \
@@ -412,7 +412,7 @@
/* Tests if the list has one and only one entry. */
static inline int sctp_list_single_entry(struct list_head *head)
{
- return (head->next != head) && (head->next == head->prev);
+ return list_is_singular(head);
}
static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk)
@@ -615,4 +615,11 @@
return sock_flag(sk, SOCK_DEAD) || sk->sk_socket;
}
+static inline void sctp_sock_set_nodelay(struct sock *sk)
+{
+ lock_sock(sk);
+ sctp_sk(sk)->nodelay = true;
+ release_sock(sk);
+}
+
#endif /* __net_sctp_h__ */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index fd7c3f7..be9ff04 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -184,7 +184,8 @@
__u32 flowlabel;
__u8 dscp;
- int pf_retrans;
+ __u16 pf_retrans;
+ __u16 ps_retrans;
/* The initial Path MTU to use for new associations. */
__u32 pathmtu;
@@ -215,6 +216,7 @@
__u32 adaptation_ind;
__u32 pd_point;
__u16 nodelay:1,
+ pf_expose:2,
reuse:1,
disable_fragments:1,
v4mapped:1,
@@ -326,7 +328,7 @@
* the association TCB is re-constructed from the cookie.
*/
__u32 raw_addr_list_len;
- struct sctp_init_chunk peer_init[0];
+ struct sctp_init_chunk peer_init[];
};
@@ -431,23 +433,13 @@
int (*setsockopt) (struct sock *sk,
int level,
int optname,
- char __user *optval,
+ sockptr_t optval,
unsigned int optlen);
int (*getsockopt) (struct sock *sk,
int level,
int optname,
char __user *optval,
int __user *optlen);
- int (*compat_setsockopt) (struct sock *sk,
- int level,
- int optname,
- char __user *optval,
- unsigned int optlen);
- int (*compat_getsockopt) (struct sock *sk,
- int level,
- int optname,
- char __user *optval,
- int __user *optlen);
void (*get_dst) (struct sctp_transport *t,
union sctp_addr *saddr,
struct flowi *fl,
@@ -898,7 +890,9 @@
* and will be initialized from the assocs value. This can be changed
* using the SCTP_PEER_ADDR_THLDS socket option
*/
- int pf_retrans;
+ __u16 pf_retrans;
+ /* Used for primary path switchover. */
+ __u16 ps_retrans;
/* PMTU : The current known path MTU. */
__u32 pathmtu;
@@ -1345,6 +1339,7 @@
u32 secid;
u32 peer_secid;
+ struct rcu_head rcu;
};
/* Recover the outter endpoint structure. */
@@ -1360,7 +1355,7 @@
struct sctp_endpoint *sctp_endpoint_new(struct sock *, gfp_t);
void sctp_endpoint_free(struct sctp_endpoint *);
void sctp_endpoint_put(struct sctp_endpoint *);
-void sctp_endpoint_hold(struct sctp_endpoint *);
+int sctp_endpoint_hold(struct sctp_endpoint *ep);
void sctp_endpoint_add_asoc(struct sctp_endpoint *, struct sctp_association *);
struct sctp_association *sctp_endpoint_lookup_assoc(
const struct sctp_endpoint *ep,
@@ -1396,7 +1391,7 @@
struct list_head prio_sched;
/* List of streams scheduled */
struct list_head active;
- /* The next stream stream in line */
+ /* The next stream in line */
struct sctp_stream_out_ext *next;
__u16 prio;
};
@@ -1458,7 +1453,7 @@
struct {
/* List of streams scheduled */
struct list_head rr_list;
- /* The next stream stream in line */
+ /* The next stream in line */
struct sctp_stream_out_ext *rr_next;
};
};
@@ -1768,7 +1763,7 @@
int max_burst;
/* This is the max_retrans value for the association. This value will
- * be initialized initialized from system defaults, but can be
+ * be initialized from system defaults, but can be
* modified by the SCTP_ASSOCINFO socket option.
*/
int max_retrans;
@@ -1777,7 +1772,9 @@
* and will be initialized from the assocs value. This can be
* changed using the SCTP_PEER_ADDR_THLDS socket option
*/
- int pf_retrans;
+ __u16 pf_retrans;
+ /* Used for primary path switchover. */
+ __u16 ps_retrans;
/* Maximum number of times the endpoint will retransmit INIT */
__u16 max_init_attempts;
@@ -2058,6 +2055,7 @@
__u8 need_ecne:1, /* Need to send an ECNE Chunk? */
temp:1, /* Is it a temporary association? */
+ pf_expose:2, /* Expose pf state? */
force_delay:1;
__u8 strreset_enable;
diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h
index e1a92c4..994e984 100644
--- a/include/net/sctp/ulpevent.h
+++ b/include/net/sctp/ulpevent.h
@@ -80,13 +80,8 @@
struct sctp_chunk *chunk,
gfp_t gfp);
-struct sctp_ulpevent *sctp_ulpevent_make_peer_addr_change(
- const struct sctp_association *asoc,
- const struct sockaddr_storage *aaddr,
- int flags,
- int state,
- int error,
- gfp_t gfp);
+void sctp_ulpevent_notify_peer_addr_change(struct sctp_transport *transport,
+ int state, int error);
struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
const struct sctp_association *asoc,
@@ -100,6 +95,13 @@
__u32 error,
gfp_t gfp);
+struct sctp_ulpevent *sctp_ulpevent_make_send_failed_event(
+ const struct sctp_association *asoc,
+ struct sctp_chunk *chunk,
+ __u16 flags,
+ __u32 error,
+ gfp_t gfp);
+
struct sctp_ulpevent *sctp_ulpevent_make_shutdown_event(
const struct sctp_association *asoc,
__u16 flags,
diff --git a/include/net/seg6.h b/include/net/seg6.h
index 640724b..9d19c15 100644
--- a/include/net/seg6.h
+++ b/include/net/seg6.h
@@ -57,7 +57,7 @@
extern int seg6_local_init(void);
extern void seg6_local_exit(void);
-extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len);
+extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced);
extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh,
int proto);
extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh);
diff --git a/include/net/smc.h b/include/net/smc.h
index bd9c0fb..e441aa9 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -37,6 +37,10 @@
#define ISM_EVENT_GID 1
#define ISM_EVENT_SWR 2
+#define ISM_RESERVED_VLANID 0x1FFF
+
+#define ISM_ERROR 0xFFFF
+
struct smcd_event {
u32 type;
u32 code;
@@ -61,6 +65,8 @@
int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx,
bool sf, unsigned int offset, void *data,
unsigned int size);
+ void (*get_system_eid)(struct smcd_dev *dev, u8 **eid);
+ u16 (*get_chid)(struct smcd_dev *dev);
};
struct smcd_dev {
@@ -75,6 +81,11 @@
struct workqueue_struct *event_wq;
u8 pnetid[SMC_MAX_PNETID_LEN];
bool pnetid_by_user;
+ struct list_head lgr_list;
+ spinlock_t lgr_lock;
+ atomic_t lgr_cnt;
+ wait_queue_head_t lgrs_deleted;
+ u8 going_away : 1;
};
struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
diff --git a/include/net/snmp.h b/include/net/snmp.h
index cb8ced4..468a678 100644
--- a/include/net/snmp.h
+++ b/include/net/snmp.h
@@ -111,6 +111,12 @@
unsigned long mibs[LINUX_MIB_XFRMMAX];
};
+/* Linux TLS */
+#define LINUX_MIB_TLSMAX __LINUX_MIB_TLSMAX
+struct linux_tls_mib {
+ unsigned long mibs[LINUX_MIB_TLSMAX];
+};
+
#define DEFINE_SNMP_STAT(type, name) \
__typeof__(type) __percpu *name
#define DEFINE_SNMP_STAT_ATOMIC(type, name) \
diff --git a/include/net/sock.h b/include/net/sock.h
index d3dd89b..2c11eb4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -59,6 +59,7 @@
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
#include <linux/poll.h>
+#include <linux/sockptr.h>
#include <linux/atomic.h>
#include <linux/refcount.h>
@@ -66,7 +67,6 @@
#include <net/checksum.h>
#include <net/tcp_states.h>
#include <linux/net_tstamp.h>
-#include <net/smc.h>
#include <net/l3mdev.h>
/*
@@ -118,19 +118,26 @@
* struct sock_common - minimal network layer representation of sockets
* @skc_daddr: Foreign IPv4 addr
* @skc_rcv_saddr: Bound local IPv4 addr
+ * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr
* @skc_hash: hash value used with various protocol lookup tables
* @skc_u16hashes: two u16 hash values used by UDP lookup tables
* @skc_dport: placeholder for inet_dport/tw_dport
* @skc_num: placeholder for inet_num/tw_num
+ * @skc_portpair: __u32 union of @skc_dport & @skc_num
* @skc_family: network address family
* @skc_state: Connection state
* @skc_reuse: %SO_REUSEADDR setting
* @skc_reuseport: %SO_REUSEPORT setting
+ * @skc_ipv6only: socket is IPV6 only
+ * @skc_net_refcnt: socket is using net ref counting
* @skc_bound_dev_if: bound device index if != 0
* @skc_bind_node: bind hash linkage for various protocol lookup tables
* @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
* @skc_prot: protocol handlers inside a network family
* @skc_net: reference to the network namespace of this socket
+ * @skc_v6_daddr: IPV6 destination address
+ * @skc_v6_rcv_saddr: IPV6 source address
+ * @skc_cookie: socket's cookie value
* @skc_node: main hash linkage for various protocol lookup tables
* @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
* @skc_tx_queue_mapping: tx queue number for this connection
@@ -138,7 +145,15 @@
* @skc_flags: place holder for sk_flags
* %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
* %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
+ * @skc_listener: connection request listener socket (aka rsk_listener)
+ * [union with @skc_flags]
+ * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row
+ * [union with @skc_flags]
* @skc_incoming_cpu: record/match cpu processing incoming packets
+ * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled)
+ * [union with @skc_incoming_cpu]
+ * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number
+ * [union with @skc_incoming_cpu]
* @skc_refcnt: reference count
*
* This is the minimal network layer representation of sockets, the header
@@ -231,7 +246,7 @@
/* public: */
};
-struct bpf_sk_storage;
+struct bpf_local_storage;
/**
* struct sock - network layer representation of sockets
@@ -246,6 +261,7 @@
* @sk_dst_cache: destination cache
* @sk_dst_pending_confirm: need to confirm neighbour
* @sk_policy: flow policy
+ * @sk_rx_skb_cache: cache copy of recently accessed RX skb
* @sk_receive_queue: incoming packets
* @sk_wmem_alloc: transmit queue bytes committed
* @sk_tsq_flags: TCP Small Queues flags
@@ -266,6 +282,8 @@
* @sk_no_check_rx: allow zero checksum in RX packets
* @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
* @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
+ * @sk_route_forced_caps: static, forced route capabilities
+ * (set in tcp_init_sock())
* @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
* @sk_gso_max_size: Maximum GSO segment size to build
* @sk_gso_max_segs: Maximum number of GSO segments
@@ -304,6 +322,8 @@
* @sk_frag: cached page frag
* @sk_peek_off: current peek_offset value
* @sk_send_head: front of stuff to transmit
+ * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head]
+ * @sk_tx_skb_cache: cache copy of recently accessed TX skb
* @sk_security: used by security modules
* @sk_mark: generic packet mark
* @sk_cgrp_data: cgroup data for this cgroup
@@ -314,11 +334,14 @@
* @sk_write_space: callback to indicate there is bf sending space available
* @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
* @sk_backlog_rcv: callback to process the backlog
+ * @sk_validate_xmit_skb: ptr to an optional validate function
* @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
* @sk_reuseport_cb: reuseport group container
+ * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage
* @sk_rcu: used during RCU grace period
* @sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
* @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
+ * @sk_txtime_report_errors: set report errors mode for SO_TXTIME
* @sk_txtime_unused: unused txtime flags
*/
struct sock {
@@ -394,7 +417,9 @@
struct sk_filter __rcu *sk_filter;
union {
struct socket_wq __rcu *sk_wq;
+ /* private: */
struct socket_wq *sk_wq_raw;
+ /* public: */
};
#ifdef CONFIG_XFRM
struct xfrm_policy __rcu *sk_policy[2];
@@ -437,31 +462,15 @@
* Because of non atomicity rules, all
* changes are protected by socket lock.
*/
- unsigned int __sk_flags_offset[0];
-#ifdef __BIG_ENDIAN_BITFIELD
-#define SK_FL_PROTO_SHIFT 16
-#define SK_FL_PROTO_MASK 0x00ff0000
-
-#define SK_FL_TYPE_SHIFT 0
-#define SK_FL_TYPE_MASK 0x0000ffff
-#else
-#define SK_FL_PROTO_SHIFT 8
-#define SK_FL_PROTO_MASK 0x0000ff00
-
-#define SK_FL_TYPE_SHIFT 16
-#define SK_FL_TYPE_MASK 0xffff0000
-#endif
-
- unsigned int sk_padding : 1,
+ u8 sk_padding : 1,
sk_kern_sock : 1,
sk_no_check_tx : 1,
sk_no_check_rx : 1,
- sk_userlocks : 4,
- sk_protocol : 8,
- sk_type : 16;
-#define SK_PROTOCOL_MAX U8_MAX
- u16 sk_gso_max_segs;
+ sk_userlocks : 4;
u8 sk_pacing_shift;
+ u16 sk_type;
+ u16 sk_protocol;
+ u16 sk_gso_max_segs;
unsigned long sk_lingertime;
struct proto *sk_prot_creator;
rwlock_t sk_callback_lock;
@@ -470,8 +479,10 @@
u32 sk_ack_backlog;
u32 sk_max_ack_backlog;
kuid_t sk_uid;
+ spinlock_t sk_peer_lock;
struct pid *sk_peer_pid;
const struct cred *sk_peer_cred;
+
long sk_rcvtimeo;
ktime_t sk_stamp;
#if BITS_PER_LONG==32
@@ -508,7 +519,7 @@
void (*sk_destruct)(struct sock *sk);
struct sock_reuseport __rcu *sk_reuseport_cb;
#ifdef CONFIG_BPF_SYSCALL
- struct bpf_sk_storage __rcu *sk_bpf_storage;
+ struct bpf_local_storage __rcu *sk_bpf_storage;
#endif
struct rcu_head sk_rcu;
};
@@ -519,10 +530,44 @@
SK_PACING_FQ = 2,
};
+/* Pointer stored in sk_user_data might not be suitable for copying
+ * when cloning the socket. For instance, it can point to a reference
+ * counted object. sk_user_data bottom bit is set if pointer must not
+ * be copied.
+ */
+#define SK_USER_DATA_NOCOPY 1UL
+#define SK_USER_DATA_BPF 2UL /* Managed by BPF */
+#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF)
+
+/**
+ * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied
+ * @sk: socket
+ */
+static inline bool sk_user_data_is_nocopy(const struct sock *sk)
+{
+ return ((uintptr_t)sk->sk_user_data & SK_USER_DATA_NOCOPY);
+}
+
#define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
-#define rcu_dereference_sk_user_data(sk) rcu_dereference(__sk_user_data((sk)))
-#define rcu_assign_sk_user_data(sk, ptr) rcu_assign_pointer(__sk_user_data((sk)), ptr)
+#define rcu_dereference_sk_user_data(sk) \
+({ \
+ void *__tmp = rcu_dereference(__sk_user_data((sk))); \
+ (void *)((uintptr_t)__tmp & SK_USER_DATA_PTRMASK); \
+})
+#define rcu_assign_sk_user_data(sk, ptr) \
+({ \
+ uintptr_t __tmp = (uintptr_t)(ptr); \
+ WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \
+ rcu_assign_pointer(__sk_user_data((sk)), __tmp); \
+})
+#define rcu_assign_sk_user_data_nocopy(sk, ptr) \
+({ \
+ uintptr_t __tmp = (uintptr_t)(ptr); \
+ WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \
+ rcu_assign_pointer(__sk_user_data((sk)), \
+ __tmp | SK_USER_DATA_NOCOPY); \
+})
/*
* SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK
@@ -802,7 +847,6 @@
SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
- SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
SOCK_MEMALLOC, /* VM depends on this socket for swapping */
SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */
SOCK_FASYNC, /* fasync() active */
@@ -838,6 +882,15 @@
__clear_bit(flag, &sk->sk_flags);
}
+static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit,
+ int valbool)
+{
+ if (valbool)
+ sock_set_flag(sk, bit);
+ else
+ sock_reset_flag(sk, bit);
+}
+
static inline bool sock_flag(const struct sock *sk, enum sock_flags flag)
{
return test_bit(flag, &sk->sk_flags);
@@ -869,17 +922,17 @@
static inline void sk_acceptq_removed(struct sock *sk)
{
- sk->sk_ack_backlog--;
+ WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog - 1);
}
static inline void sk_acceptq_added(struct sock *sk)
{
- sk->sk_ack_backlog++;
+ WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1);
}
static inline bool sk_acceptq_is_full(const struct sock *sk)
{
- return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
+ return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog);
}
/*
@@ -1093,21 +1146,13 @@
void (*destroy)(struct sock *sk);
void (*shutdown)(struct sock *sk, int how);
int (*setsockopt)(struct sock *sk, int level,
- int optname, char __user *optval,
+ int optname, sockptr_t optval,
unsigned int optlen);
int (*getsockopt)(struct sock *sk, int level,
int optname, char __user *optval,
int __user *option);
void (*keepalive)(struct sock *sk, int valbool);
#ifdef CONFIG_COMPAT
- int (*compat_setsockopt)(struct sock *sk,
- int level,
- int optname, char __user *optval,
- unsigned int optlen);
- int (*compat_getsockopt)(struct sock *sk,
- int level,
- int optname, char __user *optval,
- int __user *option);
int (*compat_ioctl)(struct sock *sk,
unsigned int cmd, unsigned long arg);
#endif
@@ -1119,7 +1164,9 @@
int (*sendpage)(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
int (*bind)(struct sock *sk,
- struct sockaddr *uaddr, int addr_len);
+ struct sockaddr *addr, int addr_len);
+ int (*bind_add)(struct sock *sk,
+ struct sockaddr *addr, int addr_len);
int (*backlog_rcv) (struct sock *sk,
struct sk_buff *skb);
@@ -1167,7 +1214,7 @@
unsigned int useroffset; /* Usercopy region offset */
unsigned int usersize; /* Usercopy region size */
- struct percpu_counter *orphan_count;
+ unsigned int __percpu *orphan_count;
struct request_sock_ops *rsk_prot;
struct timewait_sock_ops *twsk_prot;
@@ -1432,7 +1479,7 @@
{
if (!sk_has_account(sk))
return true;
- return size<= sk->sk_forward_alloc ||
+ return size <= sk->sk_forward_alloc ||
__sk_mem_schedule(sk, size, SK_MEM_RECV) ||
skb_pfmemalloc(skb);
}
@@ -1480,11 +1527,11 @@
DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
{
- sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
sk_wmem_queued_add(sk, -skb->truesize);
sk_mem_uncharge(sk, skb->truesize);
if (static_branch_unlikely(&tcp_tx_skb_cache_key) &&
!sk->sk_tx_skb_cache && !skb_cloned(skb)) {
+ skb_ext_reset(skb);
skb_zcopy_clear(skb, true);
sk->sk_tx_skb_cache = skb;
return;
@@ -1498,7 +1545,7 @@
sk->sk_lock.owned = 0;
/* The sk_lock has mutex_unlock() semantics: */
- mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
+ mutex_release(&sk->sk_lock.dep_map, _RET_IP_);
}
}
@@ -1621,12 +1668,13 @@
void sock_efree(struct sk_buff *skb);
#ifdef CONFIG_INET
void sock_edemux(struct sk_buff *skb);
+void sock_pfree(struct sk_buff *skb);
#else
#define sock_edemux sock_efree
#endif
int sock_setsockopt(struct socket *sock, int level, int op,
- char __user *optval, unsigned int optlen);
+ sockptr_t optval, unsigned int optlen);
int sock_getsockopt(struct socket *sock, int level, int op,
char __user *optval, int __user *optlen);
@@ -1671,8 +1719,6 @@
int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
int sock_no_listen(struct socket *, int);
int sock_no_shutdown(struct socket *, int);
-int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *);
-int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int);
int sock_no_sendmsg(struct socket *, struct msghdr *, size_t);
int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len);
int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int);
@@ -1692,11 +1738,7 @@
int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags);
int sock_common_setsockopt(struct socket *sock, int level, int optname,
- char __user *optval, unsigned int optlen);
-int compat_sock_common_getsockopt(struct socket *sock, int level,
- int optname, char __user *optval, int __user *optlen);
-int compat_sock_common_setsockopt(struct socket *sock, int level,
- int optname, char __user *optval, unsigned int optlen);
+ sockptr_t optval, unsigned int optlen);
void sk_common_release(struct sock *sk);
@@ -1864,10 +1906,13 @@
WRITE_ONCE(sk->sk_txhash, net_tx_rndhash());
}
-static inline void sk_rethink_txhash(struct sock *sk)
+static inline bool sk_rethink_txhash(struct sock *sk)
{
- if (sk->sk_txhash)
+ if (sk->sk_txhash) {
sk_set_txhash(sk);
+ return true;
+ }
+ return false;
}
static inline struct dst_entry *
@@ -1890,12 +1935,10 @@
return dst;
}
-static inline void dst_negative_advice(struct sock *sk)
+static inline void __dst_negative_advice(struct sock *sk)
{
struct dst_entry *ndst, *dst = __sk_dst_get(sk);
- sk_rethink_txhash(sk);
-
if (dst && dst->ops->negative_advice) {
ndst = dst->ops->negative_advice(dst);
@@ -1907,6 +1950,12 @@
}
}
+static inline void dst_negative_advice(struct sock *sk)
+{
+ sk_rethink_txhash(sk);
+ __dst_negative_advice(sk);
+}
+
static inline void
__sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
@@ -2037,7 +2086,7 @@
* sk_wmem_alloc_get - returns write allocations
* @sk: socket
*
- * Returns sk_wmem_alloc minus initial offset of one
+ * Return: sk_wmem_alloc minus initial offset of one
*/
static inline int sk_wmem_alloc_get(const struct sock *sk)
{
@@ -2048,7 +2097,7 @@
* sk_rmem_alloc_get - returns read allocations
* @sk: socket
*
- * Returns sk_rmem_alloc
+ * Return: sk_rmem_alloc
*/
static inline int sk_rmem_alloc_get(const struct sock *sk)
{
@@ -2059,7 +2108,7 @@
* sk_has_allocations - check if allocations are outstanding
* @sk: socket
*
- * Returns true if socket has write or read allocations
+ * Return: true if socket has write or read allocations
*/
static inline bool sk_has_allocations(const struct sock *sk)
{
@@ -2070,7 +2119,7 @@
* skwq_has_sleeper - check if there are any waiting processes
* @wq: struct socket_wq
*
- * Returns true if socket_wq has waiting processes
+ * Return: true if socket_wq has waiting processes
*
* The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory
* barrier call. They were added due to the race found within the tcp code.
@@ -2170,6 +2219,8 @@
void sk_stop_timer(struct sock *sk, struct timer_list *timer);
+void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer);
+
int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue,
struct sk_buff *skb, unsigned int flags,
void (*destructor)(struct sock *sk,
@@ -2187,8 +2238,13 @@
static inline int sock_error(struct sock *sk)
{
int err;
- if (likely(!sk->sk_err))
+
+ /* Avoid an atomic operation for the common case.
+ * This is racy since another cpu/thread can change sk_err under us.
+ */
+ if (likely(data_race(!sk->sk_err)))
return 0;
+
err = xchg(&sk->sk_err, 0);
return -err;
}
@@ -2266,16 +2322,22 @@
* @sk: socket
*
* Use the per task page_frag instead of the per socket one for
- * optimization when we know that we're in the normal context and owns
+ * optimization when we know that we're in process context and own
* everything that's associated with %current.
*
- * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest
- * inside other socket operations and end up recursing into sk_page_frag()
- * while it's already in use.
+ * Both direct reclaim and page faults can nest inside other
+ * socket operations and end up recursing into sk_page_frag()
+ * while it's already in use: explicitly avoid task page_frag
+ * usage if the caller is potentially doing any of them.
+ * This assumes that page fault handlers use the GFP_NOFS flags.
+ *
+ * Return: a per task page_frag if context allows that,
+ * otherwise a per socket one.
*/
static inline struct page_frag *sk_page_frag(struct sock *sk)
{
- if (gfpflags_normal_context(sk->sk_allocation))
+ if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) ==
+ (__GFP_DIRECT_RECLAIM | __GFP_FS))
return ¤t->task_frag;
return &sk->sk_frag;
@@ -2329,7 +2391,7 @@
* using skb->cb[] would keep using it directly and utilize its
* alignement guarantee.
*/
-#define SOCK_SKB_CB_OFFSET ((FIELD_SIZEOF(struct sk_buff, cb) - \
+#define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \
sizeof(struct sock_skb_cb)))
#define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \
@@ -2466,6 +2528,7 @@
&skb_shinfo(skb)->tskey);
}
+DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
/**
* sk_eat_skb - Release a skb if it is no longer needed
* @sk: socket to eat this skb from
@@ -2474,7 +2537,6 @@
* This routine must be called with interrupts disabled or with the socket
* locked so that the sk_buff queue operation is ok.
*/
-DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
{
__skb_unlink(skb, &sk->sk_receive_queue);
@@ -2499,16 +2561,14 @@
write_pnet(&sk->sk_net, net);
}
-static inline struct sock *skb_steal_sock(struct sk_buff *skb)
+static inline bool
+skb_sk_is_prefetched(struct sk_buff *skb)
{
- if (skb->sk) {
- struct sock *sk = skb->sk;
-
- skb->destructor = NULL;
- skb->sk = NULL;
- return sk;
- }
- return NULL;
+#ifdef CONFIG_INET
+ return skb->destructor == sock_pfree;
+#else
+ return false;
+#endif /* CONFIG_INET */
}
/* This helper checks if a socket is a full socket,
@@ -2519,6 +2579,35 @@
return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
}
+static inline bool
+sk_is_refcounted(struct sock *sk)
+{
+ /* Only full sockets have sk->sk_flags. */
+ return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE);
+}
+
+/**
+ * skb_steal_sock - steal a socket from an sk_buff
+ * @skb: sk_buff to steal the socket from
+ * @refcounted: is set to true if the socket is reference-counted
+ */
+static inline struct sock *
+skb_steal_sock(struct sk_buff *skb, bool *refcounted)
+{
+ if (skb->sk) {
+ struct sock *sk = skb->sk;
+
+ *refcounted = true;
+ if (skb_sk_is_prefetched(skb))
+ *refcounted = sk_is_refcounted(sk);
+ skb->destructor = NULL;
+ skb->sk = NULL;
+ return sk;
+ }
+ *refcounted = false;
+ return NULL;
+}
+
/* Checks if this SKB belongs to an HW offloaded socket
* and whether any SW fallbacks are required based on dev.
* Check decrypted mark in case skb_orphan() cleared socket.
@@ -2551,7 +2640,7 @@
return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV);
}
-void sock_enable_timestamp(struct sock *sk, int flag);
+void sock_enable_timestamp(struct sock *sk, enum sock_flags flag);
int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level,
int type);
@@ -2581,6 +2670,7 @@
extern __u32 sysctl_wmem_default;
extern __u32 sysctl_rmem_default;
+#define SKB_FRAG_PAGE_ORDER get_order(32768)
DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);
static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
@@ -2631,4 +2721,19 @@
return false;
}
+void sock_def_readable(struct sock *sk);
+
+int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk);
+void sock_enable_timestamps(struct sock *sk);
+void sock_no_linger(struct sock *sk);
+void sock_set_keepalive(struct sock *sk);
+void sock_set_priority(struct sock *sk, u32 priority);
+void sock_set_rcvbuf(struct sock *sk, int val);
+void sock_set_mark(struct sock *sk, u32 val);
+void sock_set_reuseaddr(struct sock *sk);
+void sock_set_reuseport(struct sock *sk);
+void sock_set_sndtimeo(struct sock *sk, s64 secs);
+
+int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len);
+
#endif /* _SOCK_H */
diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index 43f4a81..505f1e1 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -24,7 +24,7 @@
unsigned int bind_inany:1;
unsigned int has_conns:1;
struct bpf_prog __rcu *prog; /* optional BPF sock selector */
- struct sock *socks[0]; /* array of sock pointers */
+ struct sock *socks[]; /* array of sock pointers */
};
extern int reuseport_alloc(struct sock *sk, bool bind_inany);
@@ -55,6 +55,4 @@
return ret;
}
-int reuseport_get_id(struct sock_reuseport *reuse);
-
#endif /* _SOCK_REUSEPORT_H */
diff --git a/include/net/strparser.h b/include/net/strparser.h
index 1d20b98..bec1439 100644
--- a/include/net/strparser.h
+++ b/include/net/strparser.h
@@ -54,10 +54,24 @@
int offset;
};
+struct _strp_msg {
+ /* Internal cb structure. struct strp_msg must be first for passing
+ * to upper layer.
+ */
+ struct strp_msg strp;
+ int accum_len;
+};
+
+struct sk_skb_cb {
+#define SK_SKB_CB_PRIV_LEN 20
+ unsigned char data[SK_SKB_CB_PRIV_LEN];
+ struct _strp_msg strp;
+};
+
static inline struct strp_msg *strp_msg(struct sk_buff *skb)
{
return (struct strp_msg *)((void *)skb->cb +
- offsetof(struct qdisc_skb_cb, data));
+ offsetof(struct sk_skb_cb, strp));
}
/* Structure for an attached lower socket */
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index aee86a1..8528015 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -40,6 +40,9 @@
SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING,
SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED,
SWITCHDEV_ATTR_ID_BRIDGE_MROUTER,
+#if IS_ENABLED(CONFIG_BRIDGE_MRP)
+ SWITCHDEV_ATTR_ID_MRP_PORT_ROLE,
+#endif
};
struct switchdev_attr {
@@ -55,6 +58,9 @@
clock_t ageing_time; /* BRIDGE_AGEING_TIME */
bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */
bool mc_disabled; /* MC_DISABLED */
+#if IS_ENABLED(CONFIG_BRIDGE_MRP)
+ u8 mrp_port_role; /* MRP_PORT_ROLE */
+#endif
} u;
};
@@ -63,6 +69,16 @@
SWITCHDEV_OBJ_ID_PORT_VLAN,
SWITCHDEV_OBJ_ID_PORT_MDB,
SWITCHDEV_OBJ_ID_HOST_MDB,
+#if IS_ENABLED(CONFIG_BRIDGE_MRP)
+ SWITCHDEV_OBJ_ID_MRP,
+ SWITCHDEV_OBJ_ID_RING_TEST_MRP,
+ SWITCHDEV_OBJ_ID_RING_ROLE_MRP,
+ SWITCHDEV_OBJ_ID_RING_STATE_MRP,
+ SWITCHDEV_OBJ_ID_IN_TEST_MRP,
+ SWITCHDEV_OBJ_ID_IN_ROLE_MRP,
+ SWITCHDEV_OBJ_ID_IN_STATE_MRP,
+
+#endif
};
struct switchdev_obj {
@@ -94,6 +110,89 @@
#define SWITCHDEV_OBJ_PORT_MDB(OBJ) \
container_of((OBJ), struct switchdev_obj_port_mdb, obj)
+
+#if IS_ENABLED(CONFIG_BRIDGE_MRP)
+/* SWITCHDEV_OBJ_ID_MRP */
+struct switchdev_obj_mrp {
+ struct switchdev_obj obj;
+ struct net_device *p_port;
+ struct net_device *s_port;
+ u32 ring_id;
+ u16 prio;
+};
+
+#define SWITCHDEV_OBJ_MRP(OBJ) \
+ container_of((OBJ), struct switchdev_obj_mrp, obj)
+
+/* SWITCHDEV_OBJ_ID_RING_TEST_MRP */
+struct switchdev_obj_ring_test_mrp {
+ struct switchdev_obj obj;
+ /* The value is in us and a value of 0 represents to stop */
+ u32 interval;
+ u8 max_miss;
+ u32 ring_id;
+ u32 period;
+ bool monitor;
+};
+
+#define SWITCHDEV_OBJ_RING_TEST_MRP(OBJ) \
+ container_of((OBJ), struct switchdev_obj_ring_test_mrp, obj)
+
+/* SWICHDEV_OBJ_ID_RING_ROLE_MRP */
+struct switchdev_obj_ring_role_mrp {
+ struct switchdev_obj obj;
+ u8 ring_role;
+ u32 ring_id;
+};
+
+#define SWITCHDEV_OBJ_RING_ROLE_MRP(OBJ) \
+ container_of((OBJ), struct switchdev_obj_ring_role_mrp, obj)
+
+struct switchdev_obj_ring_state_mrp {
+ struct switchdev_obj obj;
+ u8 ring_state;
+ u32 ring_id;
+};
+
+#define SWITCHDEV_OBJ_RING_STATE_MRP(OBJ) \
+ container_of((OBJ), struct switchdev_obj_ring_state_mrp, obj)
+
+/* SWITCHDEV_OBJ_ID_IN_TEST_MRP */
+struct switchdev_obj_in_test_mrp {
+ struct switchdev_obj obj;
+ /* The value is in us and a value of 0 represents to stop */
+ u32 interval;
+ u32 in_id;
+ u32 period;
+ u8 max_miss;
+};
+
+#define SWITCHDEV_OBJ_IN_TEST_MRP(OBJ) \
+ container_of((OBJ), struct switchdev_obj_in_test_mrp, obj)
+
+/* SWICHDEV_OBJ_ID_IN_ROLE_MRP */
+struct switchdev_obj_in_role_mrp {
+ struct switchdev_obj obj;
+ struct net_device *i_port;
+ u32 ring_id;
+ u16 in_id;
+ u8 in_role;
+};
+
+#define SWITCHDEV_OBJ_IN_ROLE_MRP(OBJ) \
+ container_of((OBJ), struct switchdev_obj_in_role_mrp, obj)
+
+struct switchdev_obj_in_state_mrp {
+ struct switchdev_obj obj;
+ u32 in_id;
+ u8 in_state;
+};
+
+#define SWITCHDEV_OBJ_IN_STATE_MRP(OBJ) \
+ container_of((OBJ), struct switchdev_obj_in_state_mrp, obj)
+
+#endif
+
typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj);
enum switchdev_notifier_type {
@@ -102,6 +201,7 @@
SWITCHDEV_FDB_ADD_TO_DEVICE,
SWITCHDEV_FDB_DEL_TO_DEVICE,
SWITCHDEV_FDB_OFFLOADED,
+ SWITCHDEV_FDB_FLUSH_TO_BRIDGE,
SWITCHDEV_PORT_OBJ_ADD, /* Blocking. */
SWITCHDEV_PORT_OBJ_DEL, /* Blocking. */
diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h
index bdc20ab..8250d6f 100644
--- a/include/net/tc_act/tc_ct.h
+++ b/include/net/tc_act/tc_ct.h
@@ -25,6 +25,9 @@
u16 ct_action;
struct rcu_head rcu;
+
+ struct tcf_ct_flow_table *ct_ft;
+ struct nf_flowtable *nf_ft;
};
struct tcf_ct {
@@ -33,8 +36,10 @@
};
#define to_ct(a) ((struct tcf_ct *)a)
-#define to_ct_params(a) ((struct tcf_ct_params *) \
- rtnl_dereference((to_ct(a)->params)))
+#define to_ct_params(a) \
+ ((struct tcf_ct_params *) \
+ rcu_dereference_protected(to_ct(a)->params, \
+ lockdep_is_held(&a->tcfa_lock)))
static inline uint16_t tcf_ct_zone(const struct tc_action *a)
{
@@ -46,11 +51,36 @@
return to_ct_params(a)->ct_action;
}
+static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a)
+{
+ return to_ct_params(a)->nf_ft;
+}
+
#else
static inline uint16_t tcf_ct_zone(const struct tc_action *a) { return 0; }
static inline int tcf_ct_action(const struct tc_action *a) { return 0; }
+static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a)
+{
+ return NULL;
+}
#endif /* CONFIG_NF_CONNTRACK */
+#if IS_ENABLED(CONFIG_NET_ACT_CT)
+static inline void
+tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie)
+{
+ enum ip_conntrack_info ctinfo = cookie & NFCT_INFOMASK;
+ struct nf_conn *ct;
+
+ ct = (struct nf_conn *)(cookie & NFCT_PTRMASK);
+ nf_conntrack_get(&ct->ct_general);
+ nf_ct_set(skb, ct, ctinfo);
+}
+#else
+static inline void
+tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie) { }
+#endif
+
static inline bool is_tcf_ct(const struct tc_action *a)
{
#if defined(CONFIG_NET_CLS_ACT) && IS_ENABLED(CONFIG_NF_CONNTRACK)
diff --git a/include/net/tc_act/tc_gate.h b/include/net/tc_act/tc_gate.h
new file mode 100644
index 0000000..8bc6be8
--- /dev/null
+++ b/include/net/tc_act/tc_gate.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright 2020 NXP */
+
+#ifndef __NET_TC_GATE_H
+#define __NET_TC_GATE_H
+
+#include <net/act_api.h>
+#include <linux/tc_act/tc_gate.h>
+
+struct action_gate_entry {
+ u8 gate_state;
+ u32 interval;
+ s32 ipv;
+ s32 maxoctets;
+};
+
+struct tcfg_gate_entry {
+ int index;
+ u8 gate_state;
+ u32 interval;
+ s32 ipv;
+ s32 maxoctets;
+ struct list_head list;
+};
+
+struct tcf_gate_params {
+ s32 tcfg_priority;
+ u64 tcfg_basetime;
+ u64 tcfg_cycletime;
+ u64 tcfg_cycletime_ext;
+ u32 tcfg_flags;
+ s32 tcfg_clockid;
+ size_t num_entries;
+ struct list_head entries;
+};
+
+#define GATE_ACT_GATE_OPEN BIT(0)
+#define GATE_ACT_PENDING BIT(1)
+
+struct tcf_gate {
+ struct tc_action common;
+ struct tcf_gate_params param;
+ u8 current_gate_status;
+ ktime_t current_close_time;
+ u32 current_entry_octets;
+ s32 current_max_octets;
+ struct tcfg_gate_entry *next_entry;
+ struct hrtimer hitimer;
+ enum tk_offsets tk_offset;
+};
+
+#define to_gate(a) ((struct tcf_gate *)a)
+
+static inline bool is_tcf_gate(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ if (a->ops && a->ops->id == TCA_ID_GATE)
+ return true;
+#endif
+ return false;
+}
+
+static inline u32 tcf_gate_index(const struct tc_action *a)
+{
+ return a->tcfa_index;
+}
+
+static inline s32 tcf_gate_prio(const struct tc_action *a)
+{
+ s32 tcfg_prio;
+
+ tcfg_prio = to_gate(a)->param.tcfg_priority;
+
+ return tcfg_prio;
+}
+
+static inline u64 tcf_gate_basetime(const struct tc_action *a)
+{
+ u64 tcfg_basetime;
+
+ tcfg_basetime = to_gate(a)->param.tcfg_basetime;
+
+ return tcfg_basetime;
+}
+
+static inline u64 tcf_gate_cycletime(const struct tc_action *a)
+{
+ u64 tcfg_cycletime;
+
+ tcfg_cycletime = to_gate(a)->param.tcfg_cycletime;
+
+ return tcfg_cycletime;
+}
+
+static inline u64 tcf_gate_cycletimeext(const struct tc_action *a)
+{
+ u64 tcfg_cycletimeext;
+
+ tcfg_cycletimeext = to_gate(a)->param.tcfg_cycletime_ext;
+
+ return tcfg_cycletimeext;
+}
+
+static inline u32 tcf_gate_num_entries(const struct tc_action *a)
+{
+ u32 num_entries;
+
+ num_entries = to_gate(a)->param.num_entries;
+
+ return num_entries;
+}
+
+static inline struct action_gate_entry
+ *tcf_gate_get_list(const struct tc_action *a)
+{
+ struct action_gate_entry *oe;
+ struct tcf_gate_params *p;
+ struct tcfg_gate_entry *entry;
+ u32 num_entries;
+ int i = 0;
+
+ p = &to_gate(a)->param;
+ num_entries = p->num_entries;
+
+ list_for_each_entry(entry, &p->entries, list)
+ i++;
+
+ if (i != num_entries)
+ return NULL;
+
+ oe = kcalloc(num_entries, sizeof(*oe), GFP_ATOMIC);
+ if (!oe)
+ return NULL;
+
+ i = 0;
+ list_for_each_entry(entry, &p->entries, list) {
+ oe[i].gate_state = entry->gate_state;
+ oe[i].interval = entry->interval;
+ oe[i].ipv = entry->ipv;
+ oe[i].maxoctets = entry->maxoctets;
+ i++;
+ }
+
+ return oe;
+}
+#endif
diff --git a/include/net/tc_act/tc_police.h b/include/net/tc_act/tc_police.h
index cfdc7cb..6d1e26b 100644
--- a/include/net/tc_act/tc_police.h
+++ b/include/net/tc_act/tc_police.h
@@ -54,17 +54,57 @@
struct tcf_police *police = to_police(act);
struct tcf_police_params *params;
- params = rcu_dereference_bh_rtnl(police->params);
+ params = rcu_dereference_protected(police->params,
+ lockdep_is_held(&police->tcf_lock));
return params->rate.rate_bytes_ps;
}
-static inline s64 tcf_police_tcfp_burst(const struct tc_action *act)
+static inline u32 tcf_police_burst(const struct tc_action *act)
+{
+ struct tcf_police *police = to_police(act);
+ struct tcf_police_params *params;
+ u32 burst;
+
+ params = rcu_dereference_protected(police->params,
+ lockdep_is_held(&police->tcf_lock));
+
+ /*
+ * "rate" bytes "burst" nanoseconds
+ * ------------ * -------------------
+ * 1 second 2^6 ticks
+ *
+ * ------------------------------------
+ * NSEC_PER_SEC nanoseconds
+ * ------------------------
+ * 2^6 ticks
+ *
+ * "rate" bytes "burst" nanoseconds 2^6 ticks
+ * = ------------ * ------------------- * ------------------------
+ * 1 second 2^6 ticks NSEC_PER_SEC nanoseconds
+ *
+ * "rate" * "burst"
+ * = ---------------- bytes/nanosecond
+ * NSEC_PER_SEC^2
+ *
+ *
+ * "rate" * "burst"
+ * = ---------------- bytes/second
+ * NSEC_PER_SEC
+ */
+ burst = div_u64(params->tcfp_burst * params->rate.rate_bytes_ps,
+ NSEC_PER_SEC);
+
+ return burst;
+}
+
+static inline u32 tcf_police_tcfp_mtu(const struct tc_action *act)
{
struct tcf_police *police = to_police(act);
struct tcf_police_params *params;
- params = rcu_dereference_bh_rtnl(police->params);
- return params->tcfp_burst;
+ params = rcu_dereference_protected(police->params,
+ lockdep_is_held(&police->tcf_lock));
+ return params->tcfp_mtu;
}
#endif /* __NET_TC_POLICE_H */
diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h
index b22a1f6..00bfee7 100644
--- a/include/net/tc_act/tc_skbedit.h
+++ b/include/net/tc_act/tc_skbedit.h
@@ -27,8 +27,8 @@
};
#define to_skbedit(a) ((struct tcf_skbedit *)a)
-/* Return true iff action is mark */
-static inline bool is_tcf_skbedit_mark(const struct tc_action *a)
+/* Return true iff action is the one identified by FLAG. */
+static inline bool is_tcf_skbedit_with_flag(const struct tc_action *a, u32 flag)
{
#ifdef CONFIG_NET_CLS_ACT
u32 flags;
@@ -37,12 +37,18 @@
rcu_read_lock();
flags = rcu_dereference(to_skbedit(a)->params)->flags;
rcu_read_unlock();
- return flags == SKBEDIT_F_MARK;
+ return flags == flag;
}
#endif
return false;
}
+/* Return true iff action is mark */
+static inline bool is_tcf_skbedit_mark(const struct tc_action *a)
+{
+ return is_tcf_skbedit_with_flag(a, SKBEDIT_F_MARK);
+}
+
static inline u32 tcf_skbedit_mark(const struct tc_action *a)
{
u32 mark;
@@ -57,17 +63,7 @@
/* Return true iff action is ptype */
static inline bool is_tcf_skbedit_ptype(const struct tc_action *a)
{
-#ifdef CONFIG_NET_CLS_ACT
- u32 flags;
-
- if (a->ops && a->ops->id == TCA_ID_SKBEDIT) {
- rcu_read_lock();
- flags = rcu_dereference(to_skbedit(a)->params)->flags;
- rcu_read_unlock();
- return flags == SKBEDIT_F_PTYPE;
- }
-#endif
- return false;
+ return is_tcf_skbedit_with_flag(a, SKBEDIT_F_PTYPE);
}
static inline u32 tcf_skbedit_ptype(const struct tc_action *a)
@@ -81,4 +77,21 @@
return ptype;
}
+/* Return true iff action is priority */
+static inline bool is_tcf_skbedit_priority(const struct tc_action *a)
+{
+ return is_tcf_skbedit_with_flag(a, SKBEDIT_F_PRIORITY);
+}
+
+static inline u32 tcf_skbedit_priority(const struct tc_action *a)
+{
+ u32 priority;
+
+ rcu_read_lock();
+ priority = rcu_dereference(to_skbedit(a)->params)->priority;
+ rcu_read_unlock();
+
+ return priority;
+}
+
#endif /* __NET_TC_SKBEDIT_H */
diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h
index 0689d9b..879fe8c 100644
--- a/include/net/tc_act/tc_tunnel_key.h
+++ b/include/net/tc_act/tc_tunnel_key.h
@@ -28,8 +28,10 @@
{
#ifdef CONFIG_NET_CLS_ACT
struct tcf_tunnel_key *t = to_tunnel_key(a);
- struct tcf_tunnel_key_params *params = rtnl_dereference(t->params);
+ struct tcf_tunnel_key_params *params;
+ params = rcu_dereference_protected(t->params,
+ lockdep_is_held(&a->tcfa_lock));
if (a->ops && a->ops->id == TCA_ID_TUNNEL_KEY)
return params->tcft_action == TCA_TUNNEL_KEY_ACT_SET;
#endif
@@ -40,8 +42,10 @@
{
#ifdef CONFIG_NET_CLS_ACT
struct tcf_tunnel_key *t = to_tunnel_key(a);
- struct tcf_tunnel_key_params *params = rtnl_dereference(t->params);
+ struct tcf_tunnel_key_params *params;
+ params = rcu_dereference_protected(t->params,
+ lockdep_is_held(&a->tcfa_lock));
if (a->ops && a->ops->id == TCA_ID_TUNNEL_KEY)
return params->tcft_action == TCA_TUNNEL_KEY_ACT_RELEASE;
#endif
@@ -52,7 +56,10 @@
{
#ifdef CONFIG_NET_CLS_ACT
struct tcf_tunnel_key *t = to_tunnel_key(a);
- struct tcf_tunnel_key_params *params = rtnl_dereference(t->params);
+ struct tcf_tunnel_key_params *params;
+
+ params = rcu_dereference_protected(t->params,
+ lockdep_is_held(&a->tcfa_lock));
return ¶ms->tcft_enc_metadata->u.tun_info;
#else
@@ -69,7 +76,7 @@
if (tun) {
size_t tun_size = sizeof(*tun) + tun->options_len;
struct ip_tunnel_info *tun_copy = kmemdup(tun, tun_size,
- GFP_KERNEL);
+ GFP_ATOMIC);
return tun_copy;
}
diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index add6fb5..f94b8bc 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -11,6 +11,8 @@
struct tcf_vlan_params {
int tcfv_action;
+ unsigned char tcfv_push_dst[ETH_ALEN];
+ unsigned char tcfv_push_src[ETH_ALEN];
u16 tcfv_push_vid;
__be16 tcfv_push_proto;
u8 tcfv_push_prio;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b914959..334b8d1 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -23,9 +23,9 @@
#include <linux/cache.h>
#include <linux/percpu.h>
#include <linux/skbuff.h>
-#include <linux/cryptohash.h>
#include <linux/kref.h>
#include <linux/ktime.h>
+#include <linux/indirect_call_wrapper.h>
#include <net/inet_connection_sock.h>
#include <net/inet_timewait_sock.h>
@@ -39,6 +39,7 @@
#include <net/tcp_states.h>
#include <net/inet_ecn.h>
#include <net/dst.h>
+#include <net/mptcp.h>
#include <linux/seq_file.h>
#include <linux/memcontrol.h>
@@ -47,7 +48,9 @@
extern struct inet_hashinfo tcp_hashinfo;
-extern struct percpu_counter tcp_orphan_count;
+DECLARE_PER_CPU(unsigned int, tcp_orphan_count);
+int tcp_orphan_count_sum(void);
+
void tcp_time_wait(struct sock *sk, int state, int timeo);
#define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER)
@@ -125,6 +128,7 @@
* to combine FIN-WAIT-2 timeout with
* TIME-WAIT timer.
*/
+#define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */
#define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */
#if HZ >= 100
@@ -182,6 +186,7 @@
#define TCPOPT_SACK 5 /* SACK Block */
#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
+#define TCPOPT_MPTCP 30 /* Multipath TCP (RFC6824) */
#define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */
#define TCPOPT_EXP 254 /* Experimental */
/* Magic number to be after the option value for sharing TCP
@@ -287,19 +292,6 @@
void sk_forced_mem_schedule(struct sock *sk, int size);
-static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
-{
- struct percpu_counter *ocp = sk->sk_prot->orphan_count;
- int orphans = percpu_counter_read_positive(ocp);
-
- if (orphans << shift > sysctl_tcp_max_orphans) {
- orphans = percpu_counter_sum_positive(ocp);
- if (orphans << shift > sysctl_tcp_max_orphans)
- return true;
- }
- return false;
-}
-
bool tcp_check_oom(struct sock *sk, int shift);
@@ -328,6 +320,9 @@
size_t size, int flags);
ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
size_t size, int flags);
+int tcp_send_mss(struct sock *sk, int *size_goal, int flags);
+void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle,
+ int size_goal);
void tcp_release_cb(struct sock *sk);
void tcp_wfree(struct sk_buff *skb);
void tcp_write_timer_handler(struct sock *sk);
@@ -388,17 +383,13 @@
bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
void tcp_close(struct sock *sk, long timeout);
void tcp_init_sock(struct sock *sk);
-void tcp_init_transfer(struct sock *sk, int bpf_op);
+void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb);
__poll_t tcp_poll(struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int tcp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
-int tcp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen);
-int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen);
-int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen);
+int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+ unsigned int optlen);
void tcp_set_keepalive(struct sock *sk, int val);
void tcp_syn_ack_timeout(const struct request_sock *req);
int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
@@ -431,6 +422,7 @@
void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
void tcp_v4_mtu_reduced(struct sock *sk);
void tcp_req_err(struct sock *sk, u32 seq, bool abort);
+void tcp_ld_RTO_revert(struct sock *sk, u32 seq);
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
struct sock *tcp_create_openreq_child(const struct sock *sk,
struct request_sock *req,
@@ -452,7 +444,8 @@
struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
- enum tcp_synack_type synack_type);
+ enum tcp_synack_type synack_type,
+ struct sk_buff *syn_skb);
int tcp_disconnect(struct sock *sk, int flags);
void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
@@ -466,6 +459,8 @@
int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
u32 cookie);
struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
+struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
+ struct sock *sk, struct sk_buff *skb);
#ifdef CONFIG_SYN_COOKIES
/* Syncookies use a monotonic timer which increments every 60 seconds.
@@ -548,7 +543,7 @@
u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
u16 *mssp);
__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss);
-u64 cookie_init_timestamp(struct request_sock *req);
+u64 cookie_init_timestamp(struct request_sock *req, u64 now);
bool cookie_timestamp_decode(const struct net *net,
struct tcp_options_received *opt);
bool cookie_ecn_ok(const struct tcp_options_received *opt,
@@ -656,7 +651,6 @@
int tcp_mtu_to_mss(struct sock *sk, int pmtu);
int tcp_mss_to_mtu(struct sock *sk, int mss);
void tcp_mtup_init(struct sock *sk);
-void tcp_init_buffer_space(struct sock *sk);
static inline void tcp_bound_rto(const struct sock *sk)
{
@@ -671,6 +665,10 @@
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{
+ /* mptcp hooks are only on the slow path */
+ if (sk_is_mptcp((struct sock *)tp))
+ return;
+
tp->pred_flags = htonl((tp->tcp_header_len << 26) |
ntohl(TCP_FLAG_ACK) |
snd_wnd);
@@ -696,7 +694,7 @@
static inline u32 tcp_rto_min(struct sock *sk)
{
const struct dst_entry *dst = __sk_dst_get(sk);
- u32 rto_min = TCP_RTO_MIN;
+ u32 rto_min = inet_csk(sk)->icsk_rto_min;
if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
@@ -769,10 +767,16 @@
return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ);
}
+/* Convert a nsec timestamp into TCP TSval timestamp (ms based currently) */
+static inline u32 tcp_ns_to_ts(u64 ns)
+{
+ return div_u64(ns, NSEC_PER_SEC / TCP_TS_HZ);
+}
+
/* Could use tcp_clock_us() / 1000, but this version uses a single divide */
static inline u32 tcp_time_stamp_raw(void)
{
- return div_u64(tcp_clock_ns(), NSEC_PER_SEC / TCP_TS_HZ);
+ return tcp_ns_to_ts(tcp_clock_ns());
}
void tcp_mstamp_refresh(struct tcp_sock *tp);
@@ -784,7 +788,7 @@
static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
{
- return div_u64(skb->skb_mstamp_ns, NSEC_PER_SEC / TCP_TS_HZ);
+ return tcp_ns_to_ts(skb->skb_mstamp_ns);
}
/* provide the departure time in us unit */
@@ -896,6 +900,8 @@
TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
}
+extern const struct inet_connection_sock_af_ops ipv4_specific;
+
#if IS_ENABLED(CONFIG_IPV6)
/* This is the variant of inet6_iif() that must be used by TCP,
* as TCP moves IP6CB into a different location in skb->cb[]
@@ -921,17 +927,14 @@
#endif
return 0;
}
-#endif
-static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb)
-{
-#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
- if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
- skb && ipv4_l3mdev_skb(IPCB(skb)->flags))
- return true;
+extern const struct inet_connection_sock_af_ops ipv6_specific;
+
+INDIRECT_CALLABLE_DECLARE(void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb));
+INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb));
+INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb));
+
#endif
- return false;
-}
/* TCP_SKB_CB reference means this can not be used from early demux */
static inline int tcp_v4_sdif(struct sk_buff *skb)
@@ -972,6 +975,13 @@
return likely(!TCP_SKB_CB(skb)->eor);
}
+static inline bool tcp_skb_can_collapse(const struct sk_buff *to,
+ const struct sk_buff *from)
+{
+ return likely(tcp_skb_can_collapse_to(to) &&
+ mptcp_skb_can_collapse(to, from));
+}
+
/* Events passed to congestion control interface */
enum tcp_ca_event {
CA_EVENT_TX_START, /* first transmit when no packets in flight */
@@ -1002,6 +1012,7 @@
#define TCP_CONG_NON_RESTRICTED 0x1
/* Requires ECN/ECT set on all packets */
#define TCP_CONG_NEEDS_ECN 0x2
+#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN)
union tcp_cc_info;
@@ -1087,7 +1098,7 @@
void tcp_get_allowed_congestion_control(char *buf, size_t len);
int tcp_set_allowed_congestion_control(char *allowed);
int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
- bool reinit, bool cap_net_admin);
+ bool cap_net_admin);
u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
@@ -1096,6 +1107,7 @@
void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
extern struct tcp_congestion_ops tcp_reno;
+struct tcp_congestion_ops *tcp_ca_find(const char *name);
struct tcp_congestion_ops *tcp_ca_find_key(u32 key);
u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca);
#ifdef CONFIG_INET
@@ -1269,26 +1281,22 @@
return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
}
-/* Return in jiffies the delay before one skb is sent.
- * If @skb is NULL, we look at EDT for next packet being sent on the socket.
+/* Estimates in how many jiffies next packet for this flow can be sent.
+ * Scheduling a retransmit timer too early would be silly.
*/
-static inline unsigned long tcp_pacing_delay(const struct sock *sk,
- const struct sk_buff *skb)
+static inline unsigned long tcp_pacing_delay(const struct sock *sk)
{
- s64 pacing_delay = skb ? skb->tstamp : tcp_sk(sk)->tcp_wstamp_ns;
+ s64 delay = tcp_sk(sk)->tcp_wstamp_ns - tcp_sk(sk)->tcp_clock_cache;
- pacing_delay -= tcp_sk(sk)->tcp_clock_cache;
-
- return pacing_delay > 0 ? nsecs_to_jiffies(pacing_delay) : 0;
+ return delay > 0 ? nsecs_to_jiffies(delay) : 0;
}
static inline void tcp_reset_xmit_timer(struct sock *sk,
const int what,
unsigned long when,
- const unsigned long max_when,
- const struct sk_buff *skb)
+ const unsigned long max_when)
{
- inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk, skb),
+ inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk),
max_when);
}
@@ -1316,8 +1324,7 @@
{
if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending)
tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
- tcp_probe0_base(sk), TCP_RTO_MAX,
- NULL);
+ tcp_probe0_base(sk), TCP_RTO_MAX);
}
static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
@@ -1357,7 +1364,6 @@
rx_opt->num_sacks = 0;
}
-u32 tcp_default_init_rwnd(u32 mss);
void tcp_cwnd_restart(struct sock *sk, s32 delta);
static inline void tcp_slow_start_after_idle_check(struct sock *sk)
@@ -1402,6 +1408,8 @@
return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
}
+void tcp_cleanup_rbuf(struct sock *sk, int copied);
+
/* We provision sk_rcvbuf around 200% of sk_rcvlowat.
* If 87.5 % (7/8) of the space has been consumed, we want to override
* SO_RCVLOWAT constraint, since we are receiving skbs with too small
@@ -1545,8 +1553,9 @@
struct hlist_node node;
u8 keylen;
u8 family; /* AF_INET or AF_INET6 */
- union tcp_md5_addr addr;
u8 prefixlen;
+ union tcp_md5_addr addr;
+ int l3index; /* set if key added with L3 scope */
u8 key[TCP_MD5SIG_MAXKEYLEN];
struct rcu_head rcu;
};
@@ -1590,34 +1599,33 @@
int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
const struct sock *sk, const struct sk_buff *skb);
int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
- int family, u8 prefixlen, const u8 *newkey, u8 newkeylen,
- gfp_t gfp);
+ int family, u8 prefixlen, int l3index,
+ const u8 *newkey, u8 newkeylen, gfp_t gfp);
int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr,
- int family, u8 prefixlen);
+ int family, u8 prefixlen, int l3index);
struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
const struct sock *addr_sk);
#ifdef CONFIG_TCP_MD5SIG
#include <linux/jump_label.h>
extern struct static_key_false tcp_md5_needed;
-struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk,
+struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
const union tcp_md5_addr *addr,
int family);
static inline struct tcp_md5sig_key *
-tcp_md5_do_lookup(const struct sock *sk,
- const union tcp_md5_addr *addr,
- int family)
+tcp_md5_do_lookup(const struct sock *sk, int l3index,
+ const union tcp_md5_addr *addr, int family)
{
if (!static_branch_unlikely(&tcp_md5_needed))
return NULL;
- return __tcp_md5_do_lookup(sk, addr, family);
+ return __tcp_md5_do_lookup(sk, l3index, addr, family);
}
#define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key)
#else
-static inline struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk,
- const union tcp_md5_addr *addr,
- int family)
+static inline struct tcp_md5sig_key *
+tcp_md5_do_lookup(const struct sock *sk, int l3index,
+ const union tcp_md5_addr *addr, int family)
{
return NULL;
}
@@ -1781,9 +1789,18 @@
return skb_queue_is_last(&sk->sk_write_queue, skb);
}
+/**
+ * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue
+ * @sk: socket
+ *
+ * Since the write queue can have a temporary empty skb in it,
+ * we must not use "return skb_queue_empty(&sk->sk_write_queue)"
+ */
static inline bool tcp_write_queue_empty(const struct sock *sk)
{
- return skb_queue_empty(&sk->sk_write_queue);
+ const struct tcp_sock *tp = tcp_sk(sk);
+
+ return tp->write_seq == tp->snd_nxt;
}
static inline bool tcp_rtx_queue_empty(const struct sock *sk)
@@ -1920,6 +1937,7 @@
struct seq_net_private p;
enum tcp_seq_states state;
struct sock *syn_wait_sk;
+ struct tcp_seq_afinfo *bpf_seq_afinfo;
int bucket, offset, sbucket, num;
loff_t last_pos;
};
@@ -1932,6 +1950,10 @@
struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
netdev_features_t features);
struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb);
+INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff));
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb));
+INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff));
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb));
int tcp_gro_complete(struct sk_buff *skb);
void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
@@ -1976,7 +1998,7 @@
const struct sk_buff *skb);
int (*md5_parse)(struct sock *sk,
int optname,
- char __user *optval,
+ sockptr_t optval,
int optlen);
#endif
};
@@ -2005,9 +2027,15 @@
int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl, struct request_sock *req,
struct tcp_fastopen_cookie *foc,
- enum tcp_synack_type synack_type);
+ enum tcp_synack_type synack_type,
+ struct sk_buff *syn_skb);
};
+extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops;
+#if IS_ENABLED(CONFIG_IPV6)
+extern const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops;
+#endif
+
#ifdef CONFIG_SYN_COOKIES
static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
const struct sock *sk, struct sk_buff *skb,
@@ -2160,6 +2188,9 @@
/* diagnostic */
int (*get_info)(const struct sock *sk, struct sk_buff *skb);
size_t (*get_info_size)(const struct sock *sk);
+ /* clone ulp */
+ void (*clone)(const struct request_sock *req, struct sock *newsk,
+ const gfp_t priority);
char name[TCP_ULP_NAME_MAX];
struct module *owner;
@@ -2179,14 +2210,37 @@
struct sk_msg;
struct sk_psock;
-int tcp_bpf_init(struct sock *sk);
-void tcp_bpf_reinit(struct sock *sk);
+#ifdef CONFIG_BPF_STREAM_PARSER
+struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
+void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
+#else
+static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
+{
+}
+#endif /* CONFIG_BPF_STREAM_PARSER */
+
+#ifdef CONFIG_NET_SOCK_MSG
int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes,
int flags);
-int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
- int nonblock, int flags, int *addr_len);
int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
struct msghdr *msg, int len, int flags);
+#endif /* CONFIG_NET_SOCK_MSG */
+
+#ifdef CONFIG_CGROUP_BPF
+static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
+ struct sk_buff *skb,
+ unsigned int end_offset)
+{
+ skops->skb = skb;
+ skops->skb_data_end = skb->data + end_offset;
+}
+#else
+static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
+ struct sk_buff *skb,
+ unsigned int end_offset)
+{
+}
+#endif
/* Call BPF_SOCK_OPS program that returns an int. If the return value
* is < 0, then the BPF op failed (for example if the loaded BPF
diff --git a/include/net/tls.h b/include/net/tls.h
index 697df45..745b3bc 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -44,6 +44,7 @@
#include <linux/netdevice.h>
#include <linux/rcupdate.h>
+#include <net/net_namespace.h>
#include <net/tcp.h>
#include <net/strparser.h>
#include <crypto/aead.h>
@@ -61,7 +62,6 @@
#define TLS_RECORD_TYPE_DATA 0x17
#define TLS_AAD_SPACE_SIZE 13
-#define TLS_DEVICE_NAME_MAX 32
#define MAX_IV_SIZE 16
#define TLS_MAX_REC_SEQ_SIZE 8
@@ -75,36 +75,14 @@
*/
#define TLS_AES_CCM_IV_B0_BYTE 2
-/*
- * This structure defines the routines for Inline TLS driver.
- * The following routines are optional and filled with a
- * null pointer if not defined.
- *
- * @name: Its the name of registered Inline tls device
- * @dev_list: Inline tls device list
- * int (*feature)(struct tls_device *device);
- * Called to return Inline TLS driver capability
- *
- * int (*hash)(struct tls_device *device, struct sock *sk);
- * This function sets Inline driver for listen and program
- * device specific functioanlity as required
- *
- * void (*unhash)(struct tls_device *device, struct sock *sk);
- * This function cleans listen state set by Inline TLS driver
- *
- * void (*release)(struct kref *kref);
- * Release the registered device and allocated resources
- * @kref: Number of reference to tls_device
- */
-struct tls_device {
- char name[TLS_DEVICE_NAME_MAX];
- struct list_head dev_list;
- int (*feature)(struct tls_device *device);
- int (*hash)(struct tls_device *device, struct sock *sk);
- void (*unhash)(struct tls_device *device, struct sock *sk);
- void (*release)(struct kref *kref);
- struct kref kref;
-};
+#define __TLS_INC_STATS(net, field) \
+ __SNMP_INC_STATS((net)->mib.tls_statistics, field)
+#define TLS_INC_STATS(net, field) \
+ SNMP_INC_STATS((net)->mib.tls_statistics, field)
+#define __TLS_DEC_STATS(net, field) \
+ __SNMP_DEC_STATS((net)->mib.tls_statistics, field)
+#define TLS_DEC_STATS(net, field) \
+ SNMP_DEC_STATS((net)->mib.tls_statistics, field)
enum {
TLS_BASE,
@@ -160,7 +138,7 @@
/* protect crypto_wait with encrypt_pending */
spinlock_t encrypt_compl_lock;
int async_notify;
- int async_capable;
+ u8 async_capable:1;
#define BIT_TX_SCHEDULED 0
#define BIT_TX_CLOSING 1
@@ -176,8 +154,8 @@
struct sk_buff *recv_pkt;
u8 control;
- int async_capable;
- bool decrypted;
+ u8 async_capable:1;
+ u8 decrypted:1;
atomic_t decrypt_pending;
/* protect crypto_wait with decrypt_pending*/
spinlock_t decrypt_compl_lock;
@@ -215,7 +193,11 @@
(sizeof(struct tls_offload_context_tx) + TLS_DRIVER_STATE_SIZE_TX)
enum tls_context_flags {
- TLS_RX_SYNC_RUNNING = 0,
+ /* tls_device_down was called after the netdev went down, device state
+ * was released, and kTLS works in software, even though rx_conf is
+ * still TLS_HW (needed for transition).
+ */
+ TLS_RX_DEV_DEGRADED = 0,
/* Unlike RX where resync is driven entirely by the core in TX only
* the driver knows when things went out of sync, so we need the flag
* to be atomic.
@@ -287,6 +269,7 @@
/* cache cold stuff */
struct proto *sk_proto;
+ struct sock *sk;
void (*sk_destruct)(struct sock *sk);
@@ -319,11 +302,20 @@
enum tls_offload_sync_type {
TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ = 0,
TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT = 1,
+ TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ_ASYNC = 2,
};
#define TLS_DEVICE_RESYNC_NH_START_IVAL 2
#define TLS_DEVICE_RESYNC_NH_MAX_IVAL 128
+#define TLS_DEVICE_RESYNC_ASYNC_LOGMAX 13
+struct tls_offload_resync_async {
+ atomic64_t req;
+ u16 loglen;
+ u16 rcd_delta;
+ u32 log[TLS_DEVICE_RESYNC_ASYNC_LOGMAX];
+};
+
struct tls_offload_context_rx {
/* sw must be the first member of tls_offload_context_rx */
struct tls_sw_context_rx sw;
@@ -342,6 +334,10 @@
u32 decrypted_failed;
u32 decrypted_tgt;
} resync_nh;
+ /* TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ_ASYNC */
+ struct {
+ struct tls_offload_resync_async *resync_async;
+ };
};
u8 driver_state[] __aligned(8);
/* The TLS layer reserves room for driver specific state
@@ -354,12 +350,16 @@
#define TLS_OFFLOAD_CONTEXT_SIZE_RX \
(sizeof(struct tls_offload_context_rx) + TLS_DRIVER_STATE_SIZE_RX)
+struct tls_context *tls_ctx_create(struct sock *sk);
void tls_ctx_free(struct sock *sk, struct tls_context *ctx);
+void update_sk_prot(struct sock *sk, struct tls_context *ctx);
+
int wait_on_pending_writer(struct sock *sk, long *timeo);
int tls_sk_query(struct sock *sk, int optname, char __user *optval,
int __user *optlen);
int tls_sk_attach(struct sock *sk, int optname, char __user *optval,
unsigned int optlen);
+void tls_err_abort(struct sock *sk, int err);
int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
@@ -453,6 +453,9 @@
struct sk_buff *
tls_validate_xmit_skb(struct sock *sk, struct net_device *dev,
struct sk_buff *skb);
+struct sk_buff *
+tls_validate_xmit_skb_sw(struct sock *sk, struct net_device *dev,
+ struct sk_buff *skb);
static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
{
@@ -465,12 +468,6 @@
#endif
}
-static inline void tls_err_abort(struct sock *sk, int err)
-{
- sk->sk_err = err;
- sk->sk_error_report(sk);
-}
-
static inline bool tls_bigint_increment(unsigned char *seq, int len)
{
int i;
@@ -484,6 +481,18 @@
return (i == -1);
}
+static inline void tls_bigint_subtract(unsigned char *seq, int n)
+{
+ u64 rcd_sn;
+ __be64 *p;
+
+ BUILD_BUG_ON(TLS_MAX_REC_SEQ_SIZE != 8);
+
+ p = (__be64 *)seq;
+ rcd_sn = be64_to_cpu(*p);
+ *p = cpu_to_be64(rcd_sn - n);
+}
+
static inline struct tls_context *tls_get_ctx(const struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -499,7 +508,7 @@
struct cipher_context *ctx)
{
if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size))
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
if (prot->version != TLS_1_3_VERSION)
tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
@@ -631,13 +640,38 @@
}
#endif
+#define RESYNC_REQ BIT(0)
+#define RESYNC_REQ_ASYNC BIT(1)
/* The TLS context is valid until sk_destruct is called */
static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
- atomic64_set(&rx_ctx->resync_req, ((u64)ntohl(seq) << 32) | 1);
+ atomic64_set(&rx_ctx->resync_req, ((u64)ntohl(seq) << 32) | RESYNC_REQ);
+}
+
+/* Log all TLS record header TCP sequences in [seq, seq+len] */
+static inline void
+tls_offload_rx_resync_async_request_start(struct sock *sk, __be32 seq, u16 len)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
+
+ atomic64_set(&rx_ctx->resync_async->req, ((u64)ntohl(seq) << 32) |
+ ((u64)len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC);
+ rx_ctx->resync_async->loglen = 0;
+ rx_ctx->resync_async->rcd_delta = 0;
+}
+
+static inline void
+tls_offload_rx_resync_async_request_end(struct sock *sk, __be32 seq)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
+
+ atomic64_set(&rx_ctx->resync_async->req,
+ ((u64)ntohl(seq) << 32) | RESYNC_REQ);
}
static inline void
@@ -648,13 +682,6 @@
tls_offload_ctx_rx(tls_ctx)->resync_type = type;
}
-static inline void tls_offload_tx_resync_request(struct sock *sk)
-{
- struct tls_context *tls_ctx = tls_get_ctx(sk);
-
- WARN_ON(test_and_set_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags));
-}
-
/* Driver's seq tracking has to be disabled until resync succeeded */
static inline bool tls_offload_tx_resync_pending(struct sock *sk)
{
@@ -666,18 +693,15 @@
return ret;
}
+int __net_init tls_proc_init(struct net *net);
+void __net_exit tls_proc_fini(struct net *net);
+
int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg,
unsigned char *record_type);
-void tls_register_device(struct tls_device *device);
-void tls_unregister_device(struct tls_device *device);
int decrypt_skb(struct sock *sk, struct sk_buff *skb,
struct scatterlist *sgout);
struct sk_buff *tls_encrypt_skb(struct sk_buff *skb);
-struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
- struct net_device *dev,
- struct sk_buff *skb);
-
int tls_sw_fallback_init(struct sock *sk,
struct tls_offload_context_tx *offload_ctx,
struct tls_crypto_info *crypto_info);
@@ -685,12 +709,23 @@
#ifdef CONFIG_TLS_DEVICE
void tls_device_init(void);
void tls_device_cleanup(void);
+void tls_device_sk_destruct(struct sock *sk);
int tls_set_device_offload(struct sock *sk, struct tls_context *ctx);
void tls_device_free_resources_tx(struct sock *sk);
int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx);
void tls_device_offload_cleanup_rx(struct sock *sk);
void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq);
-int tls_device_decrypted(struct sock *sk, struct sk_buff *skb);
+void tls_offload_tx_resync_request(struct sock *sk, u32 got_seq, u32 exp_seq);
+int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx,
+ struct sk_buff *skb, struct strp_msg *rxm);
+
+static inline bool tls_is_sk_rx_device_offloaded(struct sock *sk)
+{
+ if (!sk_fullsock(sk) ||
+ smp_load_acquire(&sk->sk_destruct) != tls_device_sk_destruct)
+ return false;
+ return tls_get_ctx(sk)->rx_conf == TLS_HW;
+}
#else
static inline void tls_device_init(void) {}
static inline void tls_device_cleanup(void) {}
@@ -713,7 +748,9 @@
static inline void
tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) {}
-static inline int tls_device_decrypted(struct sock *sk, struct sk_buff *skb)
+static inline int
+tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx,
+ struct sk_buff *skb, struct strp_msg *rxm)
{
return 0;
}
diff --git a/include/net/tls_toe.h b/include/net/tls_toe.h
new file mode 100644
index 0000000..b3aa759
--- /dev/null
+++ b/include/net/tls_toe.h
@@ -0,0 +1,77 @@
+/*
+ * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/kref.h>
+#include <linux/list.h>
+
+struct sock;
+
+#define TLS_TOE_DEVICE_NAME_MAX 32
+
+/*
+ * This structure defines the routines for Inline TLS driver.
+ * The following routines are optional and filled with a
+ * null pointer if not defined.
+ *
+ * @name: Its the name of registered Inline tls device
+ * @dev_list: Inline tls device list
+ * int (*feature)(struct tls_toe_device *device);
+ * Called to return Inline TLS driver capability
+ *
+ * int (*hash)(struct tls_toe_device *device, struct sock *sk);
+ * This function sets Inline driver for listen and program
+ * device specific functioanlity as required
+ *
+ * void (*unhash)(struct tls_toe_device *device, struct sock *sk);
+ * This function cleans listen state set by Inline TLS driver
+ *
+ * void (*release)(struct kref *kref);
+ * Release the registered device and allocated resources
+ * @kref: Number of reference to tls_toe_device
+ */
+struct tls_toe_device {
+ char name[TLS_TOE_DEVICE_NAME_MAX];
+ struct list_head dev_list;
+ int (*feature)(struct tls_toe_device *device);
+ int (*hash)(struct tls_toe_device *device, struct sock *sk);
+ void (*unhash)(struct tls_toe_device *device, struct sock *sk);
+ void (*release)(struct kref *kref);
+ struct kref kref;
+};
+
+int tls_toe_bypass(struct sock *sk);
+int tls_toe_hash(struct sock *sk);
+void tls_toe_unhash(struct sock *sk);
+
+void tls_toe_register_device(struct tls_toe_device *device);
+void tls_toe_unregister_device(struct tls_toe_device *device);
diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index a8f6020..da06613 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -56,9 +56,6 @@
#define LOOPBACK4_IPV6 cpu_to_be32(0x7f000006)
-/* address family specific functions */
-extern const struct inet_connection_sock_af_ops ipv4_specific;
-
void inet6_destroy_sock(struct sock *sk);
#define IPV6_SEQ_DGRAM_HEADER \
diff --git a/include/net/tso.h b/include/net/tso.h
index 7e166a5..62c98a9 100644
--- a/include/net/tso.h
+++ b/include/net/tso.h
@@ -4,21 +4,22 @@
#include <net/ip.h>
-#define TSO_HEADER_SIZE 128
+#define TSO_HEADER_SIZE 256
struct tso_t {
- int next_frag_idx;
- void *data;
- size_t size;
- u16 ip_id;
- bool ipv6;
- u32 tcp_seq;
+ int next_frag_idx;
+ int size;
+ void *data;
+ u16 ip_id;
+ u8 tlen; /* transport header len */
+ bool ipv6;
+ u32 tcp_seq;
};
-int tso_count_descs(struct sk_buff *skb);
-void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso,
+int tso_count_descs(const struct sk_buff *skb);
+void tso_build_hdr(const struct sk_buff *skb, char *hdr, struct tso_t *tso,
int size, bool is_last);
-void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size);
-void tso_start(struct sk_buff *skb, struct tso_t *tso);
+void tso_build_data(const struct sk_buff *skb, struct tso_t *tso, int size);
+int tso_start(struct sk_buff *skb, struct tso_t *tso);
#endif /* _TSO_H */
diff --git a/include/net/udp.h b/include/net/udp.h
index fabf507..435cc00 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -27,6 +27,7 @@
#include <linux/ipv6.h>
#include <linux/seq_file.h>
#include <linux/poll.h>
+#include <linux/indirect_call_wrapper.h>
/**
* struct udp_skb_cb - UDP(-Lite) private variables
@@ -166,12 +167,18 @@
typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport,
__be16 dport);
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *,
+ struct sk_buff *));
+INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int));
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *,
+ struct sk_buff *));
+INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int));
struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
- struct udphdr *uh, udp_lookup_t lookup);
+ struct udphdr *uh, struct sock *sk);
int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
- netdev_features_t features);
+ netdev_features_t features, bool is_ipv6);
static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
{
@@ -299,7 +306,7 @@
int udp_lib_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
int udp_lib_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen,
+ sockptr_t optval, unsigned int optlen,
int (*push_pending_frames)(struct sock *));
struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
__be32 daddr, __be16 dport, int dif);
@@ -440,6 +447,7 @@
struct udp_iter_state {
struct seq_net_private p;
int bucket;
+ struct udp_seq_afinfo *bpf_seq_afinfo;
};
void *udp_seq_start(struct seq_file *seq, loff_t *pos);
@@ -480,8 +488,9 @@
* CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial
* packets in udp_gro_complete_segment. As does UDP GSO, verified by
* udp_send_skb. But when those packets are looped in dev_loopback_xmit
- * their ip_summed is set to CHECKSUM_UNNECESSARY. Reset in this
- * specific case, where PARTIAL is both correct and required.
+ * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY.
+ * Reset in this specific case, where PARTIAL is both correct and
+ * required.
*/
if (skb->pkt_type == PACKET_LOOPBACK)
skb->ip_summed = CHECKSUM_PARTIAL;
@@ -503,4 +512,9 @@
return segs;
}
+#ifdef CONFIG_BPF_STREAM_PARSER
+struct sk_psock;
+struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
+#endif /* BPF_STREAM_PARSER */
+
#endif /* _UDP_H */
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 4b1f95e..2ea453d 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -106,15 +106,16 @@
* call this function to perform Tx offloads on outgoing traffic.
*/
enum udp_parsable_tunnel_type {
- UDP_TUNNEL_TYPE_VXLAN, /* RFC 7348 */
- UDP_TUNNEL_TYPE_GENEVE, /* draft-ietf-nvo3-geneve */
- UDP_TUNNEL_TYPE_VXLAN_GPE, /* draft-ietf-nvo3-vxlan-gpe */
+ UDP_TUNNEL_TYPE_VXLAN = BIT(0), /* RFC 7348 */
+ UDP_TUNNEL_TYPE_GENEVE = BIT(1), /* draft-ietf-nvo3-geneve */
+ UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */
};
struct udp_tunnel_info {
unsigned short type;
sa_family_t sa_family;
__be16 port;
+ u8 hw_priv;
};
/* Notify network devices of offloadable types */
@@ -143,14 +144,12 @@
__be16 df, __be16 src_port, __be16 dst_port,
bool xnet, bool nocheck);
-#if IS_ENABLED(CONFIG_IPV6)
int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb,
struct net_device *dev, struct in6_addr *saddr,
struct in6_addr *daddr,
__u8 prio, __u8 ttl, __be32 label,
__be16 src_port, __be16 dst_port, bool nocheck);
-#endif
void udp_tunnel_sock_release(struct socket *sock);
@@ -183,4 +182,190 @@
udp_encap_enable();
}
+#define UDP_TUNNEL_NIC_MAX_TABLES 4
+
+enum udp_tunnel_nic_info_flags {
+ /* Device callbacks may sleep */
+ UDP_TUNNEL_NIC_INFO_MAY_SLEEP = BIT(0),
+ /* Device only supports offloads when it's open, all ports
+ * will be removed before close and re-added after open.
+ */
+ UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(1),
+ /* Device supports only IPv4 tunnels */
+ UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(2),
+ /* Device has hard-coded the IANA VXLAN port (4789) as VXLAN.
+ * This port must not be counted towards n_entries of any table.
+ * Driver will not receive any callback associated with port 4789.
+ */
+ UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(3),
+};
+
+struct udp_tunnel_nic;
+
+#define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES (U16_MAX / 2)
+
+struct udp_tunnel_nic_shared {
+ struct udp_tunnel_nic *udp_tunnel_nic_info;
+
+ struct list_head devices;
+};
+
+struct udp_tunnel_nic_shared_node {
+ struct net_device *dev;
+ struct list_head list;
+};
+
+/**
+ * struct udp_tunnel_nic_info - driver UDP tunnel offload information
+ * @set_port: callback for adding a new port
+ * @unset_port: callback for removing a port
+ * @sync_table: callback for syncing the entire port table at once
+ * @shared: reference to device global state (optional)
+ * @flags: device flags from enum udp_tunnel_nic_info_flags
+ * @tables: UDP port tables this device has
+ * @tables.n_entries: number of entries in this table
+ * @tables.tunnel_types: types of tunnels this table accepts
+ *
+ * Drivers are expected to provide either @set_port and @unset_port callbacks
+ * or the @sync_table callback. Callbacks are invoked with rtnl lock held.
+ *
+ * Devices which (misguidedly) share the UDP tunnel port table across multiple
+ * netdevs should allocate an instance of struct udp_tunnel_nic_shared and
+ * point @shared at it.
+ * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices
+ * sharing a table.
+ *
+ * Known limitations:
+ * - UDP tunnel port notifications are fundamentally best-effort -
+ * it is likely the driver will both see skbs which use a UDP tunnel port,
+ * while not being a tunneled skb, and tunnel skbs from other ports -
+ * drivers should only use these ports for non-critical RX-side offloads,
+ * e.g. the checksum offload;
+ * - none of the devices care about the socket family at present, so we don't
+ * track it. Please extend this code if you care.
+ */
+struct udp_tunnel_nic_info {
+ /* one-by-one */
+ int (*set_port)(struct net_device *dev,
+ unsigned int table, unsigned int entry,
+ struct udp_tunnel_info *ti);
+ int (*unset_port)(struct net_device *dev,
+ unsigned int table, unsigned int entry,
+ struct udp_tunnel_info *ti);
+
+ /* all at once */
+ int (*sync_table)(struct net_device *dev, unsigned int table);
+
+ struct udp_tunnel_nic_shared *shared;
+
+ unsigned int flags;
+
+ struct udp_tunnel_nic_table_info {
+ unsigned int n_entries;
+ unsigned int tunnel_types;
+ } tables[UDP_TUNNEL_NIC_MAX_TABLES];
+};
+
+/* UDP tunnel module dependencies
+ *
+ * Tunnel drivers are expected to have a hard dependency on the udp_tunnel
+ * module. NIC drivers are not, they just attach their
+ * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come.
+ * Loading a tunnel driver will cause the udp_tunnel module to be loaded
+ * and only then will all the required state structures be allocated.
+ * Since we want a weak dependency from the drivers and the core to udp_tunnel
+ * we call things through the following stubs.
+ */
+struct udp_tunnel_nic_ops {
+ void (*get_port)(struct net_device *dev, unsigned int table,
+ unsigned int idx, struct udp_tunnel_info *ti);
+ void (*set_port_priv)(struct net_device *dev, unsigned int table,
+ unsigned int idx, u8 priv);
+ void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti);
+ void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti);
+ void (*reset_ntf)(struct net_device *dev);
+
+ size_t (*dump_size)(struct net_device *dev, unsigned int table);
+ int (*dump_write)(struct net_device *dev, unsigned int table,
+ struct sk_buff *skb);
+};
+
+#ifdef CONFIG_INET
+extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops;
+#else
+#define udp_tunnel_nic_ops ((struct udp_tunnel_nic_ops *)NULL)
+#endif
+
+static inline void
+udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table,
+ unsigned int idx, struct udp_tunnel_info *ti)
+{
+ /* This helper is used from .sync_table, we indicate empty entries
+ * by zero'ed @ti. Drivers which need to know the details of a port
+ * when it gets deleted should use the .set_port / .unset_port
+ * callbacks.
+ * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings.
+ */
+ memset(ti, 0, sizeof(*ti));
+
+ if (udp_tunnel_nic_ops)
+ udp_tunnel_nic_ops->get_port(dev, table, idx, ti);
+}
+
+static inline void
+udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table,
+ unsigned int idx, u8 priv)
+{
+ if (udp_tunnel_nic_ops)
+ udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv);
+}
+
+static inline void
+udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti)
+{
+ if (udp_tunnel_nic_ops)
+ udp_tunnel_nic_ops->add_port(dev, ti);
+}
+
+static inline void
+udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti)
+{
+ if (udp_tunnel_nic_ops)
+ udp_tunnel_nic_ops->del_port(dev, ti);
+}
+
+/**
+ * udp_tunnel_nic_reset_ntf() - device-originating reset notification
+ * @dev: network interface device structure
+ *
+ * Called by the driver to inform the core that the entire UDP tunnel port
+ * state has been lost, usually due to device reset. Core will assume device
+ * forgot all the ports and issue .set_port and .sync_table callbacks as
+ * necessary.
+ *
+ * This function must be called with rtnl lock held, and will issue all
+ * the callbacks before returning.
+ */
+static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev)
+{
+ if (udp_tunnel_nic_ops)
+ udp_tunnel_nic_ops->reset_ntf(dev);
+}
+
+static inline size_t
+udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table)
+{
+ if (!udp_tunnel_nic_ops)
+ return 0;
+ return udp_tunnel_nic_ops->dump_size(dev, table);
+}
+
+static inline int
+udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table,
+ struct sk_buff *skb)
+{
+ if (!udp_tunnel_nic_ops)
+ return 0;
+ return udp_tunnel_nic_ops->dump_write(dev, table, skb);
+}
#endif
diff --git a/include/net/vsock_addr.h b/include/net/vsock_addr.h
index 57d2db5..cf8cc14 100644
--- a/include/net/vsock_addr.h
+++ b/include/net/vsock_addr.h
@@ -8,7 +8,7 @@
#ifndef _VSOCK_ADDR_H_
#define _VSOCK_ADDR_H_
-#include <linux/vm_sockets.h>
+#include <uapi/linux/vm_sockets.h>
void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port);
int vsock_addr_validate(const struct sockaddr_vm *addr);
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 373aadc..08537aa 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -7,6 +7,7 @@
#include <net/dst_metadata.h>
#include <net/rtnetlink.h>
#include <net/switchdev.h>
+#include <net/nexthop.h>
#define IANA_VXLAN_UDP_PORT 4789
@@ -120,6 +121,9 @@
#define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16)
#define VXLAN_GBP_ID_MASK (0xFFFF)
+#define VXLAN_GBP_MASK (VXLAN_GBP_DONT_LEARN | VXLAN_GBP_POLICY_APPLIED | \
+ VXLAN_GBP_ID_MASK)
+
/*
* VXLAN Generic Protocol Extension (VXLAN_F_GPE):
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -487,4 +491,28 @@
#undef VXLAN_FLAG
}
+static inline bool vxlan_fdb_nh_path_select(struct nexthop *nh,
+ int hash,
+ struct vxlan_rdst *rdst)
+{
+ struct fib_nh_common *nhc;
+
+ nhc = nexthop_path_fdb_result(nh, hash);
+ if (unlikely(!nhc))
+ return false;
+
+ switch (nhc->nhc_gw_family) {
+ case AF_INET:
+ rdst->remote_ip.sin.sin_addr.s_addr = nhc->nhc_gw.ipv4;
+ rdst->remote_ip.sa.sa_family = AF_INET;
+ break;
+ case AF_INET6:
+ rdst->remote_ip.sin6.sin6_addr = nhc->nhc_gw.ipv6;
+ rdst->remote_ip.sa.sa_family = AF_INET6;
+ break;
+ }
+
+ return true;
+}
+
#endif
diff --git a/include/net/wimax.h b/include/net/wimax.h
index 24ba7e8..f6e31d2 100644
--- a/include/net/wimax.h
+++ b/include/net/wimax.h
@@ -28,7 +28,7 @@
*
* USAGE
*
- * Embed a `struct wimax_dev` at the beginning of the the device's
+ * Embed a `struct wimax_dev` at the beginning of the device's
* private structure, initialize and register it. For details, see
* `struct wimax_dev`s documentation.
*
diff --git a/include/net/x25.h b/include/net/x25.h
index ed1acc3..d7d6c2b 100644
--- a/include/net/x25.h
+++ b/include/net/x25.h
@@ -62,7 +62,8 @@
X25_STATE_1, /* Awaiting Call Accepted */
X25_STATE_2, /* Awaiting Clear Confirmation */
X25_STATE_3, /* Data Transfer */
- X25_STATE_4 /* Awaiting Reset Confirmation */
+ X25_STATE_4, /* Awaiting Reset Confirmation */
+ X25_STATE_5 /* Call Accepted / Call Connected pending */
};
enum {
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 40c6d33..9dab2bc 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -6,6 +6,8 @@
#ifndef __LINUX_NET_XDP_H__
#define __LINUX_NET_XDP_H__
+#include <linux/skbuff.h> /* skb_shared_info */
+
/**
* DOC: XDP RX-queue information
*
@@ -37,7 +39,7 @@
MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */
MEM_TYPE_PAGE_ORDER0, /* Orig XDP full page model */
MEM_TYPE_PAGE_POOL,
- MEM_TYPE_ZERO_COPY,
+ MEM_TYPE_XSK_BUFF_POOL,
MEM_TYPE_MAX,
};
@@ -52,10 +54,6 @@
struct page_pool;
-struct zero_copy_allocator {
- void (*free)(struct zero_copy_allocator *zca, unsigned long handle);
-};
-
struct xdp_rxq_info {
struct net_device *dev;
u32 queue_index;
@@ -63,20 +61,42 @@
struct xdp_mem_info mem;
} ____cacheline_aligned; /* perf critical, avoid false-sharing */
+struct xdp_txq_info {
+ struct net_device *dev;
+};
+
struct xdp_buff {
void *data;
void *data_end;
void *data_meta;
void *data_hard_start;
- unsigned long handle;
struct xdp_rxq_info *rxq;
+ struct xdp_txq_info *txq;
+ u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
};
+/* Reserve memory area at end-of data area.
+ *
+ * This macro reserves tailroom in the XDP buffer by limiting the
+ * XDP/BPF data access to data_hard_end. Notice same area (and size)
+ * is used for XDP_PASS, when constructing the SKB via build_skb().
+ */
+#define xdp_data_hard_end(xdp) \
+ ((xdp)->data_hard_start + (xdp)->frame_sz - \
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
+static inline struct skb_shared_info *
+xdp_get_shared_info_from_buff(struct xdp_buff *xdp)
+{
+ return (struct skb_shared_info *)xdp_data_hard_end(xdp);
+}
+
struct xdp_frame {
void *data;
u16 len;
u16 headroom;
- u16 metasize;
+ u32 metasize:8;
+ u32 frame_sz:24;
/* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time,
* while mem info is valid on remote CPU.
*/
@@ -84,6 +104,22 @@
struct net_device *dev_rx; /* used by cpumap */
};
+
+static inline struct skb_shared_info *
+xdp_get_shared_info_from_frame(struct xdp_frame *frame)
+{
+ void *data_hard_start = frame->data - frame->headroom - sizeof(*frame);
+
+ return (struct skb_shared_info *)(data_hard_start + frame->frame_sz -
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
+}
+
+struct xdp_cpumap_stats {
+ unsigned int redirect;
+ unsigned int pass;
+ unsigned int drop;
+};
+
/* Clear kernel pointers in xdp_frame */
static inline void xdp_scrub_frame(struct xdp_frame *frame)
{
@@ -91,33 +127,63 @@
frame->dev_rx = NULL;
}
+/* Avoids inlining WARN macro in fast-path */
+void xdp_warn(const char *msg, const char *func, const int line);
+#define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)
+
struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp);
-/* Convert xdp_buff to xdp_frame */
static inline
-struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
+void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
{
- struct xdp_frame *xdp_frame;
- int metasize;
- int headroom;
+ xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame);
+ xdp->data = frame->data;
+ xdp->data_end = frame->data + frame->len;
+ xdp->data_meta = frame->data - frame->metasize;
+ xdp->frame_sz = frame->frame_sz;
+}
- if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY)
- return xdp_convert_zc_to_xdp_frame(xdp);
+static inline
+int xdp_update_frame_from_buff(struct xdp_buff *xdp,
+ struct xdp_frame *xdp_frame)
+{
+ int metasize, headroom;
/* Assure headroom is available for storing info */
headroom = xdp->data - xdp->data_hard_start;
metasize = xdp->data - xdp->data_meta;
metasize = metasize > 0 ? metasize : 0;
if (unlikely((headroom - metasize) < sizeof(*xdp_frame)))
- return NULL;
+ return -ENOSPC;
- /* Store info in top of packet */
- xdp_frame = xdp->data_hard_start;
+ /* Catch if driver didn't reserve tailroom for skb_shared_info */
+ if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) {
+ XDP_WARN("Driver BUG: missing reserved tailroom");
+ return -ENOSPC;
+ }
xdp_frame->data = xdp->data;
xdp_frame->len = xdp->data_end - xdp->data;
xdp_frame->headroom = headroom - sizeof(*xdp_frame);
xdp_frame->metasize = metasize;
+ xdp_frame->frame_sz = xdp->frame_sz;
+
+ return 0;
+}
+
+/* Convert xdp_buff to xdp_frame */
+static inline
+struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
+{
+ struct xdp_frame *xdp_frame;
+
+ if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
+ return xdp_convert_zc_to_xdp_frame(xdp);
+
+ /* Store info in top of packet */
+ xdp_frame = xdp->data_hard_start;
+ 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;
@@ -174,11 +240,9 @@
};
struct netdev_bpf;
-int xdp_attachment_query(struct xdp_attachment_info *info,
- struct netdev_bpf *bpf);
-bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
- struct netdev_bpf *bpf);
void xdp_attachment_setup(struct xdp_attachment_info *info,
struct netdev_bpf *bpf);
+#define DEV_MAP_BULK_SIZE 16
+
#endif /* __LINUX_NET_XDP_H__ */
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index c9398ce..cc17bc9 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -15,74 +15,39 @@
struct net_device;
struct xsk_queue;
-
-/* Masks for xdp_umem_page flags.
- * The low 12-bits of the addr will be 0 since this is the page address, so we
- * can use them for flags.
- */
-#define XSK_NEXT_PG_CONTIG_SHIFT 0
-#define XSK_NEXT_PG_CONTIG_MASK (1ULL << XSK_NEXT_PG_CONTIG_SHIFT)
-
-struct xdp_umem_page {
- void *addr;
- dma_addr_t dma;
-};
-
-struct xdp_umem_fq_reuse {
- u32 nentries;
- u32 length;
- u64 handles[];
-};
-
-/* Flags for the umem flags field.
- *
- * The NEED_WAKEUP flag is 1 due to the reuse of the flags field for public
- * flags. See inlude/uapi/include/linux/if_xdp.h.
- */
-#define XDP_UMEM_USES_NEED_WAKEUP (1 << 1)
+struct xdp_buff;
struct xdp_umem {
- struct xsk_queue *fq;
- struct xsk_queue *cq;
- struct xdp_umem_page *pages;
- u64 chunk_mask;
+ void *addrs;
u64 size;
u32 headroom;
- u32 chunk_size_nohr;
- struct user_struct *user;
- unsigned long address;
- refcount_t users;
- struct work_struct work;
- struct page **pgs;
+ u32 chunk_size;
+ u32 chunks;
u32 npgs;
- u16 queue_id;
- u8 need_wakeup;
+ struct user_struct *user;
+ refcount_t users;
u8 flags;
- int id;
- struct net_device *dev;
- struct xdp_umem_fq_reuse *fq_reuse;
bool zc;
- spinlock_t xsk_list_lock;
- struct list_head xsk_list;
+ struct page **pgs;
+ int id;
+ struct list_head xsk_dma_list;
+ struct work_struct work;
};
-/* Nodes are linked in the struct xdp_sock map_list field, and used to
- * track which maps a certain socket reside in.
- */
-struct xsk_map;
-struct xsk_map_node {
- struct list_head node;
- struct xsk_map *map;
- struct xdp_sock **map_entry;
+struct xsk_map {
+ struct bpf_map map;
+ spinlock_t lock; /* Synchronize map updates */
+ struct xdp_sock *xsk_map[];
};
struct xdp_sock {
/* struct sock must be the first member of struct xdp_sock */
struct sock sk;
- struct xsk_queue *rx;
+ struct xsk_queue *rx ____cacheline_aligned_in_smp;
struct net_device *dev;
struct xdp_umem *umem;
struct list_head flush_node;
+ struct xsk_buff_pool *pool;
u16 queue_id;
bool zc;
enum {
@@ -90,273 +55,66 @@
XSK_BOUND,
XSK_UNBOUND,
} state;
- /* Protects multiple processes in the control path */
- struct mutex mutex;
+
struct xsk_queue *tx ____cacheline_aligned_in_smp;
- struct list_head list;
- /* Mutual exclusion of NAPI TX thread and sendmsg error paths
- * in the SKB destructor callback.
- */
- spinlock_t tx_completion_lock;
+ struct list_head tx_list;
/* Protects generic receive. */
spinlock_t rx_lock;
+
+ /* Statistics */
u64 rx_dropped;
+ u64 rx_queue_full;
+
struct list_head map_list;
/* Protects map_list */
spinlock_t map_list_lock;
+ /* Protects multiple processes in the control path */
+ struct mutex mutex;
+ struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */
+ struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
};
-struct xdp_buff;
#ifdef CONFIG_XDP_SOCKETS
+
int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
-int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
-void xsk_flush(struct xdp_sock *xs);
-bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
-/* Used from netdev driver */
-bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt);
-u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr);
-void xsk_umem_discard_addr(struct xdp_umem *umem);
-void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
-bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc);
-void xsk_umem_consume_tx_done(struct xdp_umem *umem);
-struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries);
-struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem,
- struct xdp_umem_fq_reuse *newq);
-void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq);
-struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id);
-void xsk_set_rx_need_wakeup(struct xdp_umem *umem);
-void xsk_set_tx_need_wakeup(struct xdp_umem *umem);
-void xsk_clear_rx_need_wakeup(struct xdp_umem *umem);
-void xsk_clear_tx_need_wakeup(struct xdp_umem *umem);
-bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem);
+int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp);
+void __xsk_map_flush(void);
-void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
- struct xdp_sock **map_entry);
-int xsk_map_inc(struct xsk_map *map);
-void xsk_map_put(struct xsk_map *map);
-
-static inline u64 xsk_umem_extract_addr(u64 addr)
+static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
+ u32 key)
{
- return addr & XSK_UNALIGNED_BUF_ADDR_MASK;
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+ struct xdp_sock *xs;
+
+ if (key >= map->max_entries)
+ return NULL;
+
+ xs = READ_ONCE(m->xsk_map[key]);
+ return xs;
}
-static inline u64 xsk_umem_extract_offset(u64 addr)
-{
- return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
-}
-
-static inline u64 xsk_umem_add_offset_to_addr(u64 addr)
-{
- return xsk_umem_extract_addr(addr) + xsk_umem_extract_offset(addr);
-}
-
-static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
-{
- unsigned long page_addr;
-
- addr = xsk_umem_add_offset_to_addr(addr);
- page_addr = (unsigned long)umem->pages[addr >> PAGE_SHIFT].addr;
-
- return (char *)(page_addr & PAGE_MASK) + (addr & ~PAGE_MASK);
-}
-
-static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
-{
- addr = xsk_umem_add_offset_to_addr(addr);
-
- return umem->pages[addr >> PAGE_SHIFT].dma + (addr & ~PAGE_MASK);
-}
-
-/* Reuse-queue aware version of FILL queue helpers */
-static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
-{
- struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
-
- if (rq->length >= cnt)
- return true;
-
- return xsk_umem_has_addrs(umem, cnt - rq->length);
-}
-
-static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
-{
- struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
-
- if (!rq->length)
- return xsk_umem_peek_addr(umem, addr);
-
- *addr = rq->handles[rq->length - 1];
- return addr;
-}
-
-static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem)
-{
- struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
-
- if (!rq->length)
- xsk_umem_discard_addr(umem);
- else
- rq->length--;
-}
-
-static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
-{
- struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
-
- rq->handles[rq->length++] = addr;
-}
-
-/* Handle the offset appropriately depending on aligned or unaligned mode.
- * For unaligned mode, we store the offset in the upper 16-bits of the address.
- * For aligned mode, we simply add the offset to the address.
- */
-static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 address,
- u64 offset)
-{
- if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG)
- return address + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
- else
- return address + offset;
-}
#else
+
static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
return -ENOTSUPP;
}
-static inline int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+static inline int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp)
{
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
}
-static inline void xsk_flush(struct xdp_sock *xs)
+static inline void __xsk_map_flush(void)
{
}
-static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
-{
- return false;
-}
-
-static inline bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt)
-{
- return false;
-}
-
-static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
+static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
+ u32 key)
{
return NULL;
}
-static inline void xsk_umem_discard_addr(struct xdp_umem *umem)
-{
-}
-
-static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
-{
-}
-
-static inline bool xsk_umem_consume_tx(struct xdp_umem *umem,
- struct xdp_desc *desc)
-{
- return false;
-}
-
-static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem)
-{
-}
-
-static inline struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries)
-{
- return NULL;
-}
-
-static inline struct xdp_umem_fq_reuse *xsk_reuseq_swap(
- struct xdp_umem *umem,
- struct xdp_umem_fq_reuse *newq)
-{
- return NULL;
-}
-static inline void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq)
-{
-}
-
-static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
- u16 queue_id)
-{
- return NULL;
-}
-
-static inline u64 xsk_umem_extract_addr(u64 addr)
-{
- return 0;
-}
-
-static inline u64 xsk_umem_extract_offset(u64 addr)
-{
- return 0;
-}
-
-static inline u64 xsk_umem_add_offset_to_addr(u64 addr)
-{
- return 0;
-}
-
-static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
-{
- return NULL;
-}
-
-static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
-{
- return 0;
-}
-
-static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
-{
- return false;
-}
-
-static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
-{
- return NULL;
-}
-
-static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem)
-{
-}
-
-static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
-{
-}
-
-static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
-{
-}
-
-static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
-{
-}
-
-static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
-{
-}
-
-static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
-{
-}
-
-static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
-{
- return false;
-}
-
-static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle,
- u64 offset)
-{
- return 0;
-}
-
#endif /* CONFIG_XDP_SOCKETS */
#endif /* _LINUX_XDP_SOCK_H */
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
new file mode 100644
index 0000000..5b1ee8a
--- /dev/null
+++ b/include/net/xdp_sock_drv.h
@@ -0,0 +1,240 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Interface for implementing AF_XDP zero-copy support in drivers.
+ * Copyright(c) 2020 Intel Corporation.
+ */
+
+#ifndef _LINUX_XDP_SOCK_DRV_H
+#define _LINUX_XDP_SOCK_DRV_H
+
+#include <net/xdp_sock.h>
+#include <net/xsk_buff_pool.h>
+
+#ifdef CONFIG_XDP_SOCKETS
+
+void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
+bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
+void xsk_tx_release(struct xsk_buff_pool *pool);
+struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
+ u16 queue_id);
+void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool);
+bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool);
+
+static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
+{
+ return XDP_PACKET_HEADROOM + pool->headroom;
+}
+
+static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
+{
+ return pool->chunk_size;
+}
+
+static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
+{
+ return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool);
+}
+
+static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
+ struct xdp_rxq_info *rxq)
+{
+ xp_set_rxq_info(pool, rxq);
+}
+
+static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
+ unsigned long attrs)
+{
+ xp_dma_unmap(pool, attrs);
+}
+
+static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
+ struct device *dev, unsigned long attrs)
+{
+ struct xdp_umem *umem = pool->umem;
+
+ return xp_dma_map(pool, dev, attrs, umem->pgs, umem->npgs);
+}
+
+static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp)
+{
+ struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+
+ return xp_get_dma(xskb);
+}
+
+static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
+{
+ struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+
+ return xp_get_frame_dma(xskb);
+}
+
+static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
+{
+ return xp_alloc(pool);
+}
+
+static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
+{
+ return xp_can_alloc(pool, count);
+}
+
+static inline void xsk_buff_free(struct xdp_buff *xdp)
+{
+ struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+
+ xp_free(xskb);
+}
+
+static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
+ u64 addr)
+{
+ return xp_raw_get_dma(pool, addr);
+}
+
+static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
+{
+ return xp_raw_get_data(pool, addr);
+}
+
+static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
+{
+ struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+
+ if (!pool->dma_need_sync)
+ return;
+
+ xp_dma_sync_for_cpu(xskb);
+}
+
+static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
+ dma_addr_t dma,
+ size_t size)
+{
+ xp_dma_sync_for_device(pool, dma, size);
+}
+
+#else
+
+static inline void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries)
+{
+}
+
+static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool,
+ struct xdp_desc *desc)
+{
+ return false;
+}
+
+static inline void xsk_tx_release(struct xsk_buff_pool *pool)
+{
+}
+
+static inline struct xsk_buff_pool *
+xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id)
+{
+ return NULL;
+}
+
+static inline void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
+{
+}
+
+static inline void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
+{
+}
+
+static inline void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool)
+{
+}
+
+static inline void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
+{
+}
+
+static inline bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
+{
+ return false;
+}
+
+static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
+{
+ return 0;
+}
+
+static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
+{
+ return 0;
+}
+
+static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
+{
+ return 0;
+}
+
+static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
+ struct xdp_rxq_info *rxq)
+{
+}
+
+static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
+ unsigned long attrs)
+{
+}
+
+static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
+ struct device *dev, unsigned long attrs)
+{
+ return 0;
+}
+
+static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp)
+{
+ return 0;
+}
+
+static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
+{
+ return 0;
+}
+
+static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
+{
+ return NULL;
+}
+
+static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
+{
+ return false;
+}
+
+static inline void xsk_buff_free(struct xdp_buff *xdp)
+{
+}
+
+static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
+ u64 addr)
+{
+ return 0;
+}
+
+static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
+{
+ return NULL;
+}
+
+static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
+{
+}
+
+static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
+ dma_addr_t dma,
+ size_t size)
+{
+}
+
+#endif /* CONFIG_XDP_SOCKETS */
+
+#endif /* _LINUX_XDP_SOCK_DRV_H */
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 8ce6385..0049a74 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -15,6 +15,7 @@
#include <linux/audit.h>
#include <linux/slab.h>
#include <linux/refcount.h>
+#include <linux/sockptr.h>
#include <net/sock.h>
#include <net/dst.h>
@@ -127,6 +128,7 @@
struct xfrm_state_offload {
struct net_device *dev;
+ struct net_device *real_dev;
unsigned long offload_handle;
unsigned int num_exthdrs;
u8 flags;
@@ -191,8 +193,14 @@
struct xfrm_algo_aead *aead;
const char *geniv;
+ /* mapping change rate limiting */
+ __be16 new_mapping_sport;
+ u32 new_mapping; /* seconds */
+ u32 mapping_maxage; /* seconds for input SA */
+
/* Data for encapsulator */
struct xfrm_encap_tmpl *encap;
+ struct sock __rcu *encap_sk;
/* Data for care-of address */
xfrm_address_t *coaddr;
@@ -360,11 +368,6 @@
const struct xfrm_type *type_dstopts;
int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
- int (*output_finish)(struct sock *sk, struct sk_buff *skb);
- int (*extract_input)(struct xfrm_state *x,
- struct sk_buff *skb);
- int (*extract_output)(struct xfrm_state *x,
- struct sk_buff *skb);
int (*transport_finish)(struct sk_buff *skb,
int async);
void (*local_error)(struct sk_buff *skb, u32 mtu);
@@ -376,7 +379,8 @@
struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family);
struct xfrm_input_afinfo {
- unsigned int family;
+ u8 family;
+ bool is_ipip;
int (*callback)(struct sk_buff *skb, u8 protocol,
int err);
};
@@ -1406,6 +1410,8 @@
struct xfrm6_protocol {
int (*handler)(struct sk_buff *skb);
+ int (*input_handler)(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type);
int (*cb_handler)(struct sk_buff *skb, int err);
int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info);
@@ -1417,6 +1423,7 @@
/* XFRM tunnel handlers. */
struct xfrm_tunnel {
int (*handler)(struct sk_buff *skb);
+ int (*cb_handler)(struct sk_buff *skb, int err);
int (*err_handler)(struct sk_buff *skb, u32 info);
struct xfrm_tunnel __rcu *next;
@@ -1425,6 +1432,7 @@
struct xfrm6_tunnel {
int (*handler)(struct sk_buff *skb);
+ int (*cb_handler)(struct sk_buff *skb, int err);
int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info);
struct xfrm6_tunnel __rcu *next;
@@ -1543,16 +1551,18 @@
void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
int xfrm_init_replay(struct xfrm_state *x);
-u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu);
u32 xfrm_state_mtu(struct xfrm_state *x, int mtu);
int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload);
int xfrm_init_state(struct xfrm_state *x);
int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type);
int xfrm_input_resume(struct sk_buff *skb, int nexthdr);
+int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
+ int (*finish)(struct net *, struct sock *,
+ struct sk_buff *));
int xfrm_trans_queue(struct sk_buff *skb,
int (*finish)(struct net *, struct sock *,
struct sk_buff *));
-int xfrm_output_resume(struct sk_buff *skb, int err);
+int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err);
int xfrm_output(struct sock *sk, struct sk_buff *skb);
#if IS_ENABLED(CONFIG_NET_PKTGEN)
@@ -1560,7 +1570,6 @@
#endif
void xfrm_local_error(struct sk_buff *skb, int mtu);
-int xfrm4_extract_header(struct sk_buff *skb);
int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb);
int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
int encap_type);
@@ -1576,7 +1585,6 @@
return xfrm_input(skb, nexthdr, spi, 0);
}
-int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb);
int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb);
int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb);
int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol);
@@ -1584,10 +1592,11 @@
int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family);
int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family);
void xfrm4_local_error(struct sk_buff *skb, u32 mtu);
-int xfrm6_extract_header(struct sk_buff *skb);
int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb);
int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi,
struct ip6_tnl *t);
+int xfrm6_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type);
int xfrm6_transport_finish(struct sk_buff *skb, int async);
int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t);
int xfrm6_rcv(struct sk_buff *skb);
@@ -1600,28 +1609,23 @@
int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family);
__be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr);
__be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr);
-int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb);
int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb);
int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb);
int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
u8 **prevhdr);
#ifdef CONFIG_XFRM
+void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu);
int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb);
-int xfrm_user_policy(struct sock *sk, int optname,
- u8 __user *optval, int optlen);
+int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb);
+int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval,
+ int optlen);
#else
-static inline int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
+static inline int xfrm_user_policy(struct sock *sk, int optname,
+ sockptr_t optval, int optlen)
{
return -ENOPROTOOPT;
}
-
-static inline int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
-{
- /* should not happen */
- kfree_skb(skb);
- return 0;
-}
#endif
struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
@@ -1664,14 +1668,15 @@
const struct xfrm_migrate *m, int num_bundles,
const struct xfrm_kmaddress *k,
const struct xfrm_encap_tmpl *encap);
-struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net);
+struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net,
+ u32 if_id);
struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
struct xfrm_migrate *m,
struct xfrm_encap_tmpl *encap);
int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
struct xfrm_migrate *m, int num_bundles,
struct xfrm_kmaddress *k, struct net *net,
- struct xfrm_encap_tmpl *encap);
+ struct xfrm_encap_tmpl *encap, u32 if_id);
#endif
int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport);
@@ -1996,4 +2001,53 @@
return 0;
}
+
+extern const int xfrm_msg_min[XFRM_NR_MSGTYPES];
+extern const struct nla_policy xfrma_policy[XFRMA_MAX+1];
+
+struct xfrm_translator {
+ /* Allocate frag_list and put compat translation there */
+ int (*alloc_compat)(struct sk_buff *skb, const struct nlmsghdr *src);
+
+ /* Allocate nlmsg with 64-bit translaton of received 32-bit message */
+ struct nlmsghdr *(*rcv_msg_compat)(const struct nlmsghdr *nlh,
+ int maxtype, const struct nla_policy *policy,
+ struct netlink_ext_ack *extack);
+
+ /* Translate 32-bit user_policy from sockptr */
+ int (*xlate_user_policy_sockptr)(u8 **pdata32, int optlen);
+
+ struct module *owner;
+};
+
+#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT)
+extern int xfrm_register_translator(struct xfrm_translator *xtr);
+extern int xfrm_unregister_translator(struct xfrm_translator *xtr);
+extern struct xfrm_translator *xfrm_get_translator(void);
+extern void xfrm_put_translator(struct xfrm_translator *xtr);
+#else
+static inline struct xfrm_translator *xfrm_get_translator(void)
+{
+ return NULL;
+}
+static inline void xfrm_put_translator(struct xfrm_translator *xtr)
+{
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline bool xfrm6_local_dontfrag(const struct sock *sk)
+{
+ int proto;
+
+ if (!sk || sk->sk_family != AF_INET6)
+ return false;
+
+ proto = sk->sk_protocol;
+ if (proto == IPPROTO_UDP || proto == IPPROTO_RAW)
+ return inet6_sk(sk)->dontfrag;
+
+ return false;
+}
+#endif
#endif /* _NET_XFRM_H */
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
new file mode 100644
index 0000000..7a9a23e
--- /dev/null
+++ b/include/net/xsk_buff_pool.h
@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2020 Intel Corporation. */
+
+#ifndef XSK_BUFF_POOL_H_
+#define XSK_BUFF_POOL_H_
+
+#include <linux/if_xdp.h>
+#include <linux/types.h>
+#include <linux/dma-mapping.h>
+#include <net/xdp.h>
+
+struct xsk_buff_pool;
+struct xdp_rxq_info;
+struct xsk_queue;
+struct xdp_desc;
+struct xdp_umem;
+struct xdp_sock;
+struct device;
+struct page;
+
+struct xdp_buff_xsk {
+ struct xdp_buff xdp;
+ dma_addr_t dma;
+ dma_addr_t frame_dma;
+ struct xsk_buff_pool *pool;
+ bool unaligned;
+ u64 orig_addr;
+ struct list_head free_list_node;
+};
+
+struct xsk_dma_map {
+ dma_addr_t *dma_pages;
+ struct device *dev;
+ struct net_device *netdev;
+ refcount_t users;
+ struct list_head list; /* Protected by the RTNL_LOCK */
+ u32 dma_pages_cnt;
+ bool dma_need_sync;
+};
+
+struct xsk_buff_pool {
+ /* Members only used in the control path first. */
+ struct device *dev;
+ struct net_device *netdev;
+ struct list_head xsk_tx_list;
+ /* Protects modifications to the xsk_tx_list */
+ spinlock_t xsk_tx_list_lock;
+ refcount_t users;
+ struct xdp_umem *umem;
+ struct work_struct work;
+ struct list_head free_list;
+ u32 heads_cnt;
+ u16 queue_id;
+
+ /* Data path members as close to free_heads at the end as possible. */
+ struct xsk_queue *fq ____cacheline_aligned_in_smp;
+ struct xsk_queue *cq;
+ /* For performance reasons, each buff pool has its own array of dma_pages
+ * even when they are identical.
+ */
+ dma_addr_t *dma_pages;
+ struct xdp_buff_xsk *heads;
+ u64 chunk_mask;
+ u64 addrs_cnt;
+ u32 free_list_cnt;
+ u32 dma_pages_cnt;
+ u32 free_heads_cnt;
+ u32 headroom;
+ u32 chunk_size;
+ u32 frame_len;
+ u8 cached_need_wakeup;
+ bool uses_need_wakeup;
+ bool dma_need_sync;
+ bool unaligned;
+ void *addrs;
+ /* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect:
+ * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when
+ * sockets share a single cq when the same netdev and queue id is shared.
+ */
+ spinlock_t cq_lock;
+ struct xdp_buff_xsk *free_heads[];
+};
+
+/* AF_XDP core. */
+struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
+ struct xdp_umem *umem);
+int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
+ u16 queue_id, u16 flags);
+int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
+ struct net_device *dev, u16 queue_id);
+void xp_destroy(struct xsk_buff_pool *pool);
+void xp_release(struct xdp_buff_xsk *xskb);
+void xp_get_pool(struct xsk_buff_pool *pool);
+bool xp_put_pool(struct xsk_buff_pool *pool);
+void xp_clear_dev(struct xsk_buff_pool *pool);
+void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
+void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
+
+/* AF_XDP, and XDP core. */
+void xp_free(struct xdp_buff_xsk *xskb);
+
+/* AF_XDP ZC drivers, via xdp_sock_buff.h */
+void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq);
+int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
+ unsigned long attrs, struct page **pages, u32 nr_pages);
+void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs);
+struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool);
+bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count);
+void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr);
+dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr);
+static inline dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb)
+{
+ return xskb->dma;
+}
+
+static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb)
+{
+ return xskb->frame_dma;
+}
+
+void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb);
+static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb)
+{
+ xp_dma_sync_for_cpu_slow(xskb);
+}
+
+void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma,
+ size_t size);
+static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool,
+ dma_addr_t dma, size_t size)
+{
+ if (!pool->dma_need_sync)
+ return;
+
+ xp_dma_sync_for_device_slow(pool, dma, size);
+}
+
+/* Masks for xdp_umem_page flags.
+ * The low 12-bits of the addr will be 0 since this is the page address, so we
+ * can use them for flags.
+ */
+#define XSK_NEXT_PG_CONTIG_SHIFT 0
+#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
+
+static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool,
+ u64 addr, u32 len)
+{
+ bool cross_pg = (addr & (PAGE_SIZE - 1)) + len > PAGE_SIZE;
+
+ if (likely(!cross_pg))
+ return false;
+
+ if (pool->dma_pages_cnt) {
+ return !(pool->dma_pages[addr >> PAGE_SHIFT] &
+ XSK_NEXT_PG_CONTIG_MASK);
+ }
+
+ /* skb path */
+ return addr + len > pool->addrs_cnt;
+}
+
+static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr)
+{
+ return addr & pool->chunk_mask;
+}
+
+static inline u64 xp_unaligned_extract_addr(u64 addr)
+{
+ return addr & XSK_UNALIGNED_BUF_ADDR_MASK;
+}
+
+static inline u64 xp_unaligned_extract_offset(u64 addr)
+{
+ return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
+}
+
+static inline u64 xp_unaligned_add_offset_to_addr(u64 addr)
+{
+ return xp_unaligned_extract_addr(addr) +
+ xp_unaligned_extract_offset(addr);
+}
+
+#endif /* XSK_BUFF_POOL_H_ */