diff options
Diffstat (limited to 'include/linux/netdevice.h')
| -rw-r--r-- | include/linux/netdevice.h | 3465 |
1 files changed, 2124 insertions, 1341 deletions
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e675ef97a426..5870a9e514a5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket @@ -15,11 +16,6 @@ * Bjorn Ekwall. <bj0rn@blox.se> * Pekka Riikonen <priikone@poseidon.pspt.fi> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Moved to /usr/include/linux for NET3 */ #ifndef _LINUX_NETDEVICE_H @@ -32,32 +28,44 @@ #include <linux/prefetch.h> #include <asm/cache.h> #include <asm/byteorder.h> +#include <asm/local.h> #include <linux/percpu.h> #include <linux/rculist.h> #include <linux/workqueue.h> #include <linux/dynamic_queue_limits.h> -#include <linux/ethtool.h> #include <net/net_namespace.h> #ifdef CONFIG_DCB #include <net/dcbnl.h> #endif #include <net/netprio_cgroup.h> -#include <net/xdp.h> - #include <linux/netdev_features.h> #include <linux/neighbour.h> +#include <linux/netdevice_xmit.h> #include <uapi/linux/netdevice.h> #include <uapi/linux/if_bonding.h> #include <uapi/linux/pkt_cls.h> +#include <uapi/linux/netdev.h> #include <linux/hashtable.h> +#include <linux/rbtree.h> +#include <net/net_trackers.h> +#include <net/net_debug.h> +#include <net/dropreason-core.h> +#include <net/neighbour_tables.h> struct netpoll_info; struct device; +struct ethtool_ops; +struct kernel_hwtstamp_config; struct phy_device; struct dsa_port; - +struct ip_tunnel_parm_kern; +struct macsec_context; +struct macsec_ops; +struct netdev_config; +struct netdev_name_node; +struct sd_flow_limit; struct sfp_bus; /* 802.11 specific */ struct wireless_dev; @@ -66,16 +74,30 @@ struct wpan_dev; 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; +struct xdp_frame; +struct xdp_metadata_ops; +struct xdp_md; +struct ethtool_netdev_state; +struct phy_link_topology; +struct hwtstamp_provider; + +typedef u32 xdp_features_t; +void synchronize_net(void); void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); +void netdev_sw_irq_coalesce_default_on(struct net_device *dev); /* Backlog congestion levels */ #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ +#define MAX_NEST_DEV 8 + /* * Transmit return codes: transmit return codes originate from three different * namespaces: @@ -162,55 +184,65 @@ static inline bool dev_xmit_complete(int rc) * (unsigned long) so they can be read and written atomically. */ +#define NET_DEV_STAT(FIELD) \ + union { \ + unsigned long FIELD; \ + atomic_long_t __##FIELD; \ + } + struct net_device_stats { - unsigned long rx_packets; - unsigned long tx_packets; - unsigned long rx_bytes; - unsigned long tx_bytes; - unsigned long rx_errors; - unsigned long tx_errors; - unsigned long rx_dropped; - unsigned long tx_dropped; - unsigned long multicast; - unsigned long collisions; - unsigned long rx_length_errors; - unsigned long rx_over_errors; - unsigned long rx_crc_errors; - unsigned long rx_frame_errors; - unsigned long rx_fifo_errors; - unsigned long rx_missed_errors; - unsigned long tx_aborted_errors; - unsigned long tx_carrier_errors; - unsigned long tx_fifo_errors; - unsigned long tx_heartbeat_errors; - unsigned long tx_window_errors; - unsigned long rx_compressed; - unsigned long tx_compressed; + NET_DEV_STAT(rx_packets); + NET_DEV_STAT(tx_packets); + NET_DEV_STAT(rx_bytes); + NET_DEV_STAT(tx_bytes); + NET_DEV_STAT(rx_errors); + NET_DEV_STAT(tx_errors); + NET_DEV_STAT(rx_dropped); + NET_DEV_STAT(tx_dropped); + NET_DEV_STAT(multicast); + NET_DEV_STAT(collisions); + NET_DEV_STAT(rx_length_errors); + NET_DEV_STAT(rx_over_errors); + NET_DEV_STAT(rx_crc_errors); + NET_DEV_STAT(rx_frame_errors); + NET_DEV_STAT(rx_fifo_errors); + NET_DEV_STAT(rx_missed_errors); + NET_DEV_STAT(tx_aborted_errors); + NET_DEV_STAT(tx_carrier_errors); + NET_DEV_STAT(tx_fifo_errors); + NET_DEV_STAT(tx_heartbeat_errors); + NET_DEV_STAT(tx_window_errors); + NET_DEV_STAT(rx_compressed); + NET_DEV_STAT(tx_compressed); }; +#undef NET_DEV_STAT +/* per-cpu stats, allocated on demand. + * Try to fit them in a single cache line, for dev_get_stats() sake. + */ +struct net_device_core_stats { + unsigned long rx_dropped; + unsigned long tx_dropped; + unsigned long rx_nohandler; + unsigned long rx_otherhost_dropped; +} __aligned(4 * sizeof(unsigned long)); #include <linux/cache.h> #include <linux/skbuff.h> -#ifdef CONFIG_RPS -#include <linux/static_key.h> -extern struct static_key rps_needed; -extern struct static_key rfs_needed; -#endif - struct neighbour; struct neigh_parms; struct sk_buff; struct netdev_hw_addr { struct list_head list; + struct rb_node node; unsigned char addr[MAX_ADDR_LEN]; 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; @@ -221,6 +253,9 @@ struct netdev_hw_addr { struct netdev_hw_addr_list { struct list_head list; int count; + + /* Auxiliary tree for faster lookup on addition and deletion */ + struct rb_root tree; }; #define netdev_hw_addr_list_count(l) ((l)->count) @@ -232,11 +267,17 @@ struct netdev_hw_addr_list { #define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc) #define netdev_for_each_uc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->uc) +#define netdev_for_each_synced_uc_addr(_ha, _dev) \ + netdev_for_each_uc_addr((_ha), (_dev)) \ + if ((_ha)->sync_cnt) #define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc) #define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc) #define netdev_for_each_mc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->mc) +#define netdev_for_each_synced_mc_addr(_ha, _dev) \ + netdev_for_each_mc_addr((_ha), (_dev)) \ + if ((_ha)->sync_cnt) struct hh_cache { unsigned int hh_len; @@ -260,9 +301,11 @@ struct hh_cache { * relationship HH alignment <= LL alignment. */ #define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ - ((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, @@ -274,6 +317,7 @@ struct header_ops { const struct net_device *dev, const unsigned char *haddr); bool (*validate)(const char *ll_header, unsigned int len); + __be16 (*parse_protocol)(const struct sk_buff *skb); }; /* These flag bits are private to the generic network queueing @@ -287,36 +331,54 @@ enum netdev_state_t { __LINK_STATE_NOCARRIER, __LINK_STATE_LINKWATCH_PENDING, __LINK_STATE_DORMANT, + __LINK_STATE_TESTING, }; - -/* - * This structure holds boot-time configured netdevice settings. They - * are then used in the device probing. - */ -struct netdev_boot_setup { - char name[IFNAMSIZ]; - struct ifmap map; -}; -#define NETDEV_BOOT_SETUP_MAX 8 - -int __init netdev_boot_setup(char *str); - struct gro_list { struct list_head list; int count; }; /* - * size of gro hash buckets, must less than bit number of - * napi_struct::gro_bitmask + * size of gro hash buckets, must be <= the number of bits in + * gro_node::bitmask */ #define GRO_HASH_BUCKETS 8 +/** + * struct gro_node - structure to support Generic Receive Offload + * @bitmask: bitmask to indicate used buckets in @hash + * @hash: hashtable of pending aggregated skbs, separated by flows + * @rx_list: list of pending ``GRO_NORMAL`` skbs + * @rx_count: cached current length of @rx_list + * @cached_napi_id: napi_struct::napi_id cached for hotpath, 0 for standalone + */ +struct gro_node { + unsigned long bitmask; + struct gro_list hash[GRO_HASH_BUCKETS]; + struct list_head rx_list; + u32 rx_count; + u32 cached_napi_id; +}; + +/* + * Structure for per-NAPI config + */ +struct napi_config { + u64 gro_flush_timeout; + u64 irq_suspend_timeout; + u32 defer_hard_irqs; + cpumask_t affinity_mask; + u8 threaded; + unsigned int napi_id; +}; + /* * Structure for NAPI scheduling similar to tasklet but with weighting */ struct napi_struct { + /* This field should be first or softnet_data.backlog needs tweaks. */ + unsigned long state; /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means * whoever atomically sets that bit can add this napi_struct @@ -325,40 +387,63 @@ struct napi_struct { */ struct list_head poll_list; - unsigned long state; int weight; - unsigned long gro_bitmask; + u32 defer_hard_irqs_count; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL + /* CPU actively polling if netpoll is configured */ int poll_owner; #endif + /* CPU on which NAPI has been scheduled for processing */ + int list_owner; struct net_device *dev; - struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; + struct gro_node gro; struct hrtimer timer; + /* all fields past this point are write-protected by netdev_lock */ + struct task_struct *thread; + unsigned long gro_flush_timeout; + unsigned long irq_suspend_timeout; + u32 defer_hard_irqs; + /* control-path-only fields follow */ + u32 napi_id; struct list_head dev_list; struct hlist_node napi_hash_node; - unsigned int napi_id; + int irq; + struct irq_affinity_notify notify; + int napi_rmap_idx; + int index; + struct napi_config *config; }; enum { - NAPI_STATE_SCHED, /* Poll is scheduled */ - 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_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */ - NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */ + NAPI_STATE_SCHED, /* Poll is scheduled */ + NAPI_STATE_MISSED, /* reschedule a napi */ + NAPI_STATE_DISABLE, /* Disable pending */ + NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ + 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, /* Do not rearm NAPI interrupt */ + NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ + NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ + NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */ + NAPI_STATE_HAS_NOTIFIER, /* Napi has an IRQ notifier */ + NAPI_STATE_THREADED_BUSY_POLL, /* The threaded NAPI poller will busy poll */ }; enum { - NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), - 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_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), - NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), + NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), + NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), + NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), + NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), + 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), + NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), + NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), + NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED), + NAPIF_STATE_HAS_NOTIFIER = BIT(NAPI_STATE_HAS_NOTIFIER), + NAPIF_STATE_THREADED_BUSY_POLL = BIT(NAPI_STATE_THREADED_BUSY_POLL), }; enum gro_result { @@ -366,7 +451,6 @@ enum gro_result { GRO_MERGED_FREE, GRO_HELD, GRO_NORMAL, - GRO_DROP, GRO_CONSUMED, }; typedef enum gro_result gro_result_t; @@ -429,6 +513,34 @@ static inline bool napi_disable_pending(struct napi_struct *n) return test_bit(NAPI_STATE_DISABLE, &n->state); } +static inline bool napi_prefer_busy_poll(struct napi_struct *n) +{ + return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); +} + +/** + * napi_is_scheduled - test if NAPI is scheduled + * @n: NAPI context + * + * This check is "best-effort". With no locking implemented, + * a NAPI can be scheduled or terminate right after this check + * and produce not precise results. + * + * NAPI_STATE_SCHED is an internal state, napi_is_scheduled + * should not be used normally and napi_schedule should be + * used instead. + * + * Use only if the driver really needs to check if a NAPI + * is scheduled for example in the context of delayed timer + * that can be skipped if a NAPI is already scheduled. + * + * Return: True if NAPI is scheduled, False otherwise. + */ +static inline bool napi_is_scheduled(struct napi_struct *n) +{ + return test_bit(NAPI_STATE_SCHED, &n->state); +} + bool napi_schedule_prep(struct napi_struct *n); /** @@ -437,11 +549,18 @@ bool napi_schedule_prep(struct napi_struct *n); * * Schedule NAPI poll routine to be called if it is not already * running. + * Return: true if we schedule a NAPI or false if not. + * Refer to napi_schedule_prep() for additional reason on why + * a NAPI might not be scheduled. */ -static inline void napi_schedule(struct napi_struct *n) +static inline bool napi_schedule(struct napi_struct *n) { - if (napi_schedule_prep(n)) + if (napi_schedule_prep(n)) { __napi_schedule(n); + return true; + } + + return false; } /** @@ -456,67 +575,32 @@ static inline void napi_schedule_irqoff(struct napi_struct *n) __napi_schedule_irqoff(n); } -/* Try to reschedule poll. Called by dev->poll() after napi_complete(). */ -static inline bool napi_reschedule(struct napi_struct *napi) -{ - if (napi_schedule_prep(napi)) { - __napi_schedule(napi); - return true; - } - return false; -} - -bool napi_complete_done(struct napi_struct *n, int work_done); /** - * napi_complete - NAPI processing complete - * @n: NAPI context - * - * Mark NAPI processing as complete. - * Consider using napi_complete_done() instead. - * Return false if device should avoid rearming interrupts. + * napi_complete_done - NAPI processing complete + * @n: NAPI context + * @work_done: number of packets processed + * + * Mark NAPI processing as complete. Should only be called if poll budget + * has not been completely consumed. + * Prefer over napi_complete(). + * Return: false if device should avoid rearming interrupts. */ +bool napi_complete_done(struct napi_struct *n, int work_done); + static inline bool napi_complete(struct napi_struct *n) { return napi_complete_done(n, 0); } -/** - * 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); +void netif_threaded_enable(struct net_device *dev); +int dev_set_threaded(struct net_device *dev, + enum netdev_napi_threaded threaded); -/** - * napi_disable - prevent NAPI from scheduling - * @n: NAPI context - * - * Stop NAPI from being scheduled on this context. - * Waits till any outstanding processing completes. - */ void napi_disable(struct napi_struct *n); +void napi_disable_locked(struct napi_struct *n); -/** - * napi_enable - enable NAPI scheduling - * @n: NAPI context - * - * Resume NAPI from being scheduled on this context. - * Must be paired with napi_disable. - */ -static inline void napi_enable(struct napi_struct *n) -{ - BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); - smp_mb__before_atomic(); - clear_bit(NAPI_STATE_SCHED, &n->state); - clear_bit(NAPI_STATE_NPSVC, &n->state); -} +void napi_enable(struct napi_struct *n); +void napi_enable_locked(struct napi_struct *n); /** * napi_synchronize - wait until NAPI is not running @@ -547,8 +631,8 @@ static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) { unsigned long val, new; + val = READ_ONCE(n->state); do { - val = READ_ONCE(n->state); if (val & NAPIF_STATE_DISABLE) return true; @@ -556,7 +640,7 @@ static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) return false; new = val | NAPIF_STATE_MISSED; - } while (cmpxchg(&n->state, val, new) != val); + } while (!try_cmpxchg(&n->state, &val, new)); return true; } @@ -592,29 +676,34 @@ struct netdev_queue { * read-mostly part */ struct net_device *dev; + netdevice_tracker dev_tracker; + struct Qdisc __rcu *qdisc; - struct Qdisc *qdisc_sleeping; + struct Qdisc __rcu *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; -#endif -#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) - int numa_node; + const struct attribute_group **groups; #endif unsigned long tx_maxrate; /* * Number of TX timeouts for this queue * (/sys/class/net/DEV/Q/trans_timeout) */ - unsigned long trans_timeout; + atomic_long_t trans_timeout; /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; #ifdef CONFIG_XDP_SOCKETS - struct xdp_umem *umem; + /* "ops protected", see comment about net_device::lock */ + struct xsk_buff_pool *pool; #endif + /* * write-mostly part */ +#ifdef CONFIG_BQL + struct dql dql; +#endif spinlock_t _xmit_lock ____cacheline_aligned_in_smp; int xmit_lock_owner; /* @@ -624,19 +713,46 @@ struct netdev_queue { unsigned long state; -#ifdef CONFIG_BQL - struct dql dql; +/* + * slow- / control-path part + */ + /* NAPI instance for the queue + * "ops protected", see comment about net_device::lock + */ + struct napi_struct *napi; + +#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) + int numa_node; #endif } ____cacheline_aligned_in_smp; 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; +#if IS_ENABLED(CONFIG_SYSCTL) + int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net); + + return !fb_tunnels_only_for_init_net || + (net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1); +#else + return true; +#endif +} + +static inline int net_inherit_devconf(void) +{ +#if IS_ENABLED(CONFIG_SYSCTL) + return READ_ONCE(sysctl_devconf_inherit_init_net); +#else + return 0; +#endif } static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) @@ -655,106 +771,16 @@ static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node #endif } -#ifdef CONFIG_RPS -/* - * This structure holds an RPS map which can be of variable length. The - * map is an array of CPUs. - */ -struct rps_map { - unsigned int len; - struct rcu_head rcu; - u16 cpus[0]; -}; -#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) - -/* - * The rps_dev_flow structure contains the mapping of a flow to a CPU, the - * tail pointer for that CPU's input queue at the time of last enqueue, and - * a hardware filter index. - */ -struct rps_dev_flow { - u16 cpu; - u16 filter; - unsigned int last_qtail; -}; -#define RPS_NO_FILTER 0xffff - -/* - * The rps_dev_flow_table structure contains a table of flow mappings. - */ -struct rps_dev_flow_table { - unsigned int mask; - struct rcu_head rcu; - struct rps_dev_flow flows[0]; -}; -#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ - ((_num) * sizeof(struct rps_dev_flow))) - -/* - * The rps_sock_flow_table contains mappings of flows to the last CPU - * on which they were processed by the application (set in recvmsg). - * Each entry is a 32bit value. Upper part is the high-order bits - * of flow hash, lower part is CPU number. - * rps_cpu_mask is used to partition the space, depending on number of - * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 - * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, - * meaning we use 32-6=26 bits for the hash. - */ -struct rps_sock_flow_table { - u32 mask; - - u32 ents[0] ____cacheline_aligned_in_smp; -}; -#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) - -#define RPS_NO_CPU 0xffff - -extern u32 rps_cpu_mask; -extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; - -static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, - u32 hash) -{ - if (table && hash) { - unsigned int index = hash & table->mask; - u32 val = hash & ~rps_cpu_mask; - - /* We only give a hint, preemption can change CPU under us */ - val |= raw_smp_processor_id(); - - if (table->ents[index] != val) - table->ents[index] = val; - } -} - #ifdef CONFIG_RFS_ACCEL bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id); #endif -#endif /* CONFIG_RPS */ - -/* This structure contains an instance of an RX queue. */ -struct netdev_rx_queue { -#ifdef CONFIG_RPS - struct rps_map __rcu *rps_map; - struct rps_dev_flow_table __rcu *rps_flow_table; -#endif - struct kobject kobj; - struct net_device *dev; - struct xdp_rxq_info xdp_rxq; -#ifdef CONFIG_XDP_SOCKETS - struct xdp_umem *umem; -#endif -} ____cacheline_aligned_in_smp; -/* - * RX queue sysfs structures and functions. - */ -struct rx_queue_attribute { - struct attribute attr; - ssize_t (*show)(struct netdev_rx_queue *queue, char *buf); - ssize_t (*store)(struct netdev_rx_queue *queue, - const char *buf, size_t len); +/* XPS map type and offset of the xps map within net_device->xps_maps[]. */ +enum xps_map_type { + XPS_CPUS = 0, + XPS_RXQS, + XPS_MAPS_MAX, }; #ifdef CONFIG_XPS @@ -766,7 +792,7 @@ struct xps_map { 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])) \ @@ -774,10 +800,20 @@ struct xps_map { /* * This structure holds all XPS maps for device. Maps are indexed by CPU. + * + * We keep track of the number of cpus/rxqs used when the struct is allocated, + * in nr_ids. This will help not accessing out-of-bound memory. + * + * We keep track of the number of traffic classes used when the struct is + * allocated, in num_tc. This will be used to navigate the maps, to ensure we're + * not crossing its upper bound, as the original dev->num_tc can be updated in + * the meantime. */ struct xps_dev_maps { struct rcu_head rcu; - struct xps_map __rcu *attr_map[0]; /* Either CPUs map or RXQs map */ + unsigned int nr_ids; + s16 num_tc; + struct xps_map __rcu *attr_map[]; /* Either CPUs map or RXQs map */ }; #define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ @@ -834,7 +870,82 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); +enum net_device_path_type { + DEV_PATH_ETHERNET = 0, + DEV_PATH_VLAN, + DEV_PATH_BRIDGE, + DEV_PATH_PPPOE, + DEV_PATH_DSA, + DEV_PATH_MTK_WDMA, + DEV_PATH_TUN, +}; + +struct net_device_path { + enum net_device_path_type type; + const struct net_device *dev; + union { + struct { + u16 id; + __be16 proto; + u8 h_dest[ETH_ALEN]; + } encap; + struct { + union { + struct in_addr src_v4; + struct in6_addr src_v6; + }; + union { + struct in_addr dst_v4; + struct in6_addr dst_v6; + }; + + u8 l3_proto; + } tun; + struct { + enum { + DEV_PATH_BR_VLAN_KEEP, + DEV_PATH_BR_VLAN_TAG, + DEV_PATH_BR_VLAN_UNTAG, + DEV_PATH_BR_VLAN_UNTAG_HW, + } vlan_mode; + u16 vlan_id; + __be16 vlan_proto; + } bridge; + struct { + int port; + u16 proto; + } dsa; + struct { + u8 wdma_idx; + u8 queue; + u16 wcid; + u8 bss; + u8 amsdu; + } mtk_wdma; + }; +}; + +#define NET_DEVICE_PATH_STACK_MAX 5 +#define NET_DEVICE_PATH_VLAN_MAX 2 + +struct net_device_path_stack { + int num_paths; + struct net_device_path path[NET_DEVICE_PATH_STACK_MAX]; +}; + +struct net_device_path_ctx { + const struct net_device *dev; + u8 daddr[ETH_ALEN]; + + int num_vlans; + struct { + u16 id; + __be16 proto; + } vlan[NET_DEVICE_PATH_VLAN_MAX]; +}; + enum tc_setup_type { + TC_QUERY_CAPS, TC_SETUP_QDISC_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, @@ -848,6 +959,13 @@ enum tc_setup_type { TC_SETUP_QDISC_ETF, 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, + TC_SETUP_QDISC_HTB, + TC_SETUP_ACT, }; /* These structures hold the attributes of bpf state that are being passed @@ -863,18 +981,29 @@ enum bpf_netdev_command { */ 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_QUERY_XSK_UMEM, - 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; @@ -885,54 +1014,38 @@ struct netdev_bpf { 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_QUERY_XSK_UMEM, XDP_SETUP_XSK_UMEM */ + /* XDP_SETUP_XSK_POOL */ struct { - struct xdp_umem *umem; /* out for query*/ - u16 queue_id; /* in for query */ + struct xsk_buff_pool *pool; + u16 queue_id; } xsk; }; }; +/* Flags for ndo_xsk_wakeup. */ +#define XDP_WAKEUP_RX (1 << 0) +#define XDP_WAKEUP_TX (1 << 1) + #ifdef CONFIG_XFRM_OFFLOAD struct xfrmdev_ops { - int (*xdo_dev_state_add) (struct xfrm_state *x); - void (*xdo_dev_state_delete) (struct xfrm_state *x); - void (*xdo_dev_state_free) (struct xfrm_state *x); + int (*xdo_dev_state_add)(struct net_device *dev, + struct xfrm_state *x, + struct netlink_ext_ack *extack); + void (*xdo_dev_state_delete)(struct net_device *dev, + struct xfrm_state *x); + void (*xdo_dev_state_free)(struct net_device *dev, + struct xfrm_state *x); bool (*xdo_dev_offload_ok) (struct sk_buff *skb, struct xfrm_state *x); void (*xdo_dev_state_advance_esn) (struct xfrm_state *x); -}; -#endif - -#if IS_ENABLED(CONFIG_TLS_DEVICE) -enum tls_offload_ctx_dir { - TLS_OFFLOAD_CTX_DIR_RX, - TLS_OFFLOAD_CTX_DIR_TX, -}; - -struct tls_crypto_info; -struct tls_context; - -struct tlsdev_ops { - int (*tls_dev_add)(struct net_device *netdev, struct sock *sk, - enum tls_offload_ctx_dir direction, - struct tls_crypto_info *crypto_info, - u32 start_offload_tcp_sn); - void (*tls_dev_del)(struct net_device *netdev, - struct tls_context *ctx, - enum tls_offload_ctx_dir direction); - void (*tls_dev_resync_rx)(struct net_device *netdev, - struct sock *sk, u32 seq, u64 rcd_sn); + void (*xdo_dev_state_update_stats) (struct xfrm_state *x); + int (*xdo_dev_policy_add) (struct xfrm_policy *x, struct netlink_ext_ack *extack); + void (*xdo_dev_policy_delete) (struct xfrm_policy *x); + void (*xdo_dev_policy_free) (struct xfrm_policy *x); }; #endif @@ -941,6 +1054,14 @@ struct dev_ifalias { char ifalias[]; }; +struct devlink; +struct tlsdev_ops; + +struct netdev_net_notifier { + struct list_head list; + struct notifier_block *nb; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -984,8 +1105,7 @@ struct dev_ifalias { * those the driver believes to be appropriate. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - * struct net_device *sb_dev, - * select_queue_fallback_t fallback); + * struct net_device *sb_dev); * Called to decide which queue to use when device supports multiple * transmit queues. * @@ -1007,9 +1127,18 @@ struct dev_ifalias { * Test if Media Access Control address is valid for the device. * * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); - * Called when a user requests an ioctl which can't be handled by - * the generic interface code. If not defined ioctls return - * not supported error code. + * Old-style ioctl entry point. This is used internally by the + * ieee802154 subsystem but is no longer called by the device + * ioctl handler. + * + * int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd); + * Used by the bonding driver for its device specific ioctls: + * SIOCBONDENSLAVE, SIOCBONDRELEASE, SIOCBONDSETHWADDR, SIOCBONDCHANGEACTIVE, + * SIOCBONDSLAVEINFOQUERY, and SIOCBONDINFOQUERY + * + * * int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); + * Called for ethernet specific ioctls: SIOCGMIIPHY, SIOCGMIIREG, + * SIOCSMIIREG, SIOCSHWTSTAMP and SIOCGHWTSTAMP. * * int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); * Used to set network devices bus interface parameters. This interface @@ -1020,7 +1149,7 @@ struct dev_ifalias { * 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. * @@ -1139,6 +1268,12 @@ struct dev_ifalias { * 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); @@ -1154,18 +1289,39 @@ struct dev_ifalias { * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, u16 vid, u16 flags, - * struct netlink_ext_ack *extack); + * bool *notified, struct netlink_ext_ack *extack); * Adds an FDB entry to dev for addr. + * Callee shall set *notified to true if it sent any appropriate + * notification(s). Otherwise core will send a generic one. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, - * const unsigned char *addr, u16 vid) - * Deletes the FDB entry from dev coresponding to addr. + * const unsigned char *addr, u16 vid + * bool *notified, struct netlink_ext_ack *extack); + * Deletes the FDB entry from dev corresponding to addr. + * Callee shall set *notified to true if it sent any appropriate + * notification(s). Otherwise core will send a generic one. + * int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, + * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, struct net_device *filter_dev, * int *idx) * Used to add FDB entries to dump requests. Implementers should add * entries to skb and update idx with the number of entries. * + * int (*ndo_mdb_add)(struct net_device *dev, struct nlattr *tb[], + * u16 nlmsg_flags, struct netlink_ext_ack *extack); + * Adds an MDB entry to dev. + * int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[], + * struct netlink_ext_ack *extack); + * Deletes the MDB entry from dev. + * int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[], + * struct netlink_ext_ack *extack); + * Bulk deletes MDB entries from dev. + * int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, + * struct netlink_callback *cb); + * Dumps MDB entries from dev. The first argument (marker) in the netlink + * callback is used by core rtnetlink code. + * * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags, struct netlink_ext_ack *extack) * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, @@ -1188,18 +1344,9 @@ struct dev_ifalias { * not implement this, it is assumed that the hw is not able to have * multiple net devices on single physical port. * - * void (*ndo_udp_tunnel_add)(struct net_device *dev, - * struct udp_tunnel_info *ti); - * Called by UDP tunnel to notify a driver about the UDP port and socket - * address family that a UDP tunnel is listnening to. It is called only - * when a new port starts listening. The operation is protected by the - * RTNL. - * - * void (*ndo_udp_tunnel_del)(struct net_device *dev, - * struct udp_tunnel_info *ti); - * Called by UDP tunnel to notify the driver about a UDP port and socket - * address family that the UDP tunnel is not listening to anymore. The - * operation is protected by the RTNL. + * int (*ndo_get_port_parent_id)(struct net_device *dev, + * struct netdev_phys_item_id *ppid) + * Called to get the parent ID of the physical port of this device. * * void* (*ndo_dfwd_add_station)(struct net_device *pdev, * struct net_device *dev) @@ -1219,11 +1366,6 @@ struct dev_ifalias { * TX queue. * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. - * void (*ndo_change_proto_down)(struct net_device *dev, - * bool proto_down); - * This function is used to pass protocol port error state information - * to the switch driver. The switch driver can react to the proto_down - * by doing a phys down on the associated switch port. * int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); * This function is used to get egress tunnel information for given skb. * This is useful for retrieving outer tunnel header parameters while @@ -1245,6 +1387,39 @@ struct dev_ifalias { * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. + * struct net_device *(*ndo_xdp_get_xmit_slave)(struct net_device *dev, + * struct xdp_buff *xdp); + * Get the xmit slave of master device based on the xdp_buff. + * int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); + * This function is used to wake up the softirq, ksoftirqd or kthread + * responsible for sending and/or receiving packets on a specific + * queue id bound to an AF_XDP socket. The flags field specifies if + * only RX, only Tx, or both should be woken up using the flags + * XDP_WAKEUP_RX and XDP_WAKEUP_TX. + * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *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. + * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); + * Get the forwarding path to reach the real device from the HW destination address + * ktime_t (*ndo_get_tstamp)(struct net_device *dev, + * const struct skb_shared_hwtstamps *hwtstamps, + * bool cycles); + * Get hardware timestamp based on normal/adjustable time or free running + * cycle counter. This function is required if physical clock supports a + * free running cycle counter. + * + * int (*ndo_hwtstamp_get)(struct net_device *dev, + * struct kernel_hwtstamp_config *kernel_config); + * Get the currently configured hardware timestamping parameters for the + * NIC device. + * + * int (*ndo_hwtstamp_set)(struct net_device *dev, + * struct kernel_hwtstamp_config *kernel_config, + * struct netlink_ext_ack *extack); + * Change the hardware timestamping parameters for NIC device. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1258,8 +1433,7 @@ struct net_device_ops { netdev_features_t features); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); + struct net_device *sb_dev); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -1268,13 +1442,23 @@ struct net_device_ops { int (*ndo_validate_addr)(struct net_device *dev); int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); + int (*ndo_eth_ioctl)(struct net_device *dev, + struct ifreq *ifr, int cmd); + int (*ndo_siocbond)(struct net_device *dev, + struct ifreq *ifr, int cmd); + int (*ndo_siocwandev)(struct net_device *dev, + struct if_settings *ifs); + int (*ndo_siocdevprivate)(struct net_device *dev, + struct ifreq *ifr, + void __user *data, int cmd); int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); int (*ndo_change_mtu)(struct net_device *dev, 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); @@ -1290,8 +1474,7 @@ struct net_device_ops { __be16 proto, u16 vid); #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); - int (*ndo_netpoll_setup)(struct net_device *dev, - struct netpoll_info *info); + int (*ndo_netpoll_setup)(struct net_device *dev); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, @@ -1320,6 +1503,10 @@ struct net_device_ops { 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); @@ -1364,6 +1551,11 @@ struct net_device_ops { 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); + struct net_device* (*ndo_sk_get_lower_dev)(struct net_device *dev, + struct sock *sk); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, @@ -1379,12 +1571,18 @@ struct net_device_ops { const unsigned char *addr, u16 vid, u16 flags, + bool *notified, struct netlink_ext_ack *extack); int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, - u16 vid); + u16 vid, + bool *notified, + struct netlink_ext_ack *extack); + int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, + struct net_device *dev, + struct netlink_ext_ack *extack); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, @@ -1396,6 +1594,23 @@ struct net_device_ops { const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack); + int (*ndo_mdb_add)(struct net_device *dev, + struct nlattr *tb[], + u16 nlmsg_flags, + struct netlink_ext_ack *extack); + int (*ndo_mdb_del)(struct net_device *dev, + struct nlattr *tb[], + struct netlink_ext_ack *extack); + int (*ndo_mdb_del_bulk)(struct net_device *dev, + struct nlattr *tb[], + struct netlink_ext_ack *extack); + int (*ndo_mdb_dump)(struct net_device *dev, + struct sk_buff *skb, + struct netlink_callback *cb); + int (*ndo_mdb_get)(struct net_device *dev, + struct nlattr *tb[], u32 portid, + u32 seq, + struct netlink_ext_ack *extack); int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, @@ -1412,24 +1627,19 @@ struct net_device_ops { bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); + int (*ndo_get_port_parent_id)(struct net_device *dev, + struct netdev_phys_item_id *ppid); int (*ndo_get_phys_port_name)(struct net_device *dev, char *name, size_t len); - void (*ndo_udp_tunnel_add)(struct net_device *dev, - struct udp_tunnel_info *ti); - void (*ndo_udp_tunnel_del)(struct net_device *dev, - struct udp_tunnel_info *ti); void* (*ndo_dfwd_add_station)(struct net_device *pdev, struct net_device *dev); void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); - int (*ndo_get_lock_subclass)(struct net_device *dev); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, u32 maxrate); int (*ndo_get_iflink)(const struct net_device *dev); - int (*ndo_change_proto_down)(struct net_device *dev, - bool proto_down); int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); void (*ndo_set_rx_headroom)(struct net_device *dev, @@ -1439,19 +1649,44 @@ struct net_device_ops { int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, u32 flags); - int (*ndo_xsk_async_xmit)(struct net_device *dev, - u32 queue_id); + struct net_device * (*ndo_xdp_get_xmit_slave)(struct net_device *dev, + struct xdp_buff *xdp); + int (*ndo_xsk_wakeup)(struct net_device *dev, + u32 queue_id, u32 flags); + int (*ndo_tunnel_ctl)(struct net_device *dev, + struct ip_tunnel_parm_kern *p, + int cmd); + struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); + int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, + struct net_device_path *path); + ktime_t (*ndo_get_tstamp)(struct net_device *dev, + const struct skb_shared_hwtstamps *hwtstamps, + bool cycles); + int (*ndo_hwtstamp_get)(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_config); + int (*ndo_hwtstamp_set)(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_config, + struct netlink_ext_ack *extack); + +#if IS_ENABLED(CONFIG_NET_SHAPER) + /** + * @net_shaper_ops: Device shaping offload operations + * see include/net/net_shapers.h + */ + const struct net_shaper_ops *net_shaper_ops; +#endif }; /** - * enum net_device_priv_flags - &struct net_device priv_flags + * enum netdev_priv_flags - &struct net_device priv_flags * * These are the &struct net_device, they are only set internally * by drivers and used in the kernel. These flags are invisible to * userspace; this means that the order of these flags can change * during any kernel release. * - * You should have a pretty good reason to be extending these flags. + * You should add bitfield booleans after either net_device::priv_flags + * (hotpath) or ::threaded (slowpath) instead of extending these flags. * * @IFF_802_1Q_VLAN: 802.1Q VLAN device * @IFF_EBRIDGE: Ethernet bridging device @@ -1486,6 +1721,10 @@ struct net_device_ops { * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device + * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device + * @IFF_NO_ADDRCONF: prevent ipv6 addrconf + * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with + * skb_headlen(skb) == 0 (data starts from frag0) */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1517,36 +1756,32 @@ enum netdev_priv_flags { IFF_NO_RX_HANDLER = 1<<26, IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, + IFF_L3MDEV_RX_HANDLER = 1<<29, + IFF_NO_ADDRCONF = BIT_ULL(30), + IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), +}; + +/* Specifies the type of the struct net_device::ml_priv pointer */ +enum netdev_ml_priv_type { + ML_PRIV_NONE, + ML_PRIV_CAN, +}; + +enum netdev_stat_type { + NETDEV_PCPU_STAT_NONE, + NETDEV_PCPU_STAT_LSTATS, /* struct pcpu_lstats */ + NETDEV_PCPU_STAT_TSTATS, /* struct pcpu_sw_netstats */ + NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */ }; -#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN -#define IFF_EBRIDGE IFF_EBRIDGE -#define IFF_BONDING IFF_BONDING -#define IFF_ISATAP IFF_ISATAP -#define IFF_WAN_HDLC IFF_WAN_HDLC -#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE -#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE -#define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL -#define IFF_MACVLAN_PORT IFF_MACVLAN_PORT -#define IFF_BRIDGE_PORT IFF_BRIDGE_PORT -#define IFF_OVS_DATAPATH IFF_OVS_DATAPATH -#define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING -#define IFF_UNICAST_FLT IFF_UNICAST_FLT -#define IFF_TEAM_PORT IFF_TEAM_PORT -#define IFF_SUPP_NOFCS IFF_SUPP_NOFCS -#define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE -#define IFF_MACVLAN IFF_MACVLAN -#define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM -#define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER -#define IFF_NO_QUEUE IFF_NO_QUEUE -#define IFF_OPENVSWITCH IFF_OPENVSWITCH -#define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE -#define IFF_TEAM IFF_TEAM -#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED -#define IFF_MACSEC IFF_MACSEC -#define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER -#define IFF_FAILOVER IFF_FAILOVER -#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE +enum netdev_reg_state { + NETREG_UNINITIALIZED = 0, + NETREG_REGISTERED, /* completed register_netdevice */ + NETREG_UNREGISTERING, /* called unregister_netdevice */ + NETREG_UNREGISTERED, /* completed unregister todo */ + NETREG_RELEASED, /* called free_netdev */ + NETREG_DUMMY, /* dummy device for NAPI poll */ +}; /** * struct net_device - The DEVICE structure. @@ -1555,11 +1790,18 @@ enum netdev_priv_flags { * data with strictly "high-level" data, and it has to know about * almost every data structure used in the INET module. * + * @priv_flags: flags invisible to userspace defined as bits, see + * enum netdev_priv_flags for the definitions + * @lltx: device supports lockless Tx. Deprecated for real HW + * drivers. Mainly used by logical interfaces, such as + * bonding and tunnels + * @netmem_tx: device support netmem_tx. + * * @name: This is the first field of the "visible" part of this structure * (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 @@ -1588,6 +1830,7 @@ enum netdev_priv_flags { * 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 @@ -1595,33 +1838,33 @@ enum netdev_priv_flags { * @stats: Statistics struct, which was left as a legacy, use * rtnl_link_stats64 instead * - * @rx_dropped: Dropped packets by core network, + * @core_stats: core networking counters, * do not use this in drivers - * @tx_dropped: Dropped packets by core network, - * do not use this in drivers - * @rx_nohandler: nohandler dropped packets by core network on - * inactive devices, do not use this in drivers * @carrier_up_count: Number of times the carrier has been up * @carrier_down_count: Number of times the carrier has been down * * @wireless_handlers: List of functions to handle Wireless Extensions, * instead of ioctl, * see <net/iw_handler.h> for details. - * @wireless_data: Instance data managed by the core of wireless extensions * * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions + * @xdp_metadata_ops: Includes pointers to XDP metadata callbacks. + * @xsk_tx_metadata_ops: Includes pointers to AF_XDP TX metadata callbacks. * @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. * * @flags: Interface flags (a la BSD) - * @priv_flags: Like 'flags' but invisible to userspace, - * see if.h for the definitions + * @xdp_features: XDP capability supported by the device * @gflags: Global flags ( kept as legacy ) - * @padded: How much padding added by alloc_netdev() + * @priv_len: Size of the ->priv flexible array + * @priv: Flexible array containing private data * @operstate: RFC2863 operstate * @link_mode: Mapping policy to operstate * @if_port: Selectable AUI, TP, ... @@ -1644,12 +1887,16 @@ enum netdev_priv_flags { * @perm_addr: Permanent hw address * @addr_assign_type: Hw address assignment type * @addr_len: Hardware address length + * @upper_level: Maximum depth level of upper devices. + * @lower_level: Maximum depth level of lower devices. + * @threaded: napi threaded state. * @neigh_priv_len: Used in neigh_alloc() * @dev_id: Used to differentiate devices that share * the same link layer address * @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 @@ -1668,10 +1915,14 @@ enum netdev_priv_flags { * @tipc_ptr: TIPC specific data * @atalk_ptr: AppleTalk link * @ip_ptr: IPv4 specific data - * @dn_ptr: DECnet specific data * @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 + * @mctp_ptr: MCTP specific data + * @psp_dev: PSP crypto device registered for this netdev * * @dev_addr: Hw address (before bcast, * because most packets are unicast) @@ -1680,12 +1931,13 @@ enum netdev_priv_flags { * @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 * * @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 + * @tcx_ingress: BPF & 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, @@ -1700,47 +1952,64 @@ enum netdev_priv_flags { * @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_maps: all CPUs/RXQs maps for XPS device * * @xps_maps: XXX: need comments on this one - * @miniq_egress: clsact qdisc specific data for - * egress processing + * @tcx_egress: BPF & clsact qdisc specific data for egress processing + * @nf_hooks_egress: netfilter hooks executed for egress packets + * @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 + * @dev_refcnt: Number of references to this device + * @refcnt_tracker: Tracker directory for tracked references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one * * @reg_state: Register/unregister state machine * @dismantle: Device is going to be freed - * @rtnl_link_state: This enum represents the phases of creating - * a new link - * * @needs_free_netdev: Should unregister perform free_netdev? * @priv_destructor: Called from unregister * @npinfo: XXX: need comments on this one * @nd_net: Network namespace this network device is inside + * protected by @lock * * @ml_priv: Mid-layer private - * @lstats: Loopback statistics - * @tstats: Tunnel statistics - * @dstats: Dummy statistics - * @vstats: Virtual ethernet statistics + * @ml_priv_type: Mid-layer private type + * + * @pcpu_stat_type: Type of device statistics which the core should + * allocate/free: none, lstats, tstats, dstats. none + * means the driver is handling statistics allocation/ + * freeing internally. + * @lstats: Loopback statistics: packets, bytes + * @tstats: Tunnel statistics: RX/TX packets, RX/TX bytes + * @dstats: Dummy statistics: RX/TX/drop packets, RX/TX bytes * * @garp_port: GARP * @mrp_port: MRP * + * @dm_private: Drop monitor private + * * @dev: Class/net/name entry * @sysfs_groups: Space for optional device, statistics and wireless * sysfs groups * * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops + * @stat_ops: Optional ops for queue-aware statistics + * @queue_mgmt_ops: Optional ops for queue management * * @gso_max_size: Maximum size of generic segmentation offload + * @tso_max_size: Device (as in HW) limit on the max TSO request size * @gso_max_segs: Maximum number of segments that can be passed to the * NIC for GSO + * @tso_max_segs: Device (as in HW) limit on the max TSO segment count + * @gso_ipv4_max_size: Maximum size of generic segmentation offload, + * for IPv4. * * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device @@ -1750,26 +2019,166 @@ enum netdev_priv_flags { * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one + * @link_topo: Physical link topology tracking attached PHYs * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. * * @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 * switch port. * - * @wol_enabled: Wake-on-LAN is enabled + * @irq_affinity_auto: driver wants the core to store and re-assign the IRQ + * affinity. Set by netif_enable_irq_affinity(), then + * the driver must create a persistent napi by + * netif_napi_add_config() and finally bind the napi to + * IRQ (via netif_napi_set_irq()). + * + * @rx_cpu_rmap_auto: driver wants the core to manage the ARFS rmap. + * Set by calling netif_enable_cpu_rmap(). + * + * @see_all_hwtstamp_requests: device wants to see calls to + * ndo_hwtstamp_set() for all timestamp requests + * regardless of source, even if those aren't + * HWTSTAMP_SOURCE_NETDEV + * @change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN + * @netns_immutable: interface can't change network namespaces + * @fcoe_mtu: device supports maximum FCoE MTU, 2158 bytes + * + * @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 + * @ethtool: ethtool related state + * @xdp_state: stores info on attached XDP BPF programs + * + * @nested_level: Used 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. + * @gro_max_size: Maximum size of aggregated packet in generic + * receive offload (GRO) + * @gro_ipv4_max_size: Maximum size of aggregated packet in generic + * receive offload (GRO), for IPv4. + * @xdp_zc_max_segs: Maximum number of segments supported by AF_XDP + * zero copy driver + * + * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. + * @linkwatch_dev_tracker: refcount tracker used by linkwatch. + * @watchdog_dev_tracker: refcount tracker used by watchdog. + * @dev_registered_tracker: tracker for reference held while + * registered + * @offload_xstats_l3: L3 HW stats for this netdevice. + * + * @devlink_port: Pointer to related devlink port structure. + * Assigned by a driver before netdev registration using + * SET_NETDEV_DEVLINK_PORT macro. This pointer is static + * during the time netdevice is registered. + * + * @dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem, + * where the clock is recovered. + * + * @max_pacing_offload_horizon: max EDT offload horizon in nsec. + * @napi_config: An array of napi_config structures containing per-NAPI + * settings. + * @num_napi_configs: number of allocated NAPI config structs, + * always >= max(num_rx_queues, num_tx_queues). + * @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. + * + * @neighbours: List heads pointing to this device's neighbours' + * dev_list, one per address-family. + * @hwprov: Tracks which PTP performs hardware packet time stamping. * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ struct net_device { + /* Cacheline organization can be found documented in + * Documentation/networking/net_cachelines/net_device.rst. + * Please update the document when adding new fields. + */ + + /* TX read-mostly hotpath */ + __cacheline_group_begin(net_device_read_tx); + struct_group(priv_flags_fast, + unsigned long priv_flags:32; + unsigned long lltx:1; + unsigned long netmem_tx:1; + ); + const struct net_device_ops *netdev_ops; + const struct header_ops *header_ops; + struct netdev_queue *_tx; + netdev_features_t gso_partial_features; + unsigned int real_num_tx_queues; + unsigned int gso_max_size; + unsigned int gso_ipv4_max_size; + u16 gso_max_segs; + s16 num_tc; + /* Note : dev->mtu is often read without holding a lock. + * Writers usually hold RTNL. + * It is recommended to use READ_ONCE() to annotate the reads, + * and to use WRITE_ONCE() to annotate the writes. + */ + unsigned int mtu; + unsigned short needed_headroom; + struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; +#ifdef CONFIG_XPS + struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX]; +#endif +#ifdef CONFIG_NETFILTER_EGRESS + struct nf_hook_entries __rcu *nf_hooks_egress; +#endif +#ifdef CONFIG_NET_XGRESS + struct bpf_mprog_entry __rcu *tcx_egress; +#endif + __cacheline_group_end(net_device_read_tx); + + /* TXRX read-mostly hotpath */ + __cacheline_group_begin(net_device_read_txrx); + union { + struct pcpu_lstats __percpu *lstats; + struct pcpu_sw_netstats __percpu *tstats; + struct pcpu_dstats __percpu *dstats; + }; + unsigned long state; + unsigned int flags; + unsigned short hard_header_len; + netdev_features_t features; + struct inet6_dev __rcu *ip6_ptr; + __cacheline_group_end(net_device_read_txrx); + + /* RX read-mostly hotpath */ + __cacheline_group_begin(net_device_read_rx); + struct bpf_prog __rcu *xdp_prog; + struct list_head ptype_specific; + int ifindex; + unsigned int real_num_rx_queues; + struct netdev_rx_queue *_rx; + unsigned int gro_max_size; + unsigned int gro_ipv4_max_size; + rx_handler_func_t __rcu *rx_handler; + void __rcu *rx_handler_data; + possible_net_t nd_net; +#ifdef CONFIG_NETPOLL + struct netpoll_info __rcu *npinfo; +#endif +#ifdef CONFIG_NET_XGRESS + struct bpf_mprog_entry __rcu *tcx_ingress; +#endif + __cacheline_group_end(net_device_read_rx); + char name[IFNAMSIZ]; - struct hlist_node name_hlist; + struct netdev_name_node *name_node; struct dev_ifalias __rcu *ifalias; /* * I/O specific fields @@ -1778,7 +2187,6 @@ struct net_device { unsigned long mem_end; unsigned long mem_start; unsigned long base_addr; - int irq; /* * Some hardware also needs these fields (state,dev_list, @@ -1786,36 +2194,43 @@ struct net_device { * part of the usual set specified in Space.c. */ - unsigned long state; struct list_head dev_list; struct list_head napi_list; struct list_head unreg_list; struct list_head close_list; struct list_head ptype_all; - struct list_head ptype_specific; struct { struct list_head upper; struct list_head lower; } adj_list; - netdev_features_t features; + /* Read-mostly cache-line for fast-path access */ + xdp_features_t xdp_features; + const struct xdp_metadata_ops *xdp_metadata_ops; + const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops; + unsigned short gflags; + + unsigned short needed_tailroom; + netdev_features_t hw_features; netdev_features_t wanted_features; netdev_features_t vlan_features; netdev_features_t hw_enc_features; netdev_features_t mpls_features; - netdev_features_t gso_partial_features; - int ifindex; + unsigned int min_mtu; + unsigned int max_mtu; + unsigned short type; + unsigned char min_header_len; + unsigned char name_assign_type; + int group; - struct net_device_stats stats; + struct net_device_stats stats; /* not used by modern drivers */ - atomic_long_t rx_dropped; - atomic_long_t tx_dropped; - atomic_long_t rx_nohandler; + struct net_device_core_stats __percpu *core_stats; /* Stats to monitor link on/off, flapping */ atomic_t carrier_up_count; @@ -1823,13 +2238,8 @@ struct net_device { #ifdef CONFIG_WIRELESS_EXT const struct iw_handler_def *wireless_handlers; - struct iw_public_data *wireless_data; #endif - const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; -#ifdef CONFIG_NET_SWITCHDEV - const struct switchdev_ops *switchdev_ops; -#endif #ifdef CONFIG_NET_L3_MASTER_DEV const struct l3mdev_ops *l3mdev_ops; #endif @@ -1845,40 +2255,28 @@ struct net_device { const struct tlsdev_ops *tlsdev_ops; #endif - const struct header_ops *header_ops; - - unsigned int flags; - unsigned int priv_flags; - - unsigned short gflags; - unsigned short padded; - - unsigned char operstate; + unsigned int operstate; unsigned char link_mode; unsigned char if_port; unsigned char dma; - unsigned int mtu; - unsigned int min_mtu; - unsigned int max_mtu; - unsigned short type; - unsigned short hard_header_len; - unsigned char min_header_len; - - unsigned short needed_headroom; - unsigned short needed_tailroom; - /* Interface address info. */ unsigned char perm_addr[MAX_ADDR_LEN]; unsigned char addr_assign_type; unsigned char addr_len; + unsigned char upper_level; + unsigned char lower_level; + u8 threaded; + unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; + int irq; + u32 priv_len; + 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; @@ -1886,11 +2284,21 @@ struct net_device { #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 */ + struct in_device __rcu *ip_ptr; + /** @fib_nh_head: nexthops associated with this netdev */ + struct hlist_head fib_nh_head; #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; @@ -1901,41 +2309,41 @@ struct net_device { #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; #endif -#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) +#if IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; #endif - struct in_device __rcu *ip_ptr; -#if IS_ENABLED(CONFIG_DECNET) - struct dn_dev __rcu *dn_ptr; -#endif - struct inet6_dev __rcu *ip6_ptr; #if IS_ENABLED(CONFIG_AX25) - void *ax25_ptr; + struct ax25_dev __rcu *ax25_ptr; #endif +#if IS_ENABLED(CONFIG_CFG80211) struct wireless_dev *ieee80211_ptr; +#endif +#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN) struct wpan_dev *ieee802154_ptr; +#endif #if IS_ENABLED(CONFIG_MPLS_ROUTING) struct mpls_dev __rcu *mpls_ptr; #endif +#if IS_ENABLED(CONFIG_MCTP) + struct mctp_dev __rcu *mctp_ptr; +#endif +#if IS_ENABLED(CONFIG_INET_PSP) + struct psp_dev __rcu *psp_dev; +#endif /* * Cache lines mostly used on receive path (including eth_type_trans()) */ /* Interface address info used in eth_type_trans() */ - unsigned char *dev_addr; + const unsigned char *dev_addr; - struct netdev_rx_queue *_rx; unsigned int num_rx_queues; - unsigned int real_num_rx_queues; - - struct bpf_prog __rcu *xdp_prog; - unsigned long gro_flush_timeout; - rx_handler_func_t __rcu *rx_handler; - void __rcu *rx_handler_data; - -#ifdef CONFIG_NET_CLS_ACT - struct mini_Qdisc __rcu *miniq_ingress; -#endif +#define GRO_LEGACY_MAX_SIZE 65536u +/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), + * and shinfo->gso_segs is a 16bit field. + */ +#define GRO_MAX_SIZE (8 * 65535u) + unsigned int xdp_zc_max_segs; struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS struct nf_hook_entries __rcu *nf_hooks_ingress; @@ -1950,64 +2358,50 @@ struct net_device { /* * Cache lines mostly used on transmit path */ - 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; -#ifdef CONFIG_XPS - struct xps_dev_maps __rcu *xps_cpus_map; - struct xps_dev_maps __rcu *xps_rxqs_map; -#endif -#ifdef CONFIG_NET_CLS_ACT - struct mini_Qdisc __rcu *miniq_egress; -#endif + struct xdp_dev_bulk_queue __percpu *xdp_bulkq; +#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; + + u32 proto_down_reason; - int __percpu *pcpu_refcnt; struct list_head todo_list; +#ifdef CONFIG_PCPU_DEV_REFCNT + int __percpu *pcpu_refcnt; +#else + refcount_t dev_refcnt; +#endif + struct ref_tracker_dir refcnt_tracker; + struct list_head link_watch_list; - enum { NETREG_UNINITIALIZED=0, - NETREG_REGISTERED, /* completed register_netdevice */ - NETREG_UNREGISTERING, /* called unregister_netdevice */ - NETREG_UNREGISTERED, /* completed unregister todo */ - NETREG_RELEASED, /* called free_netdev */ - NETREG_DUMMY, /* dummy device for NAPI poll */ - } reg_state:8; + u8 reg_state; bool dismantle; - enum { - RTNL_LINK_INITIALIZED, - RTNL_LINK_INITIALIZING, - } rtnl_link_state:16; + /** @moving_ns: device is changing netns, protected by @lock */ + bool moving_ns; + /** @rtnl_link_initializing: Device being created, suppress events */ + bool rtnl_link_initializing; bool needs_free_netdev; void (*priv_destructor)(struct net_device *dev); -#ifdef CONFIG_NETPOLL - struct netpoll_info __rcu *npinfo; -#endif - - possible_net_t nd_net; - /* mid-layer private */ - union { - void *ml_priv; - struct pcpu_lstats __percpu *lstats; - struct pcpu_sw_netstats __percpu *tstats; - struct pcpu_dstats __percpu *dstats; - }; + void *ml_priv; + enum netdev_ml_priv_type ml_priv_type; + + enum netdev_stat_type pcpu_stat_type:8; #if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; @@ -2015,24 +2409,36 @@ struct net_device { #if IS_ENABLED(CONFIG_MRP) struct mrp_port __rcu *mrp_port; #endif - +#if IS_ENABLED(CONFIG_NET_DROP_MONITOR) + struct dm_hw_stat_delta __rcu *dm_private; +#endif struct device dev; - const struct attribute_group *sysfs_groups[4]; + const struct attribute_group *sysfs_groups[5]; const struct attribute_group *sysfs_rx_queue_group; const struct rtnl_link_ops *rtnl_link_ops; + const struct netdev_stat_ops *stat_ops; + + const struct netdev_queue_mgmt_ops *queue_mgmt_ops; + /* for setting kernel sock attribute on TCP connection setup */ -#define GSO_MAX_SIZE 65536 - unsigned int gso_max_size; -#define GSO_MAX_SEGS 65535 - u16 gso_max_segs; +#define GSO_MAX_SEGS 65535u +#define GSO_LEGACY_MAX_SIZE 65536u +/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), + * and shinfo->gso_segs is a 16bit field. + */ +#define GSO_MAX_SIZE (8 * GSO_MAX_SEGS) + +#define TSO_LEGACY_MAX_SIZE 65536 +#define TSO_MAX_SIZE UINT_MAX + unsigned int tso_max_size; +#define TSO_MAX_SEGS U16_MAX + u16 tso_max_segs; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; #endif - s16 num_tc; - struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; u8 prio_tc_map[TC_BITMASK + 1]; #if IS_ENABLED(CONFIG_FCOE) @@ -2041,15 +2447,150 @@ struct net_device { #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif + struct phy_link_topology *link_topo; struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; - struct lock_class_key *qdisc_running_key; bool proto_down; - unsigned wol_enabled:1; -}; + bool irq_affinity_auto; + bool rx_cpu_rmap_auto; + + /* priv_flags_slow, ungrouped to save space */ + unsigned long see_all_hwtstamp_requests:1; + unsigned long change_proto_down:1; + unsigned long netns_immutable:1; + unsigned long fcoe_mtu: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; + + /** @cfg: net_device queue-related configuration */ + struct netdev_config *cfg; + /** + * @cfg_pending: same as @cfg but when device is being actively + * reconfigured includes any changes to the configuration + * requested by the user, but which may or may not be rejected. + */ + struct netdev_config *cfg_pending; + struct ethtool_netdev_state *ethtool; + + /* protected by rtnl_lock */ + struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; + + u8 dev_addr_shadow[MAX_ADDR_LEN]; + netdevice_tracker linkwatch_dev_tracker; + netdevice_tracker watchdog_dev_tracker; + netdevice_tracker dev_registered_tracker; + struct rtnl_hw_stats64 *offload_xstats_l3; + + struct devlink_port *devlink_port; + +#if IS_ENABLED(CONFIG_DPLL) + struct dpll_pin __rcu *dpll_pin; +#endif +#if IS_ENABLED(CONFIG_PAGE_POOL) + /** @page_pools: page pools created for this netdevice */ + struct hlist_head page_pools; +#endif + + /** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */ + struct dim_irq_moder *irq_moder; + + u64 max_pacing_offload_horizon; + struct napi_config *napi_config; + u32 num_napi_configs; + u32 napi_defer_hard_irqs; + unsigned long gro_flush_timeout; + + /** + * @up: copy of @state's IFF_UP, but safe to read with just @lock. + * May report false negatives while the device is being opened + * or closed (@lock does not protect .ndo_open, or .ndo_close). + */ + bool up; + + /** + * @request_ops_lock: request the core to run all @netdev_ops and + * @ethtool_ops under the @lock. + */ + bool request_ops_lock; + + /** + * @lock: netdev-scope lock, protects a small selection of fields. + * Should always be taken using netdev_lock() / netdev_unlock() helpers. + * Drivers are free to use it for other protection. + * + * For the drivers that implement shaper or queue API, the scope + * of this lock is expanded to cover most ndo/queue/ethtool/sysfs + * operations. Drivers may opt-in to this behavior by setting + * @request_ops_lock. + * + * @lock protection mixes with rtnl_lock in multiple ways, fields are + * either: + * + * - simply protected by the instance @lock; + * + * - double protected - writers hold both locks, readers hold either; + * + * - ops protected - protected by the lock held around the NDOs + * and other callbacks, that is the instance lock on devices for + * which netdev_need_ops_lock() returns true, otherwise by rtnl_lock; + * + * - double ops protected - always protected by rtnl_lock but for + * devices for which netdev_need_ops_lock() returns true - also + * the instance lock. + * + * Simply protects: + * @gro_flush_timeout, @napi_defer_hard_irqs, @napi_list, + * @net_shaper_hierarchy, @reg_state, @threaded + * + * Double protects: + * @up, @moving_ns, @nd_net, @xdp_features + * + * Double ops protects: + * @real_num_rx_queues, @real_num_tx_queues + * + * Also protects some fields in: + * struct napi_struct, struct netdev_queue, struct netdev_rx_queue + * + * Ordering: take after rtnl_lock. + */ + struct mutex lock; + +#if IS_ENABLED(CONFIG_NET_SHAPER) + /** + * @net_shaper_hierarchy: data tracking the current shaper status + * see include/net/net_shapers.h + */ + struct net_shaper_hierarchy *net_shaper_hierarchy; +#endif + + struct hlist_head neighbours[NEIGH_NR_TABLES]; + + struct hwtstamp_provider __rcu *hwprov; + + u8 priv[] ____cacheline_aligned + __counted_by(priv_len); +} ____cacheline_aligned; #define to_net_dev(d) container_of(d, struct net_device, dev) +/* + * Driver should use this to assign devlink port instance to a netdevice + * before it registers the netdevice. Therefore devlink_port is static + * during the netdev lifetime after it is registered. + */ +#define SET_NETDEV_DEVLINK_PORT(dev, port) \ +({ \ + WARN_ON((dev)->reg_state != NETREG_UNINITIALIZED); \ + ((dev)->devlink_port = (port)); \ +}) + static inline bool netif_elide_gro(const struct net_device *dev) { if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog) @@ -2086,6 +2627,22 @@ int netdev_get_num_tc(struct net_device *dev) 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, @@ -2101,6 +2658,7 @@ static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) { + DEBUG_NET_WARN_ON_ONCE(index >= dev->num_tx_queues); return &dev->_tx[index]; } @@ -2122,26 +2680,11 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, 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); \ -} - -struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb, - struct net_device *sb_dev); +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, + struct sk_buff *skb, + struct net_device *sb_dev); /* returns the headroom that the master device needs to take in account * when forwarding to this dev @@ -2163,6 +2706,29 @@ static inline void netdev_reset_rx_headroom(struct net_device *dev) netdev_set_rx_headroom(dev, -1); } +static inline void *netdev_get_ml_priv(struct net_device *dev, + enum netdev_ml_priv_type type) +{ + if (dev->ml_priv_type != type) + return NULL; + + return dev->ml_priv; +} + +static inline void netdev_set_ml_priv(struct net_device *dev, + void *ml_priv, + enum netdev_ml_priv_type type) +{ + WARN(dev->ml_priv_type && dev->ml_priv_type != type, + "Overwriting already set ml_priv_type (%u) with different ml_priv_type (%u)!\n", + dev->ml_priv_type, type); + WARN(!dev->ml_priv_type && dev->ml_priv, + "Overwriting already set ml_priv and ml_priv_type is ML_PRIV_NONE!\n"); + + dev->ml_priv = ml_priv; + dev->ml_priv_type = type; +} + /* * Net namespace inlines */ @@ -2173,6 +2739,12 @@ struct net *dev_net(const struct net_device *dev) } static inline +struct net *dev_net_rcu(const struct net_device *dev) +{ + return read_pnet_rcu(&dev->nd_net); +} + +static inline void dev_net_set(struct net_device *dev, struct net *net) { write_pnet(&dev->nd_net, net); @@ -2186,7 +2758,7 @@ void dev_net_set(struct net_device *dev, struct net *net) */ static inline void *netdev_priv(const struct net_device *dev) { - return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN); + return (void *)dev->priv; } /* Set the sysfs physical device reference for the network logical device @@ -2200,158 +2772,167 @@ static inline void *netdev_priv(const struct net_device *dev) */ #define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype)) +void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, + enum netdev_queue_type type, + struct napi_struct *napi); + +static inline void netdev_lock(struct net_device *dev) +{ + mutex_lock(&dev->lock); +} + +static inline void netdev_unlock(struct net_device *dev) +{ + mutex_unlock(&dev->lock); +} +/* Additional netdev_lock()-related helpers are in net/netdev_lock.h */ + +void netif_napi_set_irq_locked(struct napi_struct *napi, int irq); + +static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) +{ + netdev_lock(napi->dev); + netif_napi_set_irq_locked(napi, irq); + netdev_unlock(napi->dev); +} + /* Default NAPI poll() weight * Device drivers are strongly advised to not use bigger value */ #define NAPI_POLL_WEIGHT 64 +void netif_napi_add_weight_locked(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight); + +static inline void +netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight) +{ + netdev_lock(dev); + netif_napi_add_weight_locked(dev, napi, poll, weight); + netdev_unlock(dev); +} + /** - * netif_napi_add - initialize a NAPI context - * @dev: network device - * @napi: NAPI context - * @poll: polling function - * @weight: default weight + * netif_napi_add() - initialize a NAPI context + * @dev: network device + * @napi: NAPI context + * @poll: polling function * * netif_napi_add() must be used to initialize a NAPI context prior to calling * *any* of the other NAPI-related functions. */ -void netif_napi_add(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight); +static inline void +netif_napi_add(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int)) +{ + netif_napi_add_weight(dev, napi, poll, NAPI_POLL_WEIGHT); +} + +static inline void +netif_napi_add_locked(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int)) +{ + netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT); +} + +static inline void +netif_napi_add_tx_weight(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight) +{ + set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); + netif_napi_add_weight(dev, napi, poll, weight); +} + +static inline void +netif_napi_add_config_locked(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int index) +{ + napi->index = index; + napi->config = &dev->napi_config[index]; + netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT); +} /** - * netif_tx_napi_add - initialize a NAPI context - * @dev: network device - * @napi: NAPI context - * @poll: polling function - * @weight: default weight + * netif_napi_add_config - initialize a NAPI context with persistent config + * @dev: network device + * @napi: NAPI context + * @poll: polling function + * @index: the NAPI index + */ +static inline void +netif_napi_add_config(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int index) +{ + netdev_lock(dev); + netif_napi_add_config_locked(dev, napi, poll, index); + netdev_unlock(dev); +} + +/** + * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only + * @dev: network device + * @napi: NAPI context + * @poll: polling function * * This variant of netif_napi_add() should be used from drivers using NAPI * to exclusively poll a TX queue. * This will avoid we add it into napi_hash[], thus polluting this hash table. */ -static inline void netif_tx_napi_add(struct net_device *dev, +static inline void netif_napi_add_tx(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), - int weight) + int (*poll)(struct napi_struct *, int)) { - set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); - netif_napi_add(dev, napi, poll, weight); + netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } +void __netif_napi_del_locked(struct napi_struct *napi); + /** - * netif_napi_del - remove a NAPI context + * __netif_napi_del - remove a NAPI context * @napi: NAPI context * - * netif_napi_del() removes a NAPI context from the network device NAPI list + * 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); - -struct napi_gro_cb { - /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ - void *frag0; - - /* Length of frag0. */ - unsigned int frag0_len; - - /* This indicates where we are processing relative to skb->data. */ - int data_offset; - - /* This is non-zero if the packet cannot be merged with the new skb. */ - u16 flush; - - /* Save the IP ID here and check when we get to the transport layer */ - u16 flush_id; - - /* Number of segments aggregated. */ - u16 count; - - /* Start offset for remote checksum offload */ - u16 gro_remcsum_start; - - /* jiffies when first packet was created/queued */ - unsigned long age; - - /* Used in ipv6_gro_receive() and foo-over-udp */ - u16 proto; - - /* This is non-zero if the packet may be of the same flow. */ - u8 same_flow:1; - - /* Used in tunnel GRO receive */ - u8 encap_mark:1; - - /* GRO checksum is valid */ - u8 csum_valid:1; - - /* Number of checksums via CHECKSUM_UNNECESSARY */ - u8 csum_cnt:3; - - /* Free the skb? */ - u8 free:2; -#define NAPI_GRO_FREE 1 -#define NAPI_GRO_FREE_STOLEN_HEAD 2 - - /* Used in foo-over-udp, set in udp[46]_gro_receive */ - u8 is_ipv6:1; - - /* Used in GRE, set in fou/gue_gro_receive */ - u8 is_fou:1; - - /* Used to determine if flush_id can be ignored */ - u8 is_atomic:1; - - /* Number of gro_receive callbacks this packet already went through */ - u8 recursion_counter:4; - - /* 1 bit hole */ - - /* used to support CHECKSUM_COMPLETE for tunneling protocols */ - __wsum csum; - - /* used in skb_gro_receive() slow path */ - struct sk_buff *last; -}; - -#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) - -#define GRO_RECURSION_LIMIT 15 -static inline int gro_recursion_inc_test(struct sk_buff *skb) +static inline void __netif_napi_del(struct napi_struct *napi) { - return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; + netdev_lock(napi->dev); + __netif_napi_del_locked(napi); + netdev_unlock(napi->dev); } -typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); -static inline struct sk_buff *call_gro_receive(gro_receive_t cb, - struct list_head *head, - struct sk_buff *skb) +static inline void netif_napi_del_locked(struct napi_struct *napi) { - if (unlikely(gro_recursion_inc_test(skb))) { - NAPI_GRO_CB(skb)->flush |= 1; - return NULL; - } - - return cb(head, skb); + __netif_napi_del_locked(napi); + synchronize_net(); } -typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, - struct sk_buff *); -static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, - struct sock *sk, - struct list_head *head, - struct sk_buff *skb) +/** + * netif_napi_del - remove a NAPI context + * @napi: NAPI context + * + * netif_napi_del() removes a NAPI context from the network device NAPI list + */ +static inline void netif_napi_del(struct napi_struct *napi) { - if (unlikely(gro_recursion_inc_test(skb))) { - NAPI_GRO_CB(skb)->flush |= 1; - return NULL; - } - - return cb(sk, head, skb); + __netif_napi_del(napi); + synchronize_net(); } +int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs); +void netif_set_affinity_auto(struct net_device *dev); + struct packet_type { __be16 type; /* This is really htons(ether_type). */ bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ + netdevice_tracker dev_tracker; int (*func) (struct sk_buff *, struct net_device *, struct packet_type *, @@ -2361,6 +2942,7 @@ struct packet_type { 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; }; @@ -2382,19 +2964,113 @@ struct packet_offload { /* often modified stats are per-CPU, other are shared (netdev->stats) */ struct pcpu_sw_netstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); +struct pcpu_dstats { + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; + u64_stats_t rx_drops; + u64_stats_t tx_drops; + struct u64_stats_sync syncp; +} __aligned(8 * 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); + u64_stats_add(&tstats->rx_bytes, len); + u64_stats_inc(&tstats->rx_packets); + u64_stats_update_end(&tstats->syncp); +} + +static inline void dev_sw_netstats_tx_add(struct net_device *dev, + unsigned int packets, + unsigned int len) +{ + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + u64_stats_add(&tstats->tx_bytes, len); + u64_stats_add(&tstats->tx_packets, 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); +} + +static inline void dev_dstats_rx_add(struct net_device *dev, + unsigned int len) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->rx_packets); + u64_stats_add(&dstats->rx_bytes, len); + u64_stats_update_end(&dstats->syncp); +} + +static inline void dev_dstats_rx_dropped(struct net_device *dev) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->rx_drops); + u64_stats_update_end(&dstats->syncp); +} + +static inline void dev_dstats_rx_dropped_add(struct net_device *dev, + unsigned int packets) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_add(&dstats->rx_drops, packets); + u64_stats_update_end(&dstats->syncp); +} + +static inline void dev_dstats_tx_add(struct net_device *dev, + unsigned int len) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->tx_packets); + u64_stats_add(&dstats->tx_bytes, len); + u64_stats_update_end(&dstats->syncp); +} + +static inline void dev_dstats_tx_dropped(struct net_device *dev) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->tx_drops); + u64_stats_update_end(&dstats->syncp); +} + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ @@ -2412,6 +3088,20 @@ struct pcpu_lstats { #define netdev_alloc_pcpu_stats(type) \ __netdev_alloc_pcpu_stats(type, GFP_KERNEL) +#define devm_netdev_alloc_pcpu_stats(dev, type) \ +({ \ + typeof(type) __percpu *pcpu_stats = devm_alloc_percpu(dev, type);\ + if (pcpu_stats) { \ + int __cpu; \ + for_each_possible_cpu(__cpu) { \ + typeof(type) *stat; \ + stat = per_cpu_ptr(pcpu_stats, __cpu); \ + u64_stats_init(&stat->syncp); \ + } \ + } \ + pcpu_stats; \ +}) + enum netdev_lag_tx_type { NETDEV_LAG_TX_TYPE_UNKNOWN, NETDEV_LAG_TX_TYPE_RANDOM, @@ -2428,6 +3118,7 @@ enum netdev_lag_hash { NETDEV_LAG_HASH_L23, NETDEV_LAG_HASH_E23, NETDEV_LAG_HASH_E34, + NETDEV_LAG_HASH_VLAN_SRCMAC, NETDEV_LAG_HASH_UNKNOWN, }; @@ -2468,6 +3159,7 @@ enum netdev_cmd { NETDEV_PRE_TYPE_CHANGE, NETDEV_POST_TYPE_CHANGE, NETDEV_POST_INIT, + NETDEV_PRE_UNINIT, NETDEV_RELEASE, NETDEV_NOTIFY_PEERS, NETDEV_JOIN, @@ -2485,11 +3177,25 @@ enum netdev_cmd { NETDEV_CVLAN_FILTER_DROP_INFO, NETDEV_SVLAN_FILTER_PUSH_INFO, NETDEV_SVLAN_FILTER_DROP_INFO, + NETDEV_OFFLOAD_XSTATS_ENABLE, + NETDEV_OFFLOAD_XSTATS_DISABLE, + NETDEV_OFFLOAD_XSTATS_REPORT_USED, + NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, + NETDEV_XDP_FEAT_CHANGE, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); 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; @@ -2526,6 +3232,42 @@ struct netdev_notifier_pre_changeaddr_info { const unsigned char *dev_addr; }; +enum netdev_offload_xstats_type { + NETDEV_OFFLOAD_XSTATS_TYPE_L3 = 1, +}; + +struct netdev_notifier_offload_xstats_info { + struct netdev_notifier_info info; /* must be first */ + enum netdev_offload_xstats_type type; + + union { + /* NETDEV_OFFLOAD_XSTATS_REPORT_DELTA */ + struct netdev_notifier_offload_xstats_rd *report_delta; + /* NETDEV_OFFLOAD_XSTATS_REPORT_USED */ + struct netdev_notifier_offload_xstats_ru *report_used; + }; +}; + +int netdev_offload_xstats_enable(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct netlink_ext_ack *extack); +int netdev_offload_xstats_disable(struct net_device *dev, + enum netdev_offload_xstats_type type); +bool netdev_offload_xstats_enabled(const struct net_device *dev, + enum netdev_offload_xstats_type type); +int netdev_offload_xstats_get(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_hw_stats64 *stats, bool *used, + struct netlink_ext_ack *extack); +void +netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *rd, + const struct rtnl_hw_stats64 *stats); +void +netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *ru); +void netdev_offload_xstats_push_delta(struct net_device *dev, + enum netdev_offload_xstats_type type, + const struct rtnl_hw_stats64 *stats); + static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { @@ -2546,9 +3288,8 @@ netdev_notifier_info_to_extack(const struct netdev_notifier_info *info) } int call_netdevice_notifiers(unsigned long val, struct net_device *dev); - - -extern rwlock_t dev_base_lock; /* Device list lock */ +int call_netdevice_notifiers_info(unsigned long val, + struct netdev_notifier_info *info); #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) @@ -2560,13 +3301,20 @@ extern rwlock_t dev_base_lock; /* Device list lock */ 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) \ - for_each_netdev_rcu(&init_net, slave) \ + for_each_netdev_rcu(dev_net_rcu(bond), slave) \ if (netdev_master_upper_dev_get_rcu(slave) == (bond)) #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) +#define for_each_netdev_dump(net, d, ifindex) \ + for (; (d = xa_find(&(net)->dev_by_index, &ifindex, \ + ULONG_MAX, XA_PRESENT)); ifindex++) + static inline struct net_device *next_net_device(struct net_device *dev) { struct list_head *lh; @@ -2593,19 +3341,12 @@ static inline struct net_device *first_net_device(struct net *net) net_device_entry(net->dev_base_head.next); } -static inline struct net_device *first_net_device_rcu(struct net *net) -{ - struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head)); - - return lh == &net->dev_base_head ? NULL : net_device_entry(lh); -} - int netdev_boot_setup_check(struct net_device *dev); -unsigned long netdev_boot_base(const char *prefix, int unit); +struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, + const char *hwaddr); struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); -struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type); void dev_add_pack(struct packet_type *pt); void dev_remove_pack(struct packet_type *pt); void __dev_remove_pack(struct packet_type *pt); @@ -2614,301 +3355,75 @@ void dev_remove_offload(struct packet_offload *po); int dev_get_iflink(const struct net_device *dev); int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb); -struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, - unsigned short mask); +int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, + struct net_device_path_stack *stack); struct net_device *dev_get_by_name(struct net *net, const char *name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); +bool netdev_name_in_use(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); +int netif_open(struct net_device *dev, struct netlink_ext_ack *extack); int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); +void netif_close(struct net_device *dev); void dev_close(struct net_device *dev); -void dev_close_many(struct list_head *head, bool unlink); +void netif_close_many(struct list_head *head, bool unlink); +void netif_disable_lro(struct net_device *dev); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); -u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); -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 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); -static inline void unregister_netdevice(struct net_device *dev) -{ - unregister_netdevice_queue(dev, NULL); -} - -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 *sb_dev); -DECLARE_PER_CPU(int, xmit_recursion); -#define XMIT_RECURSION_LIMIT 10 +int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev); +int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); -static inline int dev_recursion_level(void) -{ - return this_cpu_read(xmit_recursion); -} - -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); -struct net_device *dev_get_by_napi_id(unsigned int napi_id); -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); - -static inline unsigned int skb_gro_offset(const struct sk_buff *skb) +static inline int dev_queue_xmit(struct sk_buff *skb) { - return NAPI_GRO_CB(skb)->data_offset; + return __dev_queue_xmit(skb, NULL); } -static inline unsigned int skb_gro_len(const struct sk_buff *skb) +static inline int dev_queue_xmit_accel(struct sk_buff *skb, + struct net_device *sb_dev) { - return skb->len - NAPI_GRO_CB(skb)->data_offset; + return __dev_queue_xmit(skb, sb_dev); } -static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) +static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { - NAPI_GRO_CB(skb)->data_offset += len; -} - -static inline void *skb_gro_header_fast(struct sk_buff *skb, - unsigned int offset) -{ - return NAPI_GRO_CB(skb)->frag0 + offset; -} - -static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) -{ - return NAPI_GRO_CB(skb)->frag0_len < hlen; -} + int ret; -static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) -{ - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; -} - -static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, - unsigned int offset) -{ - if (!pskb_may_pull(skb, hlen)) - return NULL; - - skb_gro_frag0_invalidate(skb); - return skb->data + offset; -} - -static inline void *skb_gro_network_header(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + - skb_network_offset(skb); -} - -static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, - const void *start, unsigned int len) -{ - if (NAPI_GRO_CB(skb)->csum_valid) - NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum, - csum_partial(start, len, 0)); -} - -/* GRO checksum functions. These are logical equivalents of the normal - * checksum functions (in skbuff.h) except that they operate on the GRO - * offsets and fields in sk_buff. - */ - -__sum16 __skb_gro_checksum_complete(struct sk_buff *skb); - -static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); -} - -static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, - bool zero_okay, - __sum16 check) -{ - return ((skb->ip_summed != CHECKSUM_PARTIAL || - skb_checksum_start_offset(skb) < - skb_gro_offset(skb)) && - !skb_at_gro_remcsum_start(skb) && - NAPI_GRO_CB(skb)->csum_cnt == 0 && - (!zero_okay || check)); -} - -static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb, - __wsum psum) -{ - if (NAPI_GRO_CB(skb)->csum_valid && - !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum))) - return 0; - - NAPI_GRO_CB(skb)->csum = psum; - - return __skb_gro_checksum_complete(skb); -} - -static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) -{ - if (NAPI_GRO_CB(skb)->csum_cnt > 0) { - /* Consume a checksum from CHECKSUM_UNNECESSARY */ - NAPI_GRO_CB(skb)->csum_cnt--; - } else { - /* Update skb for CHECKSUM_UNNECESSARY and csum_level when we - * verified a new top level checksum or an encapsulated one - * during GRO. This saves work if we fallback to normal path. - */ - __skb_incr_checksum_unnecessary(skb); - } -} - -#define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \ - compute_pseudo) \ -({ \ - __sum16 __ret = 0; \ - if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ - __ret = __skb_gro_checksum_validate_complete(skb, \ - compute_pseudo(skb, proto)); \ - if (!__ret) \ - skb_gro_incr_csum_unnecessary(skb); \ - __ret; \ -}) - -#define skb_gro_checksum_validate(skb, proto, compute_pseudo) \ - __skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo) - -#define skb_gro_checksum_validate_zero_check(skb, proto, check, \ - compute_pseudo) \ - __skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo) - -#define skb_gro_checksum_simple_validate(skb) \ - __skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo) - -static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->csum_cnt == 0 && - !NAPI_GRO_CB(skb)->csum_valid); -} - -static inline void __skb_gro_checksum_convert(struct sk_buff *skb, - __sum16 check, __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) \ -do { \ - if (__skb_gro_checksum_convert_check(skb)) \ - __skb_gro_checksum_convert(skb, check, \ - compute_pseudo(skb, proto)); \ -} while (0) - -struct gro_remcsum { - int offset; - __wsum delta; -}; - -static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) -{ - grc->offset = 0; - grc->delta = 0; + ret = __dev_direct_xmit(skb, queue_id); + if (!dev_xmit_complete(ret)) + kfree_skb(skb); + return ret; } -static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, - unsigned int off, size_t hdrlen, - int start, int offset, - struct gro_remcsum *grc, - bool nopartial) +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); +static inline void unregister_netdevice(struct net_device *dev) { - __wsum delta; - size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); - - BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); - - if (!nopartial) { - NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; - return ptr; - } - - ptr = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, off + plen)) { - ptr = skb_gro_header_slow(skb, off + plen, off); - if (!ptr) - return NULL; - } - - delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, - start, offset); - - /* Adjust skb->csum since we changed the packet */ - NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); - - grc->offset = off + hdrlen + offset; - grc->delta = delta; - - return ptr; + unregister_netdevice_queue(dev, NULL); } -static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, - struct gro_remcsum *grc) -{ - void *ptr; - size_t plen = grc->offset + sizeof(u16); - - if (!grc->delta) - return; - - ptr = skb_gro_header_fast(skb, grc->offset); - if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { - ptr = skb_gro_header_slow(skb, plen, grc->offset); - if (!ptr) - return; - } - - remcsum_unadjust((__sum16 *)ptr, grc->delta); -} +int netdev_refcnt_read(const struct net_device *dev); +void free_netdev(struct net_device *dev); -#ifdef CONFIG_XFRM_OFFLOAD -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) -{ - if (PTR_ERR(pp) != -EINPROGRESS) - NAPI_GRO_CB(skb)->flush |= flush; -} -static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff *pp, - int flush, - struct gro_remcsum *grc) -{ - if (PTR_ERR(pp) != -EINPROGRESS) { - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, grc); - skb->remcsum_offload = 0; - } -} -#else -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) -{ - NAPI_GRO_CB(skb)->flush |= flush; -} -static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff *pp, - int flush, - struct gro_remcsum *grc) -{ - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, grc); - skb->remcsum_offload = 0; -} -#endif +struct net_device *netdev_get_xmit_slave(struct net_device *dev, + struct sk_buff *skb, + bool all_slaves); +struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, + struct sock *sk); +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 *netdev_get_by_index(struct net *net, int ifindex, + netdevice_tracker *tracker, gfp_t gfp); +struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex); +struct net_device *netdev_get_by_name(struct net *net, const char *name, + netdevice_tracker *tracker, gfp_t gfp); +struct net_device *netdev_get_by_flags_rcu(struct net *net, netdevice_tracker *tracker, + unsigned short flags, unsigned short mask); +struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); +void netdev_copy_name(struct net_device *dev, char *name); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -2931,6 +3446,15 @@ static inline int dev_parse_header(const struct sk_buff *skb, return dev->header_ops->parse(skb, haddr); } +static inline __be16 dev_parse_header_protocol(const struct sk_buff *skb) +{ + const struct net_device *dev = skb->dev; + + if (!dev->header_ops || !dev->header_ops->parse_protocol) + return 0; + return dev->header_ops->parse_protocol(skb); +} + /* ll_header must have at least hard_header_len allocated */ static inline bool dev_validate_header(const struct net_device *dev, char *ll_header, int len) @@ -2951,26 +3475,36 @@ static inline bool dev_validate_header(const struct net_device *dev, return false; } -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); -static inline int unregister_gifconf(unsigned int family) +static inline bool dev_has_header(const struct net_device *dev) { - return register_gifconf(family, NULL); + return dev->header_ops && dev->header_ops->create; } -#ifdef CONFIG_NET_FLOW_LIMIT -#define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */ -struct sd_flow_limit { - u64 count; - unsigned int num_buckets; - unsigned int history_head; - u16 history[FLOW_LIMIT_HISTORY]; - u8 buckets[]; +struct numa_drop_counters { + atomic_t drops0 ____cacheline_aligned_in_smp; + atomic_t drops1 ____cacheline_aligned_in_smp; }; -extern int netdev_flow_limit_table_len; -#endif /* CONFIG_NET_FLOW_LIMIT */ +static inline int numa_drop_read(const struct numa_drop_counters *ndc) +{ + return atomic_read(&ndc->drops0) + atomic_read(&ndc->drops1); +} + +static inline void numa_drop_add(struct numa_drop_counters *ndc, int val) +{ + int n = numa_node_id() % 2; + + if (n) + atomic_add(val, &ndc->drops1); + else + atomic_add(val, &ndc->drops0); +} + +static inline void numa_drop_reset(struct numa_drop_counters *ndc) +{ + atomic_set(&ndc->drops0, 0); + atomic_set(&ndc->drops1, 0); +} /* * Incoming packets are placed on per-CPU queues @@ -2978,14 +3512,19 @@ extern int netdev_flow_limit_table_len; struct softnet_data { struct list_head poll_list; struct sk_buff_head process_queue; + local_lock_t process_queue_bh_lock; /* stats */ unsigned int processed; unsigned int time_squeeze; - unsigned int received_rps; #ifdef CONFIG_RPS struct softnet_data *rps_ipi_list; #endif + + unsigned int received_rps; + bool in_net_rx_action; + bool in_napi_threaded_poll; + #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit __rcu *flow_limit; #endif @@ -2995,6 +3534,8 @@ struct softnet_data { #ifdef CONFIG_XFRM_OFFLOAD struct sk_buff_head xfrm_backlog; #endif + /* written and read only by owning cpu: */ + struct netdev_xmit xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, * and only read by other cpus. Worth using a cache line. @@ -3005,30 +3546,45 @@ struct softnet_data { call_single_data_t csd ____cacheline_aligned_in_smp; struct softnet_data *rps_ipi_next; unsigned int cpu; + + /* We force a cacheline alignment from here, to hold together + * input_queue_tail, input_pkt_queue and backlog.state. + * We add holes so that backlog.state is the last field + * of this cache line. + */ + long pad[3] ____cacheline_aligned_in_smp; unsigned int input_queue_tail; #endif - unsigned int dropped; struct sk_buff_head input_pkt_queue; + struct napi_struct backlog; + struct numa_drop_counters drop_counters; + + int defer_ipi_scheduled ____cacheline_aligned_in_smp; + call_single_data_t defer_csd; +}; + +DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); + +struct page_pool_bh { + struct page_pool *pool; + local_lock_t bh_lock; }; +DECLARE_PER_CPU(struct page_pool_bh, system_page_pool); -static inline void input_queue_head_incr(struct softnet_data *sd) +#ifndef CONFIG_PREEMPT_RT +static inline int dev_recursion_level(void) { -#ifdef CONFIG_RPS - sd->input_queue_head++; -#endif + return this_cpu_read(softnet_data.xmit.recursion); } - -static inline void input_queue_tail_incr_save(struct softnet_data *sd, - unsigned int *qtail) +#else +static inline int dev_recursion_level(void) { -#ifdef CONFIG_RPS - *qtail = ++sd->input_queue_tail; -#endif + return current->net_xmit.recursion; } -DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); +#endif void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); @@ -3093,6 +3649,13 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev) static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { + /* Paired with READ_ONCE() from dev_watchdog() */ + WRITE_ONCE(dev_queue->trans_start, jiffies); + + /* This barrier is paired with smp_mb() from dev_watchdog() */ + smp_mb__before_atomic(); + + /* Must be an atomic op see netif_txq_try_stop() */ set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } @@ -3144,6 +3707,34 @@ netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue) } /** + * netdev_queue_set_dql_min_limit - set dql minimum limit + * @dev_queue: pointer to transmit queue + * @min_limit: dql minimum limit + * + * Forces xmit_more() to return true until the minimum threshold + * defined by @min_limit is reached (or until the tx queue is + * empty). Warning: to be use with care, misuse will impact the + * latency. + */ +static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue, + unsigned int min_limit) +{ +#ifdef CONFIG_BQL + dev_queue->dql.min_limit = min_limit; +#endif +} + +static inline int netdev_queue_dql_avail(const struct netdev_queue *txq) +{ +#ifdef CONFIG_BQL + /* Non-BQL migrated drivers will return 0, too. */ + return dql_avail(&txq->dql); +#else + return 0; +#endif +} + +/** * netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write * @dev_queue: pointer to transmit queue * @@ -3171,6 +3762,16 @@ static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_qu #endif } +/** + * netdev_tx_sent_queue - report the number of bytes queued to a given tx queue + * @dev_queue: network device queue + * @bytes: number of bytes queued to the device queue + * + * Report the number of bytes queued for sending/completion to the network + * device hardware queue. @bytes should be a good approximation and should + * exactly match netdev_completed_queue() @bytes. + * This is typically called once per packet, from ndo_start_xmit(). + */ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, unsigned int bytes) { @@ -3180,6 +3781,12 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, if (likely(dql_avail(&dev_queue->dql) >= 0)) return; + /* Paired with READ_ONCE() from dev_watchdog() */ + WRITE_ONCE(dev_queue->trans_start, jiffies); + + /* This barrier is paired with smp_mb() from dev_watchdog() */ + smp_mb__before_atomic(); + set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state); /* @@ -3187,7 +3794,7 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, * because in netdev_tx_completed_queue we update the dql_completed * before checking the XOFF flag. */ - smp_mb(); + smp_mb__after_atomic(); /* check again in case another CPU has just made room avail */ if (unlikely(dql_avail(&dev_queue->dql) >= 0)) @@ -3216,13 +3823,14 @@ static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, } /** - * netdev_sent_queue - report the number of bytes queued to hardware - * @dev: network device - * @bytes: number of bytes queued to the hardware device queue + * netdev_sent_queue - report the number of bytes queued to hardware + * @dev: network device + * @bytes: number of bytes queued to the hardware device queue * - * Report the number of bytes queued for sending/completion to the network - * device hardware queue. @bytes should be a good approximation and should - * exactly match netdev_completed_queue() @bytes + * Report the number of bytes queued for sending/completion to the network + * device hardware queue#0. @bytes should be a good approximation and should + * exactly match netdev_completed_queue() @bytes. + * This is typically called once per packet, from ndo_start_xmit(). */ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes) { @@ -3237,6 +3845,15 @@ static inline bool __netdev_sent_queue(struct net_device *dev, xmit_more); } +/** + * netdev_tx_completed_queue - report number of packets/bytes at TX completion. + * @dev_queue: network device queue + * @pkts: number of packets (currently ignored) + * @bytes: number of bytes dequeued from the device queue + * + * Must be called at most once per TX completion round (and not per + * individual packet), so that BQL can adjust its limits appropriately. + */ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, unsigned int pkts, unsigned int bytes) { @@ -3247,13 +3864,13 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, dql_completed(&dev_queue->dql, bytes); /* - * Without the memory barrier there is a small possiblity that + * Without the memory barrier there is a small possibility that * netdev_tx_sent_queue will miss the update and cause the queue to * be stopped forever */ - smp_mb(); + smp_mb(); /* NOTE: netdev_txq_completed_mb() assumes this exists */ - if (dql_avail(&dev_queue->dql) < 0) + if (unlikely(dql_avail(&dev_queue->dql) < 0)) return; if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state)) @@ -3286,6 +3903,17 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q) } /** + * netdev_tx_reset_subqueue - reset the BQL stats and state of a netdev queue + * @dev: network device + * @qid: stack index of the queue to reset + */ +static inline void netdev_tx_reset_subqueue(const struct net_device *dev, + u32 qid) +{ + netdev_tx_reset_queue(netdev_get_tx_queue(dev, qid)); +} + +/** * netdev_reset_queue - reset the packets and bytes count of a network device * @dev_queue: network device * @@ -3294,7 +3922,7 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q) */ static inline void netdev_reset_queue(struct net_device *dev_queue) { - netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0)); + netdev_tx_reset_subqueue(dev_queue, 0); } /** @@ -3363,7 +3991,7 @@ static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index) } /** - * netif_subqueue_stopped - test status of subqueue + * __netif_subqueue_stopped - test status of subqueue * @dev: network device * @queue_index: sub queue index * @@ -3377,6 +4005,13 @@ static inline bool __netif_subqueue_stopped(const struct net_device *dev, return netif_tx_queue_stopped(txq); } +/** + * netif_subqueue_stopped - test status of subqueue + * @dev: network device + * @skb: sub queue buffer pointer + * + * Check individual transmit queue of a device with multiple transmit queues. + */ static inline bool netif_subqueue_stopped(const struct net_device *dev, struct sk_buff *skb) { @@ -3401,7 +4036,7 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index); int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, - u16 index, bool is_rxqs_map); + u16 index, enum xps_map_type type); /** * netif_attr_test_mask - Test a CPU or Rx queue set in a mask @@ -3425,7 +4060,7 @@ static inline bool netif_attr_test_mask(unsigned long j, * @online_mask: bitmask for CPUs/Rx queues that are online * @nr_bits: number of bits in the bitmask * - * Returns true if a CPU/Rx queue is online. + * Returns: true if a CPU/Rx queue is online. */ static inline bool netif_attr_test_online(unsigned long j, const unsigned long *online_mask, @@ -3445,7 +4080,8 @@ static inline bool netif_attr_test_online(unsigned long j, * @srcp: the cpumask/Rx queue mask pointer * @nr_bits: number of bits in the bitmask * - * Returns >= nr_bits if no further CPUs/Rx queues set. + * Returns: next (after n) CPU/Rx queue index in the mask; + * >= nr_bits if no further CPUs/Rx queues set. */ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, unsigned int nr_bits) @@ -3461,13 +4097,14 @@ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, } /** - * 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 * @nr_bits: number of bits in the bitmask * - * Returns >= nr_bits if no further CPUs/Rx queues set in both. + * Returns: next (after n) CPU/Rx queue index set in both masks; + * >= nr_bits if no further CPUs/Rx queues set in both. */ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, const unsigned long *src2p, @@ -3496,7 +4133,7 @@ static inline int netif_set_xps_queue(struct net_device *dev, static inline int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, - u16 index, bool is_rxqs_map) + u16 index, enum xps_map_type type) { return 0; } @@ -3514,51 +4151,19 @@ static inline bool netif_is_multiqueue(const struct net_device *dev) } int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq); - -#ifdef CONFIG_SYSFS int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq); -#else -static inline int netif_set_real_num_rx_queues(struct net_device *dev, - unsigned int rxqs) -{ - dev->real_num_rx_queues = rxqs; - return 0; -} -#endif +int netif_set_real_num_queues(struct net_device *dev, + unsigned int txq, unsigned int rxq); -static inline struct netdev_rx_queue * -__netif_get_rx_queue(struct net_device *dev, unsigned int rxq) -{ - return dev->_rx + rxq; -} - -#ifdef CONFIG_SYSFS -static inline unsigned int get_netdev_rx_queue_index( - struct netdev_rx_queue *queue) -{ - struct net_device *dev = queue->dev; - int index = queue - dev->_rx; - - BUG_ON(index >= dev->num_rx_queues); - return index; -} -#endif - -#define DEFAULT_MAX_NUM_RSS_QUEUES (8) int netif_get_num_default_rss_queues(void); -enum skb_free_reason { - SKB_REASON_CONSUMED, - SKB_REASON_DROPPED, -}; - -void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason); -void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason); +void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason); +void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason); /* * It is not allowed to call kfree_skb() or consume_skb() from hardware * interrupt context or with hardware interrupts being disabled. - * (in_irq() || irqs_disabled()) + * (in_hardirq() || irqs_disabled()) * * We provide four helpers that can be used in following contexts : * @@ -3576,37 +4181,45 @@ void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason); */ static inline void dev_kfree_skb_irq(struct sk_buff *skb) { - __dev_kfree_skb_irq(skb, SKB_REASON_DROPPED); + dev_kfree_skb_irq_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } static inline void dev_consume_skb_irq(struct sk_buff *skb) { - __dev_kfree_skb_irq(skb, SKB_REASON_CONSUMED); + dev_kfree_skb_irq_reason(skb, SKB_CONSUMED); } static inline void dev_kfree_skb_any(struct sk_buff *skb) { - __dev_kfree_skb_any(skb, SKB_REASON_DROPPED); + dev_kfree_skb_any_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } static inline void dev_consume_skb_any(struct sk_buff *skb) { - __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); + dev_kfree_skb_any_reason(skb, SKB_CONSUMED); } -void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); -int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); +u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, + const struct bpf_prog *xdp_prog); +void generic_xdp_tx(struct sk_buff *skb, const struct bpf_prog *xdp_prog); +int do_xdp_generic(const struct bpf_prog *xdp_prog, struct sk_buff **pskb); int netif_rx(struct sk_buff *skb); -int netif_rx_ni(struct sk_buff *skb); +int __netif_rx(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_internal(struct list_head *head); void netif_receive_skb_list(struct list_head *head); -gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); -void napi_gro_flush(struct napi_struct *napi, bool flush_old); +gro_result_t gro_receive_skb(struct gro_node *gro, struct sk_buff *skb); + +static inline gro_result_t napi_gro_receive(struct napi_struct *napi, + struct sk_buff *skb) +{ + return gro_receive_skb(&napi->gro, skb); +} + struct sk_buff *napi_get_frags(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); -struct packet_offload *gro_find_receive_by_type(__be16 type); -struct packet_offload *gro_find_complete_by_type(__be16 type); static inline void napi_free_frags(struct napi_struct *napi) { @@ -3621,86 +4234,209 @@ int netdev_rx_handler_register(struct net_device *dev, void netdev_rx_handler_unregister(struct net_device *dev); bool dev_valid_name(const char *name); +static inline bool is_socket_ioctl_cmd(unsigned int cmd) +{ + return _IOC_TYPE(cmd) == SOCK_IOC_TYPE; +} +int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg); +int put_user_ifreq(struct ifreq *ifr, void __user *arg); int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, - bool *need_copyout); -int dev_ifconf(struct net *net, struct ifconf *, int); -int dev_ethtool(struct net *net, struct ifreq *); -unsigned int dev_get_flags(const struct net_device *); + void __user *data, bool *need_copyout); +int dev_ifconf(struct net *net, struct ifconf __user *ifc); +int dev_eth_ioctl(struct net_device *dev, + struct ifreq *ifr, unsigned int cmd); +int generic_hwtstamp_get_lower(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_cfg); +int generic_hwtstamp_set_lower(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_cfg, + struct netlink_ext_ack *extack); +int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); +unsigned int netif_get_flags(const struct net_device *dev); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); +int netif_change_flags(struct net_device *dev, unsigned int flags, + struct netlink_ext_ack *extack); int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); -void __dev_notify_flags(struct net_device *, unsigned int old_flags, - unsigned int gchanges); -int dev_change_name(struct net_device *, const char *); +int netif_set_alias(struct net_device *dev, const char *alias, size_t len); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); -int dev_change_net_namespace(struct net_device *, struct net *, const char *); -int __dev_set_mtu(struct net_device *, int); -int dev_set_mtu_ext(struct net_device *dev, int mtu, - struct netlink_ext_ack *extack); +int __dev_change_net_namespace(struct net_device *dev, struct net *net, + const char *pat, int new_ifindex, + struct netlink_ext_ack *extack); +int dev_change_net_namespace(struct net_device *dev, struct net *net, + const char *pat); +int __netif_set_mtu(struct net_device *dev, int new_mtu); +int netif_set_mtu(struct net_device *dev, int new_mtu); int dev_set_mtu(struct net_device *, int); -int dev_change_tx_queue_len(struct net_device *, unsigned long); -void dev_set_group(struct net_device *, int); -int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, - struct netlink_ext_ack *extack); -int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, +int netif_pre_changeaddr_notify(struct net_device *dev, const char *addr, + struct netlink_ext_ack *extack); +int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss, + struct netlink_ext_ack *extack); +int dev_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss, struct netlink_ext_ack *extack); -int dev_change_carrier(struct net_device *, bool new_carrier); -int dev_get_phys_port_id(struct net_device *dev, - struct netdev_phys_item_id *ppid); -int dev_get_phys_port_name(struct net_device *dev, - char *name, size_t len); -int dev_change_proto_down(struct net_device *dev, bool proto_down); +int dev_set_mac_address_user(struct net_device *dev, struct sockaddr_storage *ss, + struct netlink_ext_ack *extack); +int netif_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); +int netif_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid, bool recurse); +bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); + 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 xdp_umem_query(struct net_device *dev, u16 queue_id); +int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +u8 dev_xdp_prog_count(struct net_device *dev); +int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); +int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); +u8 dev_xdp_sb_prog_count(struct net_device *dev); +u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); + +u32 dev_get_min_mp_channel_count(const struct net_device *dev); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); +int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb); +static __always_inline bool __is_skb_forwardable(const struct net_device *dev, + const struct sk_buff *skb, + const bool check_mtu) +{ + const u32 vlan_hdr_len = 4; /* VLAN_HLEN */ + unsigned int len; + + if (!(dev->flags & IFF_UP)) + return false; + + if (!check_mtu) + return true; + + len = dev->mtu + dev->hard_header_len + vlan_hdr_len; + if (skb->len <= len) + return true; + + /* if TSO is enabled, we don't care about the length as the packet + * could be forwarded without being segmented before + */ + if (skb_is_gso(skb)) + return true; + + return false; +} + +void netdev_core_stats_inc(struct net_device *dev, u32 offset); + +#define DEV_CORE_STATS_INC(FIELD) \ +static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ +{ \ + netdev_core_stats_inc(dev, \ + offsetof(struct net_device_core_stats, FIELD)); \ +} +DEV_CORE_STATS_INC(rx_dropped) +DEV_CORE_STATS_INC(tx_dropped) +DEV_CORE_STATS_INC(rx_nohandler) +DEV_CORE_STATS_INC(rx_otherhost_dropped) +#undef DEV_CORE_STATS_INC + static __always_inline int ____dev_forward_skb(struct net_device *dev, - struct sk_buff *skb) + struct sk_buff *skb, + const bool check_mtu) { if (skb_orphan_frags(skb, GFP_ATOMIC) || - unlikely(!is_skb_forwardable(dev, skb))) { - atomic_long_inc(&dev->rx_dropped); + unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) { + dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); return NET_RX_DROP; } - skb_scrub_packet(skb, true); + skb_scrub_packet(skb, !net_eq(dev_net(dev), dev_net(skb->dev))); skb->priority = 0; return 0; } -bool dev_nit_active(struct net_device *dev); +bool dev_nit_active_rcu(const struct net_device *dev); +static inline bool dev_nit_active(const struct net_device *dev) +{ + bool ret; + + rcu_read_lock(); + ret = dev_nit_active_rcu(dev); + rcu_read_unlock(); + return ret; +} + void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); -extern int netdev_budget; -extern unsigned int netdev_budget_usecs; +static inline void __dev_put(struct net_device *dev) +{ + if (dev) { +#ifdef CONFIG_PCPU_DEV_REFCNT + this_cpu_dec(*dev->pcpu_refcnt); +#else + refcount_dec(&dev->dev_refcnt); +#endif + } +} -/* Called by rtnetlink.c:rtnl_unlock() */ -void netdev_run_todo(void); +static inline void __dev_hold(struct net_device *dev) +{ + if (dev) { +#ifdef CONFIG_PCPU_DEV_REFCNT + this_cpu_inc(*dev->pcpu_refcnt); +#else + refcount_inc(&dev->dev_refcnt); +#endif + } +} -/** - * dev_put - release reference to device - * @dev: network device - * - * Release reference to device to allow it to be freed. +static inline void __netdev_tracker_alloc(struct net_device *dev, + netdevice_tracker *tracker, + gfp_t gfp) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); +#endif +} + +/* netdev_tracker_alloc() can upgrade a prior untracked reference + * taken by dev_get_by_name()/dev_get_by_index() to a tracked one. */ -static inline void dev_put(struct net_device *dev) +static inline void netdev_tracker_alloc(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) { - this_cpu_dec(*dev->pcpu_refcnt); +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + refcount_dec(&dev->refcnt_tracker.no_tracker); + __netdev_tracker_alloc(dev, tracker, gfp); +#endif +} + +static inline void netdev_tracker_free(struct net_device *dev, + netdevice_tracker *tracker) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_free(&dev->refcnt_tracker, tracker); +#endif +} + +static inline void netdev_hold(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) +{ + if (dev) { + __dev_hold(dev); + __netdev_tracker_alloc(dev, tracker, gfp); + } +} + +static inline void netdev_put(struct net_device *dev, + netdevice_tracker *tracker) +{ + if (dev) { + netdev_tracker_free(dev, tracker); + __dev_put(dev); + } } /** @@ -3708,10 +4444,40 @@ static inline void dev_put(struct net_device *dev) * @dev: network device * * Hold reference to device to keep it from being freed. + * Try using netdev_hold() instead. */ static inline void dev_hold(struct net_device *dev) { - this_cpu_inc(*dev->pcpu_refcnt); + netdev_hold(dev, NULL, GFP_ATOMIC); +} + +/** + * dev_put - release reference to device + * @dev: network device + * + * Release reference to device to allow it to be freed. + * Try using netdev_put() instead. + */ +static inline void dev_put(struct net_device *dev) +{ + netdev_put(dev, NULL); +} + +DEFINE_FREE(dev_put, struct net_device *, if (_T) dev_put(_T)) + +static inline void netdev_ref_replace(struct net_device *odev, + struct net_device *ndev, + netdevice_tracker *tracker, + gfp_t gfp) +{ + if (odev) + netdev_tracker_free(odev, tracker); + + __dev_hold(ndev); + __dev_put(odev); + + if (ndev) + __netdev_tracker_alloc(ndev, tracker, gfp); } /* Carrier loss detection, dial on demand. The functions netif_carrier_on @@ -3722,10 +4488,17 @@ static inline void dev_hold(struct net_device *dev) * called netif_lowerlayer_*() because they represent the state of any * kind of lower layer not just hardware media. */ - -void linkwatch_init_dev(struct net_device *dev); void linkwatch_fire_event(struct net_device *dev); -void linkwatch_forget_dev(struct net_device *dev); + +/** + * linkwatch_sync_dev - sync linkwatch for the given device + * @dev: network device to sync linkwatch for + * + * Sync linkwatch for the given device, removing it from the + * pending work list (if queued). + */ +void linkwatch_sync_dev(struct net_device *dev); +void __linkwatch_sync_dev(struct net_device *dev); /** * netif_carrier_ok - test if carrier present @@ -3740,11 +4513,11 @@ static inline bool netif_carrier_ok(const struct net_device *dev) unsigned long dev_trans_start(struct net_device *dev); -void __netdev_watchdog_up(struct net_device *dev); +void netdev_watchdog_up(struct net_device *dev); void netif_carrier_on(struct net_device *dev); - void netif_carrier_off(struct net_device *dev); +void netif_carrier_event(struct net_device *dev); /** * netif_dormant_on - mark device as dormant. @@ -3789,6 +4562,46 @@ static inline bool netif_dormant(const struct net_device *dev) /** + * 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 * @@ -3796,8 +4609,10 @@ static inline bool netif_dormant(const struct net_device *dev) */ static inline bool netif_oper_up(const struct net_device *dev) { - return (dev->operstate == IF_OPER_UP || - dev->operstate == IF_OPER_UNKNOWN /* backward compat */); + unsigned int operstate = READ_ONCE(dev->operstate); + + return operstate == IF_OPER_UP || + operstate == IF_OPER_UNKNOWN /* backward compat */; } /** @@ -3806,7 +4621,7 @@ static inline bool netif_oper_up(const struct net_device *dev) * * Check if device has not been removed from system. */ -static inline bool netif_device_present(struct net_device *dev) +static inline bool netif_device_present(const struct net_device *dev) { return test_bit(__LINK_STATE_PRESENT, &dev->state); } @@ -3820,22 +4635,48 @@ void netif_device_attach(struct net_device *dev); */ 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) @@ -3861,13 +4702,14 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) if (debug_value == 0) /* no output */ return 0; /* set low N bits */ - return (1 << debug_value) - 1; + return (1U << debug_value) - 1; } 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) @@ -3884,33 +4726,51 @@ static inline void __netif_tx_release(struct netdev_queue *txq) 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); } -static inline void txq_trans_update(struct netdev_queue *txq) +/* + * txq->trans_start can be read locklessly from dev_watchdog() + */ +static inline void txq_trans_update(const struct net_device *dev, + struct netdev_queue *txq) { - if (txq->xmit_lock_owner != -1) - txq->trans_start = jiffies; + if (!dev->lltx) + WRITE_ONCE(txq->trans_start, jiffies); +} + +static inline void txq_trans_cond_update(struct netdev_queue *txq) +{ + unsigned long now = jiffies; + + if (READ_ONCE(txq->trans_start) != now) + WRITE_ONCE(txq->trans_start, now); } /* legacy drivers only, netdev_start_xmit() sets txq->trans_start */ @@ -3918,8 +4778,7 @@ static inline void netif_trans_update(struct net_device *dev) { struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); - if (txq->trans_start != jiffies) - txq->trans_start = jiffies; + txq_trans_cond_update(txq); } /** @@ -3928,27 +4787,7 @@ static inline void netif_trans_update(struct net_device *dev) * * Get network device transmit lock */ -static inline void netif_tx_lock(struct net_device *dev) -{ - unsigned int i; - int cpu; - - spin_lock(&dev->tx_global_lock); - cpu = smp_processor_id(); - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - - /* We are the only thread of execution doing a - * freeze, but we have to grab the _xmit_lock in - * order to synchronize with threads which are in - * the ->hard_start_xmit() handler and already - * checked the frozen bit. - */ - __netif_tx_lock(txq, cpu); - set_bit(__QUEUE_STATE_FROZEN, &txq->state); - __netif_tx_unlock(txq); - } -} +void netif_tx_lock(struct net_device *dev); static inline void netif_tx_lock_bh(struct net_device *dev) { @@ -3956,22 +4795,7 @@ static inline void netif_tx_lock_bh(struct net_device *dev) netif_tx_lock(dev); } -static inline void netif_tx_unlock(struct net_device *dev) -{ - unsigned int i; - - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - - /* No need to grab the _xmit_lock here. If the - * queue is not stopped for another reason, we - * force a schedule. - */ - clear_bit(__QUEUE_STATE_FROZEN, &txq->state); - netif_schedule_queue(txq); - } - spin_unlock(&dev->tx_global_lock); -} +void netif_tx_unlock(struct net_device *dev); static inline void netif_tx_unlock_bh(struct net_device *dev) { @@ -3980,7 +4804,7 @@ static inline void netif_tx_unlock_bh(struct net_device *dev) } #define HARD_TX_LOCK(dev, txq, cpu) { \ - if ((dev->features & NETIF_F_LLTX) == 0) { \ + if (!(dev)->lltx) { \ __netif_tx_lock(txq, cpu); \ } else { \ __netif_tx_acquire(txq); \ @@ -3988,12 +4812,12 @@ static inline void netif_tx_unlock_bh(struct net_device *dev) } #define HARD_TX_TRYLOCK(dev, txq) \ - (((dev->features & NETIF_F_LLTX) == 0) ? \ + (!(dev)->lltx ? \ __netif_tx_trylock(txq) : \ __netif_tx_acquire(txq)) #define HARD_TX_UNLOCK(dev, txq) { \ - if ((dev->features & NETIF_F_LLTX) == 0) { \ + if (!(dev)->lltx) { \ __netif_tx_unlock(txq); \ } else { \ __netif_tx_release(txq); \ @@ -4007,6 +4831,7 @@ static inline void netif_tx_disable(struct net_device *dev) local_bh_disable(); cpu = smp_processor_id(); + spin_lock(&dev->tx_global_lock); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); @@ -4014,27 +4839,29 @@ static inline void netif_tx_disable(struct net_device *dev) netif_tx_stop_queue(txq); __netif_tx_unlock(txq); } + spin_unlock(&dev->tx_global_lock); local_bh_enable(); } static inline void netif_addr_lock(struct net_device *dev) { - spin_lock(&dev->addr_list_lock); -} - -static inline void netif_addr_lock_nested(struct net_device *dev) -{ - int subclass = SINGLE_DEPTH_NESTING; + unsigned char nest_level = 0; - if (dev->netdev_ops->ndo_get_lock_subclass) - subclass = dev->netdev_ops->ndo_get_lock_subclass(dev); - - spin_lock_nested(&dev->addr_list_lock, subclass); +#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) @@ -4058,14 +4885,14 @@ static inline void netif_addr_unlock_bh(struct net_device *dev) void ether_setup(struct net_device *dev); +/* Allocate dummy net_device */ +struct net_device *alloc_netdev_dummy(int sizeof_priv); + /* Support for loadable net-drivers */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, 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) @@ -4076,9 +4903,14 @@ int dev_get_valid_name(struct net *net, struct net_device *dev, 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); +int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, @@ -4103,12 +4935,24 @@ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ +void dev_addr_mod(struct net_device *dev, unsigned int offset, + const void *addr, size_t len); + +static inline void +__dev_addr_set(struct net_device *dev, const void *addr, size_t len) +{ + dev_addr_mod(dev, 0, addr, len); +} + +static inline void dev_addr_set(struct net_device *dev, const u8 *addr) +{ + __dev_addr_set(dev, addr, dev->addr_len); +} + int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); -void dev_addr_flush(struct net_device *dev); -int dev_addr_init(struct net_device *dev); /* Functions used for unicast addresses handling */ int dev_uc_add(struct net_device *dev, const unsigned char *addr); @@ -4121,7 +4965,7 @@ void dev_uc_flush(struct net_device *dev); void dev_uc_init(struct net_device *dev); /** - * __dev_uc_sync - Synchonize device's unicast list + * __dev_uc_sync - Synchronize device's unicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed @@ -4165,7 +5009,7 @@ void dev_mc_flush(struct net_device *dev); void dev_mc_init(struct net_device *dev); /** - * __dev_mc_sync - Synchonize device's multicast list + * __dev_mc_sync - Synchronize device's multicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed @@ -4198,10 +5042,13 @@ static inline void __dev_mc_unsync(struct net_device *dev, /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); -void __dev_set_rx_mode(struct net_device *dev); +int netif_set_promiscuity(struct net_device *dev, int inc); int dev_set_promiscuity(struct net_device *dev, int inc); +int netif_set_allmulti(struct net_device *dev, int inc, bool notify); int dev_set_allmulti(struct net_device *dev, int inc); +void netif_state_change(struct net_device *dev); void netdev_state_change(struct net_device *dev); +void __netdev_notify_peers(struct net_device *dev); void netdev_notify_peers(struct net_device *dev); void netdev_features_change(struct net_device *dev); /* Load a device via the kmod */ @@ -4210,20 +5057,29 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, 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); +void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); + +enum { + NESTED_SYNC_IMM_BIT, + NESTED_SYNC_TODO_BIT, +}; -extern int netdev_max_backlog; -extern int netdev_tstamp_prequeue; -extern int weight_p; -extern int dev_weight_rx_bias; -extern int dev_weight_tx_bias; -extern int dev_rx_weight; -extern int dev_tx_weight; +#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); /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ @@ -4234,8 +5090,8 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, 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); @@ -4268,19 +5124,16 @@ void *netdev_lower_get_next(struct net_device *dev, ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) -struct net_device *netdev_all_lower_get_next(struct net_device *dev, +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); -struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, - 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); @@ -4294,6 +5147,16 @@ int netdev_master_upper_dev_link(struct net_device *dev, struct netlink_ext_ack *extack); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); +int netdev_adjacent_change_prepare(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev, + struct netlink_ext_ack *extack); +void netdev_adjacent_change_commit(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev); +void netdev_adjacent_change_abort(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); @@ -4305,17 +5168,11 @@ void netdev_lower_state_changed(struct net_device *lower_dev, extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); -int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); int skb_crc32c_csum_help(struct sk_buff *skb); int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features); -struct sk_buff *__skb_gso_segment(struct sk_buff *skb, - netdev_features_t features, bool tx_path); -struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, - netdev_features_t features); - struct netdev_bonding_info { ifslave slave; ifbond master; @@ -4329,11 +5186,14 @@ struct netdev_notifier_bonding_info { void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info); -static inline -struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) +#if IS_ENABLED(CONFIG_ETHTOOL_NETLINK) +void ethtool_notify(struct net_device *dev, unsigned int cmd); +#else +static inline void ethtool_notify(struct net_device *dev, unsigned int cmd) { - return __skb_gso_segment(skb, features, true); } +#endif + __be16 skb_network_protocol(struct sk_buff *skb, int *depth); static inline bool can_checksum_protocol(netdev_features_t features, @@ -4371,17 +5231,45 @@ static inline void netdev_rx_csum_fault(struct net_device *dev, void net_enable_timestamp(void); void net_disable_timestamp(void); -#ifdef CONFIG_PROC_FS -int __init dev_proc_init(void); +static inline ktime_t netdev_get_tstamp(struct net_device *dev, + const struct skb_shared_hwtstamps *hwtstamps, + bool cycles) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_get_tstamp) + return ops->ndo_get_tstamp(dev, hwtstamps, cycles); + + return hwtstamps->hwtstamp; +} + +#ifndef CONFIG_PREEMPT_RT +static inline void netdev_xmit_set_more(bool more) +{ + __this_cpu_write(softnet_data.xmit.more, more); +} + +static inline bool netdev_xmit_more(void) +{ + return __this_cpu_read(softnet_data.xmit.more); +} #else -#define dev_proc_init() 0 +static inline void netdev_xmit_set_more(bool more) +{ + current->net_xmit.more = more; +} + +static inline bool netdev_xmit_more(void) +{ + return current->net_xmit.more; +} #endif static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, bool more) { - skb->xmit_more = more ? 1 : 0; + netdev_xmit_set_more(more); return ops->ndo_start_xmit(skb, dev); } @@ -4393,7 +5281,7 @@ static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_devi rc = __netdev_start_xmit(ops, skb, dev, more); if (rc == NETDEV_TX_OK) - txq_trans_update(txq); + txq_trans_update(dev, txq); return rc; } @@ -4403,22 +5291,10 @@ int netdev_class_create_file_ns(const struct class_attribute *class_attr, 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); -void linkwatch_run_queue(void); - static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { @@ -4453,6 +5329,7 @@ static inline netdev_features_t netdev_add_tso_features(netdev_features_t featur int __netdev_update_features(struct net_device *dev); void netdev_update_features(struct net_device *dev); void netdev_change_features(struct net_device *dev); +void netdev_compute_master_upper_features(struct net_device *dev, bool update_header); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); @@ -4461,16 +5338,22 @@ netdev_features_t passthru_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); netdev_features_t netif_skb_features(struct sk_buff *skb); +void skb_warn_bad_offload(const struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) { - netdev_features_t feature = (netdev_features_t)gso_type << NETIF_F_GSO_SHIFT; + netdev_features_t feature; + + if (gso_type & (SKB_GSO_TCP_FIXEDID | SKB_GSO_TCP_FIXEDID_INNER)) + gso_type |= __SKB_GSO_TCP_FIXEDID; + + feature = ((netdev_features_t)gso_type << NETIF_F_GSO_SHIFT) & NETIF_F_GSO_MASK; /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); - BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(__SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT)); @@ -4485,6 +5368,9 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) 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)); + BUILD_BUG_ON(SKB_GSO_TCP_ACCECN != + (NETIF_F_GSO_ACCECN >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } @@ -4503,23 +5389,27 @@ static inline bool netif_needs_gso(struct sk_buff *skb, (skb->ip_summed != CHECKSUM_UNNECESSARY))); } -static inline void netif_set_gso_max_size(struct net_device *dev, - unsigned int size) +void netif_set_tso_max_size(struct net_device *dev, unsigned int size); +void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs); +void netif_inherit_tso_max(struct net_device *to, + const struct net_device *from); + +static inline unsigned int +netif_get_gro_max_size(const struct net_device *dev, const struct sk_buff *skb) { - dev->gso_max_size = size; + /* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */ + return skb->protocol == htons(ETH_P_IPV6) ? + READ_ONCE(dev->gro_max_size) : + READ_ONCE(dev->gro_ipv4_max_size); } -static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, - int pulled_hlen, u16 mac_offset, - int mac_len) +static inline unsigned int +netif_get_gso_max_size(const struct net_device *dev, const struct sk_buff *skb) { - skb->protocol = protocol; - skb->encapsulation = 1; - skb_push(skb, pulled_hlen); - skb_reset_transport_header(skb); - skb->mac_header = mac_offset; - skb->network_header = skb->mac_header + mac_len; - skb->mac_len = mac_len; + /* pairs with WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ + return skb->protocol == htons(ETH_P_IPV6) ? + READ_ONCE(dev->gso_max_size) : + READ_ONCE(dev->gso_ipv4_max_size); } static inline bool netif_is_macsec(const struct net_device *dev) @@ -4552,6 +5442,11 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_has_l3_rx_handler(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_RX_HANDLER; +} + static inline bool netif_is_l3_master(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_MASTER; @@ -4562,6 +5457,15 @@ static inline bool netif_is_l3_slave(const struct net_device *dev) return dev->priv_flags & IFF_L3MDEV_SLAVE; } +static inline int dev_sdif(const struct net_device *dev) +{ +#ifdef CONFIG_NET_L3_MASTER_DEV + if (netif_is_l3_slave(dev)) + return dev->ifindex; +#endif + return 0; +} + static inline bool netif_is_bridge_master(const struct net_device *dev) { return dev->priv_flags & IFF_EBRIDGE; @@ -4582,6 +5486,16 @@ static inline bool netif_is_ovs_port(const struct net_device *dev) return dev->priv_flags & IFF_OVS_DATAPATH; } +static inline bool netif_is_any_bridge_master(const struct net_device *dev) +{ + return netif_is_bridge_master(dev) || netif_is_ovs_master(dev); +} + +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; @@ -4627,7 +5541,7 @@ static inline void netif_keep_dst(struct net_device *dev) static inline bool netif_reduces_vlan_mtu(struct net_device *dev) { /* TODO: reserve and use an additional IFF bit, if we get more users */ - return dev->priv_flags & IFF_MACSEC; + return netif_is_macsec(dev); } extern struct pernet_operations __net_initdata loopback_net_ops; @@ -4643,14 +5557,11 @@ static inline const char *netdev_name(const struct net_device *dev) return dev->name; } -static inline bool netdev_unregistering(const struct net_device *dev) -{ - return dev->reg_state == NETREG_UNREGISTERING; -} - static inline const char *netdev_reg_state(const struct net_device *dev) { - switch (dev->reg_state) { + u8 reg_state = READ_ONCE(dev->reg_state); + + switch (reg_state) { case NETREG_UNINITIALIZED: return " (uninitialized)"; case NETREG_REGISTERED: return ""; case NETREG_UNREGISTERING: return " (unregistering)"; @@ -4659,84 +5570,13 @@ static inline const char *netdev_reg_state(const struct net_device *dev) case NETREG_DUMMY: return " (dummy)"; } - WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, dev->reg_state); + WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, reg_state); return " (unknown)"; } -__printf(3, 4) -void netdev_printk(const char *level, const struct net_device *dev, - const char *format, ...); -__printf(2, 3) -void netdev_emerg(const struct net_device *dev, const char *format, ...); -__printf(2, 3) -void netdev_alert(const struct net_device *dev, const char *format, ...); -__printf(2, 3) -void netdev_crit(const struct net_device *dev, const char *format, ...); -__printf(2, 3) -void netdev_err(const struct net_device *dev, const char *format, ...); -__printf(2, 3) -void netdev_warn(const struct net_device *dev, const char *format, ...); -__printf(2, 3) -void netdev_notice(const struct net_device *dev, const char *format, ...); -__printf(2, 3) -void netdev_info(const struct net_device *dev, const char *format, ...); - -#define netdev_level_once(level, dev, fmt, ...) \ -do { \ - static bool __print_once __read_mostly; \ - \ - if (!__print_once) { \ - __print_once = true; \ - netdev_printk(level, dev, fmt, ##__VA_ARGS__); \ - } \ -} while (0) - -#define netdev_emerg_once(dev, fmt, ...) \ - netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__) -#define netdev_alert_once(dev, fmt, ...) \ - netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__) -#define netdev_crit_once(dev, fmt, ...) \ - netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__) -#define netdev_err_once(dev, fmt, ...) \ - netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__) -#define netdev_warn_once(dev, fmt, ...) \ - netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__) -#define netdev_notice_once(dev, fmt, ...) \ - netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__) -#define netdev_info_once(dev, fmt, ...) \ - netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__) - #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) -#if defined(CONFIG_DYNAMIC_DEBUG) -#define netdev_dbg(__dev, format, args...) \ -do { \ - dynamic_netdev_dbg(__dev, format, ##args); \ -} while (0) -#elif defined(DEBUG) -#define netdev_dbg(__dev, format, args...) \ - netdev_printk(KERN_DEBUG, __dev, format, ##args) -#else -#define netdev_dbg(__dev, format, args...) \ -({ \ - if (0) \ - netdev_printk(KERN_DEBUG, __dev, format, ##args); \ -}) -#endif - -#if defined(VERBOSE_DEBUG) -#define netdev_vdbg netdev_dbg -#else - -#define netdev_vdbg(dev, format, args...) \ -({ \ - if (0) \ - netdev_printk(KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - /* * netdev_WARN() acts like dev_printk(), but with the key difference * of using a WARN/WARN_ON to get the message out, including the @@ -4750,73 +5590,6 @@ do { \ WARN_ONCE(1, "netdevice: %s%s: " format, netdev_name(dev), \ netdev_reg_state(dev), ##args) -/* netif printk helpers, similar to netdev_printk */ - -#define netif_printk(priv, type, level, dev, fmt, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - netdev_printk(level, (dev), fmt, ##args); \ -} while (0) - -#define netif_level(level, priv, type, dev, fmt, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - netdev_##level(dev, fmt, ##args); \ -} while (0) - -#define netif_emerg(priv, type, dev, fmt, args...) \ - netif_level(emerg, priv, type, dev, fmt, ##args) -#define netif_alert(priv, type, dev, fmt, args...) \ - netif_level(alert, priv, type, dev, fmt, ##args) -#define netif_crit(priv, type, dev, fmt, args...) \ - netif_level(crit, priv, type, dev, fmt, ##args) -#define netif_err(priv, type, dev, fmt, args...) \ - netif_level(err, priv, type, dev, fmt, ##args) -#define netif_warn(priv, type, dev, fmt, args...) \ - netif_level(warn, priv, type, dev, fmt, ##args) -#define netif_notice(priv, type, dev, fmt, args...) \ - netif_level(notice, priv, type, dev, fmt, ##args) -#define netif_info(priv, type, dev, fmt, args...) \ - netif_level(info, priv, type, dev, fmt, ##args) - -#if defined(CONFIG_DYNAMIC_DEBUG) -#define netif_dbg(priv, type, netdev, format, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - dynamic_netdev_dbg(netdev, format, ##args); \ -} while (0) -#elif defined(DEBUG) -#define netif_dbg(priv, type, dev, format, args...) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args) -#else -#define netif_dbg(priv, type, dev, format, args...) \ -({ \ - if (0) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - -/* if @cond then downgrade to debug, else print at @level */ -#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \ - do { \ - if (cond) \ - netif_dbg(priv, type, netdev, fmt, ##args); \ - else \ - netif_ ## level(priv, type, netdev, fmt, ##args); \ - } while (0) - -#if defined(VERBOSE_DEBUG) -#define netif_vdbg netif_dbg -#else -#define netif_vdbg(priv, type, dev, format, args...) \ -({ \ - if (0) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - /* * The list of packet types we will receive (as opposed to discard) * and the routines to invoke. @@ -4839,4 +5612,14 @@ do { \ #define PTYPE_HASH_SIZE (16) #define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) +extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; + +extern struct net_device *blackhole_netdev; + +/* Note: Avoid these macros in fast path, prefer per-cpu or per-queue counters. */ +#define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD) +#define DEV_STATS_ADD(DEV, FIELD, VAL) \ + atomic_long_add((VAL), &(DEV)->stats.__##FIELD) +#define DEV_STATS_READ(DEV, FIELD) atomic_long_read(&(DEV)->stats.__##FIELD) + #endif /* _LINUX_NETDEVICE_H */ |