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/linux/netdevice.h b/include/linux/netdevice.h
index ddc66ab..861f248 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -53,6 +53,9 @@
struct device;
struct phy_device;
struct dsa_port;
+struct ip_tunnel_parm;
+struct macsec_context;
+struct macsec_ops;
struct sfp_bus;
/* 802.11 specific */
@@ -62,9 +65,12 @@
struct mpls_dev;
/* UDP Tunnel offloads */
struct udp_tunnel_info;
+struct udp_tunnel_nic_info;
+struct udp_tunnel_nic;
struct bpf_prog;
struct xdp_buff;
+void synchronize_net(void);
void netdev_set_default_ethtool_ops(struct net_device *dev,
const struct ethtool_ops *ops);
@@ -206,9 +212,8 @@
unsigned char type;
#define NETDEV_HW_ADDR_T_LAN 1
#define NETDEV_HW_ADDR_T_SAN 2
-#define NETDEV_HW_ADDR_T_SLAVE 3
-#define NETDEV_HW_ADDR_T_UNICAST 4
-#define NETDEV_HW_ADDR_T_MULTICAST 5
+#define NETDEV_HW_ADDR_T_UNICAST 3
+#define NETDEV_HW_ADDR_T_MULTICAST 4
bool global_use;
int sync_cnt;
int refcount;
@@ -286,6 +291,7 @@
__LINK_STATE_NOCARRIER,
__LINK_STATE_LINKWATCH_PENDING,
__LINK_STATE_DORMANT,
+ __LINK_STATE_TESTING,
};
@@ -326,6 +332,7 @@
unsigned long state;
int weight;
+ int defer_hard_irqs_count;
unsigned long gro_bitmask;
int (*poll)(struct napi_struct *, int);
#ifdef CONFIG_NETPOLL
@@ -347,7 +354,7 @@
NAPI_STATE_MISSED, /* reschedule a napi */
NAPI_STATE_DISABLE, /* Disable pending */
NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */
- NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */
+ NAPI_STATE_LISTED, /* NAPI added to system lists */
NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
};
@@ -357,7 +364,7 @@
NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED),
NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE),
NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC),
- NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED),
+ NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED),
NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
};
@@ -482,20 +489,6 @@
}
/**
- * napi_hash_del - remove a NAPI from global table
- * @napi: NAPI context
- *
- * Warning: caller must observe RCU grace period
- * before freeing memory containing @napi, if
- * this function returns true.
- * Note: core networking stack automatically calls it
- * from netif_napi_del().
- * Drivers might want to call this helper to combine all
- * the needed RCU grace periods into a single one.
- */
-bool napi_hash_del(struct napi_struct *napi);
-
-/**
* napi_disable - prevent NAPI from scheduling
* @n: NAPI context
*
@@ -611,7 +604,7 @@
/* Subordinate device that the queue has been assigned to */
struct net_device *sb_dev;
#ifdef CONFIG_XDP_SOCKETS
- struct xdp_umem *umem;
+ struct xsk_buff_pool *pool;
#endif
/*
* write-mostly part
@@ -633,11 +626,16 @@
extern int sysctl_fb_tunnels_only_for_init_net;
extern int sysctl_devconf_inherit_init_net;
+/*
+ * sysctl_fb_tunnels_only_for_init_net == 0 : For all netns
+ * == 1 : For initns only
+ * == 2 : For none.
+ */
static inline bool net_has_fallback_tunnels(const struct net *net)
{
- return net == &init_net ||
- !IS_ENABLED(CONFIG_SYSCTL) ||
- !sysctl_fb_tunnels_only_for_init_net;
+ return !IS_ENABLED(CONFIG_SYSCTL) ||
+ !sysctl_fb_tunnels_only_for_init_net ||
+ (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1);
}
static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
@@ -664,7 +662,7 @@
struct rps_map {
unsigned int len;
struct rcu_head rcu;
- u16 cpus[0];
+ u16 cpus[];
};
#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16)))
@@ -686,7 +684,7 @@
struct rps_dev_flow_table {
unsigned int mask;
struct rcu_head rcu;
- struct rps_dev_flow flows[0];
+ struct rps_dev_flow flows[];
};
#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \
((_num) * sizeof(struct rps_dev_flow)))
@@ -704,7 +702,7 @@
struct rps_sock_flow_table {
u32 mask;
- u32 ents[0] ____cacheline_aligned_in_smp;
+ u32 ents[] ____cacheline_aligned_in_smp;
};
#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num]))
@@ -744,7 +742,7 @@
struct net_device *dev;
struct xdp_rxq_info xdp_rxq;
#ifdef CONFIG_XDP_SOCKETS
- struct xdp_umem *umem;
+ struct xsk_buff_pool *pool;
#endif
} ____cacheline_aligned_in_smp;
@@ -767,7 +765,7 @@
unsigned int len;
unsigned int alloc_len;
struct rcu_head rcu;
- u16 queues[0];
+ u16 queues[];
};
#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16)))
#define XPS_MIN_MAP_ALLOC ((L1_CACHE_ALIGN(offsetof(struct xps_map, queues[1])) \
@@ -778,7 +776,7 @@
*/
struct xps_dev_maps {
struct rcu_head rcu;
- struct xps_map __rcu *attr_map[0]; /* Either CPUs map or RXQs map */
+ struct xps_map __rcu *attr_map[]; /* Either CPUs map or RXQs map */
};
#define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \
@@ -850,6 +848,10 @@
TC_SETUP_ROOT_QDISC,
TC_SETUP_QDISC_GRED,
TC_SETUP_QDISC_TAPRIO,
+ TC_SETUP_FT,
+ TC_SETUP_QDISC_ETS,
+ TC_SETUP_QDISC_TBF,
+ TC_SETUP_QDISC_FIFO,
};
/* These structures hold the attributes of bpf state that are being passed
@@ -865,17 +867,29 @@
*/
XDP_SETUP_PROG,
XDP_SETUP_PROG_HW,
- XDP_QUERY_PROG,
- XDP_QUERY_PROG_HW,
/* BPF program for offload callbacks, invoked at program load time. */
BPF_OFFLOAD_MAP_ALLOC,
BPF_OFFLOAD_MAP_FREE,
- XDP_SETUP_XSK_UMEM,
+ XDP_SETUP_XSK_POOL,
};
struct bpf_prog_offload_ops;
struct netlink_ext_ack;
struct xdp_umem;
+struct xdp_dev_bulk_queue;
+struct bpf_xdp_link;
+
+enum bpf_xdp_mode {
+ XDP_MODE_SKB = 0,
+ XDP_MODE_DRV = 1,
+ XDP_MODE_HW = 2,
+ __MAX_XDP_MODE
+};
+
+struct bpf_xdp_entity {
+ struct bpf_prog *prog;
+ struct bpf_xdp_link *link;
+};
struct netdev_bpf {
enum bpf_netdev_command command;
@@ -886,19 +900,13 @@
struct bpf_prog *prog;
struct netlink_ext_ack *extack;
};
- /* XDP_QUERY_PROG, XDP_QUERY_PROG_HW */
- struct {
- u32 prog_id;
- /* flags with which program was installed */
- u32 prog_flags;
- };
/* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */
struct {
struct bpf_offloaded_map *offmap;
};
- /* XDP_SETUP_XSK_UMEM */
+ /* XDP_SETUP_XSK_POOL */
struct {
- struct xdp_umem *umem;
+ struct xsk_buff_pool *pool;
u16 queue_id;
} xsk;
};
@@ -927,6 +935,20 @@
struct devlink;
struct tlsdev_ops;
+struct netdev_name_node {
+ struct hlist_node hlist;
+ struct list_head list;
+ struct net_device *dev;
+ const char *name;
+};
+
+int netdev_name_node_alt_create(struct net_device *dev, const char *name);
+int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
+
+struct netdev_net_notifier {
+ struct list_head list;
+ struct notifier_block *nb;
+};
/*
* This structure defines the management hooks for network devices.
@@ -1006,7 +1028,7 @@
* Called when a user wants to change the Maximum Transfer Unit
* of a device.
*
- * void (*ndo_tx_timeout)(struct net_device *dev);
+ * void (*ndo_tx_timeout)(struct net_device *dev, unsigned int txqueue);
* Callback used when the transmitter has not made any progress
* for dev->watchdog ticks.
*
@@ -1125,6 +1147,12 @@
* int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);
* Called to release previously enslaved netdev.
*
+ * struct net_device *(*ndo_get_xmit_slave)(struct net_device *dev,
+ * struct sk_buff *skb,
+ * bool all_slaves);
+ * Get the xmit slave of master device. If all_slaves is true, function
+ * assume all the slaves can transmit.
+ *
* Feature/offload setting functions.
* netdev_features_t (*ndo_fix_features)(struct net_device *dev,
* netdev_features_t features);
@@ -1245,6 +1273,12 @@
* Get devlink port instance associated with a given netdev.
* Called with a reference on the netdevice and devlink locks only,
* rtnl_lock is not held.
+ * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p,
+ * int cmd);
+ * Add, change, delete or get information on an IPv4 tunnel.
+ * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
+ * If a device is paired with a peer device, return the peer instance.
+ * The caller must be under RCU read context.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1273,7 +1307,8 @@
int new_mtu);
int (*ndo_neigh_setup)(struct net_device *dev,
struct neigh_parms *);
- void (*ndo_tx_timeout) (struct net_device *dev);
+ void (*ndo_tx_timeout) (struct net_device *dev,
+ unsigned int txqueue);
void (*ndo_get_stats64)(struct net_device *dev,
struct rtnl_link_stats64 *storage);
@@ -1319,6 +1354,10 @@
struct nlattr *port[]);
int (*ndo_get_vf_port)(struct net_device *dev,
int vf, struct sk_buff *skb);
+ int (*ndo_get_vf_guid)(struct net_device *dev,
+ int vf,
+ struct ifla_vf_guid *node_guid,
+ struct ifla_vf_guid *port_guid);
int (*ndo_set_vf_guid)(struct net_device *dev,
int vf, u64 guid,
int guid_type);
@@ -1363,6 +1402,9 @@
struct netlink_ext_ack *extack);
int (*ndo_del_slave)(struct net_device *dev,
struct net_device *slave_dev);
+ struct net_device* (*ndo_get_xmit_slave)(struct net_device *dev,
+ struct sk_buff *skb,
+ bool all_slaves);
netdev_features_t (*ndo_fix_features)(struct net_device *dev,
netdev_features_t features);
int (*ndo_set_features)(struct net_device *dev,
@@ -1442,6 +1484,9 @@
int (*ndo_xsk_wakeup)(struct net_device *dev,
u32 queue_id, u32 flags);
struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev);
+ int (*ndo_tunnel_ctl)(struct net_device *dev,
+ struct ip_tunnel_parm *p, int cmd);
+ struct net_device * (*ndo_get_peer_dev)(struct net_device *dev);
};
/**
@@ -1572,7 +1617,7 @@
* (i.e. as seen by users in the "Space.c" file). It is the name
* of the interface.
*
- * @name_hlist: Device name hash chain, please keep it close to name[]
+ * @name_node: Name hashlist node
* @ifalias: SNMP alias
* @mem_end: Shared memory end
* @mem_start: Shared memory start
@@ -1601,6 +1646,7 @@
* and drivers will need to set them appropriately.
*
* @mpls_features: Mask of features inheritable by MPLS
+ * @gso_partial_features: value(s) from NETIF_F_GSO\*
*
* @ifindex: interface index
* @group: The group the device belongs to
@@ -1625,8 +1671,11 @@
* @netdev_ops: Includes several pointers to callbacks,
* if one wants to override the ndo_*() functions
* @ethtool_ops: Management operations
+ * @l3mdev_ops: Layer 3 master device operations
* @ndisc_ops: Includes callbacks for different IPv6 neighbour
* discovery handling. Necessary for e.g. 6LoWPAN.
+ * @xfrmdev_ops: Transformation offload operations
+ * @tlsdev_ops: Transport Layer Security offload operations
* @header_ops: Includes callbacks for creating,parsing,caching,etc
* of Layer 2 headers.
*
@@ -1665,6 +1714,7 @@
* @dev_port: Used to differentiate devices that share
* the same function
* @addr_list_lock: XXX: need comments on this one
+ * @name_assign_type: network interface name assignment type
* @uc_promisc: Counter that indicates promiscuous mode
* has been enabled due to the need to listen to
* additional unicast addresses in a device that
@@ -1687,6 +1737,9 @@
* @ip6_ptr: IPv6 specific data
* @ax25_ptr: AX.25 specific data
* @ieee80211_ptr: IEEE 802.11 specific data, assign before registering
+ * @ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network
+ * device struct
+ * @mpls_ptr: mpls_dev struct pointer
*
* @dev_addr: Hw address (before bcast,
* because most packets are unicast)
@@ -1695,12 +1748,17 @@
* @num_rx_queues: Number of RX queues
* allocated at register_netdev() time
* @real_num_rx_queues: Number of RX queues currently active in device
+ * @xdp_prog: XDP sockets filter program pointer
+ * @gro_flush_timeout: timeout for GRO layer in NAPI
+ * @napi_defer_hard_irqs: If not zero, provides a counter that would
+ * allow to avoid NIC hard IRQ, on busy queues.
*
* @rx_handler: handler for received packets
* @rx_handler_data: XXX: need comments on this one
* @miniq_ingress: ingress/clsact qdisc specific data for
* ingress processing
* @ingress_queue: XXX: need comments on this one
+ * @nf_hooks_ingress: netfilter hooks executed for ingress packets
* @broadcast: hw bcast address
*
* @rx_cpu_rmap: CPU reverse-mapping for RX completion interrupts,
@@ -1715,14 +1773,19 @@
* @qdisc: Root qdisc from userspace point of view
* @tx_queue_len: Max frames per queue allowed
* @tx_global_lock: XXX: need comments on this one
+ * @xdp_bulkq: XDP device bulk queue
+ * @xps_cpus_map: all CPUs map for XPS device
+ * @xps_rxqs_map: all RXQs map for XPS device
*
* @xps_maps: XXX: need comments on this one
* @miniq_egress: clsact qdisc specific data for
* egress processing
+ * @qdisc_hash: qdisc hash table
* @watchdog_timeo: Represents the timeout that is used by
* the watchdog (see dev_watchdog())
* @watchdog_timer: List of timers
*
+ * @proto_down_reason: reason a netdev interface is held down
* @pcpu_refcnt: Number of references to this device
* @todo_list: Delayed register/unregister
* @link_watch_list: XXX: need comments on this one
@@ -1769,13 +1832,9 @@
* @phydev: Physical device may attach itself
* for hardware timestamping
* @sfp_bus: attached &struct sfp_bus structure.
- * @qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock
- * spinlock
- * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount
- * @qdisc_xmit_lock_key: lockdep class annotating
- * netdev_queue->_xmit_lock spinlock
- * @addr_list_lock_key: lockdep class annotating
- * net_device->addr_list_lock spinlock
+ *
+ * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock
+ * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount
*
* @proto_down: protocol port state information can be sent to the
* switch driver and used to set the phys state of the
@@ -1783,13 +1842,29 @@
*
* @wol_enabled: Wake-on-LAN is enabled
*
+ * @net_notifier_list: List of per-net netdev notifier block
+ * that follow this device when it is moved
+ * to another network namespace.
+ *
+ * @macsec_ops: MACsec offloading ops
+ *
+ * @udp_tunnel_nic_info: static structure describing the UDP tunnel
+ * offload capabilities of the device
+ * @udp_tunnel_nic: UDP tunnel offload state
+ * @xdp_state: stores info on attached XDP BPF programs
+ *
+ * @nested_level: Used as as a parameter of spin_lock_nested() of
+ * dev->addr_list_lock.
+ * @unlink_list: As netif_addr_lock() can be called recursively,
+ * keep a list of interfaces to be deleted.
+ *
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
*/
struct net_device {
char name[IFNAMSIZ];
- struct hlist_node name_hlist;
+ struct netdev_name_node *name_node;
struct dev_ifalias __rcu *ifalias;
/*
* I/O specific fields
@@ -1887,6 +1962,7 @@
unsigned short type;
unsigned short hard_header_len;
unsigned char min_header_len;
+ unsigned char name_assign_type;
unsigned short needed_headroom;
unsigned short needed_tailroom;
@@ -1897,12 +1973,12 @@
unsigned char addr_len;
unsigned char upper_level;
unsigned char lower_level;
+
unsigned short neigh_priv_len;
unsigned short dev_id;
unsigned short dev_port;
spinlock_t addr_list_lock;
- unsigned char name_assign_type;
- bool uc_promisc;
+
struct netdev_hw_addr_list uc;
struct netdev_hw_addr_list mc;
struct netdev_hw_addr_list dev_addrs;
@@ -1910,8 +1986,15 @@
#ifdef CONFIG_SYSFS
struct kset *queues_kset;
#endif
+#ifdef CONFIG_LOCKDEP
+ struct list_head unlink_list;
+#endif
unsigned int promiscuity;
unsigned int allmulti;
+ bool uc_promisc;
+#ifdef CONFIG_LOCKDEP
+ unsigned char nested_level;
+#endif
/* Protocol-specific pointers */
@@ -1954,6 +2037,7 @@
struct bpf_prog __rcu *xdp_prog;
unsigned long gro_flush_timeout;
+ int napi_defer_hard_irqs;
rx_handler_func_t __rcu *rx_handler;
void __rcu *rx_handler_data;
@@ -1977,13 +2061,11 @@
struct netdev_queue *_tx ____cacheline_aligned_in_smp;
unsigned int num_tx_queues;
unsigned int real_num_tx_queues;
- struct Qdisc *qdisc;
-#ifdef CONFIG_NET_SCHED
- DECLARE_HASHTABLE (qdisc_hash, 4);
-#endif
+ struct Qdisc __rcu *qdisc;
unsigned int tx_queue_len;
spinlock_t tx_global_lock;
- int watchdog_timeo;
+
+ struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
#ifdef CONFIG_XPS
struct xps_dev_maps __rcu *xps_cpus_map;
@@ -1993,11 +2075,17 @@
struct mini_Qdisc __rcu *miniq_egress;
#endif
+#ifdef CONFIG_NET_SCHED
+ DECLARE_HASHTABLE (qdisc_hash, 4);
+#endif
/* These may be needed for future network-power-down code. */
struct timer_list watchdog_timer;
+ int watchdog_timeo;
- int __percpu *pcpu_refcnt;
+ u32 proto_down_reason;
+
struct list_head todo_list;
+ int __percpu *pcpu_refcnt;
struct list_head link_watch_list;
@@ -2069,12 +2157,22 @@
#endif
struct phy_device *phydev;
struct sfp_bus *sfp_bus;
- struct lock_class_key qdisc_tx_busylock_key;
- struct lock_class_key qdisc_running_key;
- struct lock_class_key qdisc_xmit_lock_key;
- struct lock_class_key addr_list_lock_key;
+ struct lock_class_key *qdisc_tx_busylock;
+ struct lock_class_key *qdisc_running_key;
bool proto_down;
unsigned wol_enabled:1;
+
+ struct list_head net_notifier_list;
+
+#if IS_ENABLED(CONFIG_MACSEC)
+ /* MACsec management functions */
+ const struct macsec_ops *macsec_ops;
+#endif
+ const struct udp_tunnel_nic_info *udp_tunnel_nic_info;
+ struct udp_tunnel_nic *udp_tunnel_nic;
+
+ /* protected by rtnl_lock */
+ struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE];
};
#define to_net_dev(d) container_of(d, struct net_device, dev)
@@ -2114,6 +2212,22 @@
return dev->num_tc;
}
+static inline void net_prefetch(void *p)
+{
+ prefetch(p);
+#if L1_CACHE_BYTES < 128
+ prefetch((u8 *)p + L1_CACHE_BYTES);
+#endif
+}
+
+static inline void net_prefetchw(void *p)
+{
+ prefetchw(p);
+#if L1_CACHE_BYTES < 128
+ prefetchw((u8 *)p + L1_CACHE_BYTES);
+#endif
+}
+
void netdev_unbind_sb_channel(struct net_device *dev,
struct net_device *sb_dev);
int netdev_bind_sb_channel_queue(struct net_device *dev,
@@ -2150,6 +2264,23 @@
f(dev, &dev->_tx[i], arg);
}
+#define netdev_lockdep_set_classes(dev) \
+{ \
+ static struct lock_class_key qdisc_tx_busylock_key; \
+ static struct lock_class_key qdisc_running_key; \
+ static struct lock_class_key qdisc_xmit_lock_key; \
+ static struct lock_class_key dev_addr_list_lock_key; \
+ unsigned int i; \
+ \
+ (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \
+ (dev)->qdisc_running_key = &qdisc_running_key; \
+ lockdep_set_class(&(dev)->addr_list_lock, \
+ &dev_addr_list_lock_key); \
+ for (i = 0; i < (dev)->num_tx_queues; i++) \
+ lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \
+ &qdisc_xmit_lock_key); \
+}
+
u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev);
struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
@@ -2275,12 +2406,26 @@
}
/**
+ * __netif_napi_del - remove a NAPI context
+ * @napi: NAPI context
+ *
+ * Warning: caller must observe RCU grace period before freeing memory
+ * containing @napi. Drivers might want to call this helper to combine
+ * all the needed RCU grace periods into a single one.
+ */
+void __netif_napi_del(struct napi_struct *napi);
+
+/**
* netif_napi_del - remove a NAPI context
* @napi: NAPI context
*
* netif_napi_del() removes a NAPI context from the network device NAPI list
*/
-void netif_napi_del(struct napi_struct *napi);
+static inline void netif_napi_del(struct napi_struct *napi)
+{
+ __netif_napi_del(napi);
+ synchronize_net();
+}
struct napi_gro_cb {
/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
@@ -2339,7 +2484,8 @@
/* Number of gro_receive callbacks this packet already went through */
u8 recursion_counter:4;
- /* 1 bit hole */
+ /* GRO is done by frag_list pointer chaining. */
+ u8 is_flist:1;
/* used to support CHECKSUM_COMPLETE for tunneling protocols */
__wsum csum;
@@ -2397,6 +2543,7 @@
struct net_device *);
bool (*id_match)(struct packet_type *ptype,
struct sock *sk);
+ struct net *af_packet_net;
void *af_packet_priv;
struct list_head list;
};
@@ -2426,11 +2573,33 @@
} __aligned(4 * sizeof(u64));
struct pcpu_lstats {
- u64 packets;
- u64 bytes;
+ u64_stats_t packets;
+ u64_stats_t bytes;
struct u64_stats_sync syncp;
} __aligned(2 * sizeof(u64));
+void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes);
+
+static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int len)
+{
+ struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->rx_bytes += len;
+ tstats->rx_packets++;
+ u64_stats_update_end(&tstats->syncp);
+}
+
+static inline void dev_lstats_add(struct net_device *dev, unsigned int len)
+{
+ struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats);
+
+ u64_stats_update_begin(&lstats->syncp);
+ u64_stats_add(&lstats->bytes, len);
+ u64_stats_inc(&lstats->packets);
+ u64_stats_update_end(&lstats->syncp);
+}
+
#define __netdev_alloc_pcpu_stats(type, gfp) \
({ \
typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\
@@ -2526,6 +2695,15 @@
int register_netdevice_notifier(struct notifier_block *nb);
int unregister_netdevice_notifier(struct notifier_block *nb);
+int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb);
+int unregister_netdevice_notifier_net(struct net *net,
+ struct notifier_block *nb);
+int register_netdevice_notifier_dev_net(struct net_device *dev,
+ struct notifier_block *nb,
+ struct netdev_net_notifier *nn);
+int unregister_netdevice_notifier_dev_net(struct net_device *dev,
+ struct notifier_block *nb,
+ struct netdev_net_notifier *nn);
struct netdev_notifier_info {
struct net_device *dev;
@@ -2596,6 +2774,9 @@
list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list)
#define for_each_netdev_continue(net, d) \
list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list)
+#define for_each_netdev_continue_reverse(net, d) \
+ list_for_each_entry_continue_reverse(d, &(net)->dev_base_head, \
+ dev_list)
#define for_each_netdev_continue_rcu(net, d) \
list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
#define for_each_netdev_in_bond_rcu(bond, slave) \
@@ -2665,9 +2846,21 @@
struct net_device *sb_dev);
u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev);
+
int dev_queue_xmit(struct sk_buff *skb);
int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
-int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
+int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
+
+static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+{
+ int ret;
+
+ ret = __dev_direct_xmit(skb, queue_id);
+ if (!dev_xmit_complete(ret))
+ kfree_skb(skb);
+ return ret;
+}
+
int register_netdevice(struct net_device *dev);
void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
void unregister_netdevice_many(struct list_head *head);
@@ -2679,9 +2872,11 @@
int netdev_refcnt_read(const struct net_device *dev);
void free_netdev(struct net_device *dev);
void netdev_freemem(struct net_device *dev);
-void synchronize_net(void);
int init_dummy_netdev(struct net_device *dev);
+struct net_device *netdev_get_xmit_slave(struct net_device *dev,
+ struct sk_buff *skb,
+ bool all_slaves);
struct net_device *dev_get_by_index(struct net *net, int ifindex);
struct net_device *__dev_get_by_index(struct net *net, int ifindex);
struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
@@ -2689,6 +2884,7 @@
int netdev_get_name(struct net *net, char *name, int ifindex);
int dev_restart(struct net_device *dev);
int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb);
+int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb);
static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
{
@@ -2825,16 +3021,16 @@
}
static inline void __skb_gro_checksum_convert(struct sk_buff *skb,
- __sum16 check, __wsum pseudo)
+ __wsum pseudo)
{
NAPI_GRO_CB(skb)->csum = ~pseudo;
NAPI_GRO_CB(skb)->csum_valid = 1;
}
-#define skb_gro_checksum_try_convert(skb, proto, check, compute_pseudo) \
+#define skb_gro_checksum_try_convert(skb, proto, compute_pseudo) \
do { \
if (__skb_gro_checksum_convert_check(skb)) \
- __skb_gro_checksum_convert(skb, check, \
+ __skb_gro_checksum_convert(skb, \
compute_pseudo(skb, proto)); \
} while (0)
@@ -2986,6 +3182,11 @@
return false;
}
+static inline bool dev_has_header(const struct net_device *dev)
+{
+ return dev->header_ops && dev->header_ops->create;
+}
+
typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr,
int len, int size);
int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
@@ -3171,7 +3372,6 @@
}
void netif_tx_stop_all_queues(struct net_device *dev);
-void netdev_update_lockdep_key(struct net_device *dev);
static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
{
@@ -3524,7 +3724,7 @@
}
/**
- * netif_attrmask_next_and - get the next CPU/Rx queue in *src1p & *src2p
+ * netif_attrmask_next_and - get the next CPU/Rx queue in \*src1p & \*src2p
* @n: CPU/Rx queue index
* @src1p: the first CPUs/Rx queues mask pointer
* @src2p: the second CPUs/Rx queues mask pointer
@@ -3661,6 +3861,7 @@
int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
int netif_rx(struct sk_buff *skb);
int netif_rx_ni(struct sk_buff *skb);
+int netif_rx_any_context(struct sk_buff *skb);
int netif_receive_skb(struct sk_buff *skb);
int netif_receive_skb_core(struct sk_buff *skb);
void netif_receive_skb_list(struct list_head *head);
@@ -3728,15 +3929,18 @@
bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
int dev_change_proto_down(struct net_device *dev, bool proto_down);
int dev_change_proto_down_generic(struct net_device *dev, bool proto_down);
+void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask,
+ u32 value);
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again);
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, int *ret);
typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
- int fd, u32 flags);
-u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
- enum bpf_netdev_command cmd);
+ int fd, int expected_fd, u32 flags);
+int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
+
int xdp_umem_query(struct net_device *dev, u16 queue_id);
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
@@ -3865,6 +4069,46 @@
/**
+ * netif_testing_on - mark device as under test.
+ * @dev: network device
+ *
+ * Mark device as under test (as per RFC2863).
+ *
+ * The testing state indicates that some test(s) must be performed on
+ * the interface. After completion, of the test, the interface state
+ * will change to up, dormant, or down, as appropriate.
+ */
+static inline void netif_testing_on(struct net_device *dev)
+{
+ if (!test_and_set_bit(__LINK_STATE_TESTING, &dev->state))
+ linkwatch_fire_event(dev);
+}
+
+/**
+ * netif_testing_off - set device as not under test.
+ * @dev: network device
+ *
+ * Device is not in testing state.
+ */
+static inline void netif_testing_off(struct net_device *dev)
+{
+ if (test_and_clear_bit(__LINK_STATE_TESTING, &dev->state))
+ linkwatch_fire_event(dev);
+}
+
+/**
+ * netif_testing - test if device is under test
+ * @dev: network device
+ *
+ * Check if device is under test
+ */
+static inline bool netif_testing(const struct net_device *dev)
+{
+ return test_bit(__LINK_STATE_TESTING, &dev->state);
+}
+
+
+/**
* netif_oper_up - test if device is operational
* @dev: network device
*
@@ -3896,22 +4140,48 @@
*/
enum {
- NETIF_MSG_DRV = 0x0001,
- NETIF_MSG_PROBE = 0x0002,
- NETIF_MSG_LINK = 0x0004,
- NETIF_MSG_TIMER = 0x0008,
- NETIF_MSG_IFDOWN = 0x0010,
- NETIF_MSG_IFUP = 0x0020,
- NETIF_MSG_RX_ERR = 0x0040,
- NETIF_MSG_TX_ERR = 0x0080,
- NETIF_MSG_TX_QUEUED = 0x0100,
- NETIF_MSG_INTR = 0x0200,
- NETIF_MSG_TX_DONE = 0x0400,
- NETIF_MSG_RX_STATUS = 0x0800,
- NETIF_MSG_PKTDATA = 0x1000,
- NETIF_MSG_HW = 0x2000,
- NETIF_MSG_WOL = 0x4000,
+ NETIF_MSG_DRV_BIT,
+ NETIF_MSG_PROBE_BIT,
+ NETIF_MSG_LINK_BIT,
+ NETIF_MSG_TIMER_BIT,
+ NETIF_MSG_IFDOWN_BIT,
+ NETIF_MSG_IFUP_BIT,
+ NETIF_MSG_RX_ERR_BIT,
+ NETIF_MSG_TX_ERR_BIT,
+ NETIF_MSG_TX_QUEUED_BIT,
+ NETIF_MSG_INTR_BIT,
+ NETIF_MSG_TX_DONE_BIT,
+ NETIF_MSG_RX_STATUS_BIT,
+ NETIF_MSG_PKTDATA_BIT,
+ NETIF_MSG_HW_BIT,
+ NETIF_MSG_WOL_BIT,
+
+ /* When you add a new bit above, update netif_msg_class_names array
+ * in net/ethtool/common.c
+ */
+ NETIF_MSG_CLASS_COUNT,
};
+/* Both ethtool_ops interface and internal driver implementation use u32 */
+static_assert(NETIF_MSG_CLASS_COUNT <= 32);
+
+#define __NETIF_MSG_BIT(bit) ((u32)1 << (bit))
+#define __NETIF_MSG(name) __NETIF_MSG_BIT(NETIF_MSG_ ## name ## _BIT)
+
+#define NETIF_MSG_DRV __NETIF_MSG(DRV)
+#define NETIF_MSG_PROBE __NETIF_MSG(PROBE)
+#define NETIF_MSG_LINK __NETIF_MSG(LINK)
+#define NETIF_MSG_TIMER __NETIF_MSG(TIMER)
+#define NETIF_MSG_IFDOWN __NETIF_MSG(IFDOWN)
+#define NETIF_MSG_IFUP __NETIF_MSG(IFUP)
+#define NETIF_MSG_RX_ERR __NETIF_MSG(RX_ERR)
+#define NETIF_MSG_TX_ERR __NETIF_MSG(TX_ERR)
+#define NETIF_MSG_TX_QUEUED __NETIF_MSG(TX_QUEUED)
+#define NETIF_MSG_INTR __NETIF_MSG(INTR)
+#define NETIF_MSG_TX_DONE __NETIF_MSG(TX_DONE)
+#define NETIF_MSG_RX_STATUS __NETIF_MSG(RX_STATUS)
+#define NETIF_MSG_PKTDATA __NETIF_MSG(PKTDATA)
+#define NETIF_MSG_HW __NETIF_MSG(HW)
+#define NETIF_MSG_WOL __NETIF_MSG(WOL)
#define netif_msg_drv(p) ((p)->msg_enable & NETIF_MSG_DRV)
#define netif_msg_probe(p) ((p)->msg_enable & NETIF_MSG_PROBE)
@@ -3943,7 +4213,8 @@
static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
{
spin_lock(&txq->_xmit_lock);
- txq->xmit_lock_owner = cpu;
+ /* Pairs with READ_ONCE() in __dev_queue_xmit() */
+ WRITE_ONCE(txq->xmit_lock_owner, cpu);
}
static inline bool __netif_tx_acquire(struct netdev_queue *txq)
@@ -3960,26 +4231,32 @@
static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
{
spin_lock_bh(&txq->_xmit_lock);
- txq->xmit_lock_owner = smp_processor_id();
+ /* Pairs with READ_ONCE() in __dev_queue_xmit() */
+ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
}
static inline bool __netif_tx_trylock(struct netdev_queue *txq)
{
bool ok = spin_trylock(&txq->_xmit_lock);
- if (likely(ok))
- txq->xmit_lock_owner = smp_processor_id();
+
+ if (likely(ok)) {
+ /* Pairs with READ_ONCE() in __dev_queue_xmit() */
+ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
+ }
return ok;
}
static inline void __netif_tx_unlock(struct netdev_queue *txq)
{
- txq->xmit_lock_owner = -1;
+ /* Pairs with READ_ONCE() in __dev_queue_xmit() */
+ WRITE_ONCE(txq->xmit_lock_owner, -1);
spin_unlock(&txq->_xmit_lock);
}
static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
{
- txq->xmit_lock_owner = -1;
+ /* Pairs with READ_ONCE() in __dev_queue_xmit() */
+ WRITE_ONCE(txq->xmit_lock_owner, -1);
spin_unlock_bh(&txq->_xmit_lock);
}
@@ -4097,12 +4374,23 @@
static inline void netif_addr_lock(struct net_device *dev)
{
- spin_lock(&dev->addr_list_lock);
+ unsigned char nest_level = 0;
+
+#ifdef CONFIG_LOCKDEP
+ nest_level = dev->nested_level;
+#endif
+ spin_lock_nested(&dev->addr_list_lock, nest_level);
}
static inline void netif_addr_lock_bh(struct net_device *dev)
{
- spin_lock_bh(&dev->addr_list_lock);
+ unsigned char nest_level = 0;
+
+#ifdef CONFIG_LOCKDEP
+ nest_level = dev->nested_level;
+#endif
+ local_bh_disable();
+ spin_lock_nested(&dev->addr_list_lock, nest_level);
}
static inline void netif_addr_unlock(struct net_device *dev)
@@ -4131,9 +4419,6 @@
unsigned char name_assign_type,
void (*setup)(struct net_device *),
unsigned int txqs, unsigned int rxqs);
-int dev_get_valid_name(struct net *net, struct net_device *dev,
- const char *name);
-
#define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \
alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1)
@@ -4144,6 +4429,8 @@
int register_netdev(struct net_device *dev);
void unregister_netdev(struct net_device *dev);
+int devm_register_netdev(struct device *dev, struct net_device *ndev);
+
/* General hardware address lists handling functions */
int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
struct netdev_hw_addr_list *from_list, int addr_len);
@@ -4278,6 +4565,8 @@
struct rtnl_link_stats64 *storage);
void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
const struct net_device_stats *netdev_stats);
+void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
+ const struct pcpu_sw_netstats __percpu *netstats);
extern int netdev_max_backlog;
extern int netdev_tstamp_prequeue;
@@ -4288,12 +4577,38 @@
extern int dev_tx_weight;
extern int gro_normal_batch;
+enum {
+ NESTED_SYNC_IMM_BIT,
+ NESTED_SYNC_TODO_BIT,
+};
+
+#define __NESTED_SYNC_BIT(bit) ((u32)1 << (bit))
+#define __NESTED_SYNC(name) __NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT)
+
+#define NESTED_SYNC_IMM __NESTED_SYNC(IMM)
+#define NESTED_SYNC_TODO __NESTED_SYNC(TODO)
+
+struct netdev_nested_priv {
+ unsigned char flags;
+ void *data;
+};
+
bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
struct list_head **iter);
struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
struct list_head **iter);
+#ifdef CONFIG_LOCKDEP
+static LIST_HEAD(net_unlink_list);
+
+static inline void net_unlink_todo(struct net_device *dev)
+{
+ if (list_empty(&dev->unlink_list))
+ list_add_tail(&dev->unlink_list, &net_unlink_list);
+}
+#endif
+
/* iterate through upper list, must be called under RCU read lock */
#define netdev_for_each_upper_dev_rcu(dev, updev, iter) \
for (iter = &(dev)->adj_list.upper, \
@@ -4303,8 +4618,8 @@
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *upper_dev,
- void *data),
- void *data);
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv);
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev);
@@ -4341,12 +4656,12 @@
struct list_head **iter);
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
- void *data),
- void *data);
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv);
int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
- void *data),
- void *data);
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv);
void *netdev_adjacent_get_private(struct list_head *adj_list);
void *netdev_lower_get_first_private_rcu(struct net_device *dev);
@@ -4404,6 +4719,15 @@
void netdev_bonding_info_change(struct net_device *dev,
struct netdev_bonding_info *bonding_info);
+#if IS_ENABLED(CONFIG_ETHTOOL_NETLINK)
+void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data);
+#else
+static inline void ethtool_notify(struct net_device *dev, unsigned int cmd,
+ const void *data)
+{
+}
+#endif
+
static inline
struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features)
{
@@ -4483,16 +4807,6 @@
void netdev_class_remove_file_ns(const struct class_attribute *class_attr,
const void *ns);
-static inline int netdev_class_create_file(const struct class_attribute *class_attr)
-{
- return netdev_class_create_file_ns(class_attr, NULL);
-}
-
-static inline void netdev_class_remove_file(const struct class_attribute *class_attr)
-{
- netdev_class_remove_file_ns(class_attr, NULL);
-}
-
extern const struct kobj_ns_type_operations net_ns_type_operations;
const char *netdev_drivername(const struct net_device *dev);
@@ -4565,6 +4879,7 @@
BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT));
+ BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT));
return (features & feature) == feature;
}
@@ -4667,6 +4982,11 @@
return dev->priv_flags & IFF_OVS_DATAPATH;
}
+static inline bool netif_is_any_bridge_port(const struct net_device *dev)
+{
+ return netif_is_bridge_port(dev) || netif_is_ovs_port(dev);
+}
+
static inline bool netif_is_team_master(const struct net_device *dev)
{
return dev->priv_flags & IFF_TEAM;
@@ -4794,7 +5114,8 @@
#define MODULE_ALIAS_NETDEV(device) \
MODULE_ALIAS("netdev-" device)
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
#define netdev_dbg(__dev, format, args...) \
do { \
dynamic_netdev_dbg(__dev, format, ##args); \
@@ -4864,7 +5185,8 @@
#define netif_info(priv, type, dev, fmt, args...) \
netif_level(info, priv, type, dev, fmt, ##args)
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
#define netif_dbg(priv, type, netdev, format, args...) \
do { \
if (netif_msg_##type(priv)) \