diff options
Diffstat (limited to 'include/linux/netdevice.h')
| -rw-r--r-- | include/linux/netdevice.h | 264 |
1 files changed, 202 insertions, 62 deletions
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 38377392d082..74fd5d37f15a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -30,6 +30,7 @@ #include <linux/bug.h> #include <linux/delay.h> #include <linux/atomic.h> +#include <linux/prefetch.h> #include <asm/cache.h> #include <asm/byteorder.h> @@ -543,7 +544,7 @@ struct netdev_queue { * read mostly part */ struct net_device *dev; - struct Qdisc *qdisc; + struct Qdisc __rcu *qdisc; struct Qdisc *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; @@ -997,6 +998,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * Callback to use for xmit over the accelerated station. This * is used in place of ndo_start_xmit on accelerated net * devices. + * bool (*ndo_gso_check) (struct sk_buff *skb, + * struct net_device *dev); + * Called by core transmit path to determine if device is capable of + * performing GSO on a packet. The device returns true if it is + * able to GSO the packet, false otherwise. If the return value is + * false the stack will do software GSO. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1146,6 +1153,8 @@ struct net_device_ops { struct net_device *dev, void *priv); int (*ndo_get_lock_subclass)(struct net_device *dev); + bool (*ndo_gso_check) (struct sk_buff *skb, + struct net_device *dev); }; /** @@ -1206,6 +1215,7 @@ enum netdev_priv_flags { IFF_SUPP_NOFCS = 1<<19, IFF_LIVE_ADDR_CHANGE = 1<<20, IFF_MACVLAN = 1<<21, + IFF_XMIT_DST_RELEASE_PERM = 1<<22, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1230,6 +1240,7 @@ enum netdev_priv_flags { #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 /** * struct net_device - The DEVICE structure. @@ -1416,6 +1427,8 @@ enum netdev_priv_flags { * @gso_max_size: Maximum size of generic segmentation offload * @gso_max_segs: Maximum number of segments that can be passed to the * NIC for GSO + * @gso_min_segs: Minimum number of segments that can be passed to the + * NIC for GSO * * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device @@ -1666,7 +1679,7 @@ struct net_device { unsigned int gso_max_size; #define GSO_MAX_SEGS 65535 u16 gso_max_segs; - + u16 gso_min_segs; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; #endif @@ -1747,6 +1760,12 @@ struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, return &dev->_tx[index]; } +static inline struct netdev_queue *skb_get_tx_queue(const struct net_device *dev, + const struct sk_buff *skb) +{ + return netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); +} + static inline void netdev_for_each_tx_queue(struct net_device *dev, void (*f)(struct net_device *, struct netdev_queue *, @@ -1781,24 +1800,13 @@ void dev_net_set(struct net_device *dev, struct net *net) #endif } -static inline bool netdev_uses_dsa_tags(struct net_device *dev) +static inline bool netdev_uses_dsa(struct net_device *dev) { -#ifdef CONFIG_NET_DSA_TAG_DSA - if (dev->dsa_ptr != NULL) - return dsa_uses_dsa_tags(dev->dsa_ptr); -#endif - - return 0; -} - -static inline bool netdev_uses_trailer_tags(struct net_device *dev) -{ -#ifdef CONFIG_NET_DSA_TAG_TRAILER +#if IS_ENABLED(CONFIG_NET_DSA) if (dev->dsa_ptr != NULL) - return dsa_uses_trailer_tags(dev->dsa_ptr); + return dsa_uses_tagged_protocol(dev->dsa_ptr); #endif - - return 0; + return false; } /** @@ -1879,11 +1887,20 @@ struct napi_gro_cb { /* jiffies when first packet was created/queued */ unsigned long age; - /* Used in ipv6_gro_receive() */ + /* Used in ipv6_gro_receive() and foo-over-udp */ u16 proto; /* Used in udp_gro_receive */ - u16 udp_mark; + u8 udp_mark:1; + + /* GRO checksum is valid */ + u8 csum_valid:1; + + /* Number of checksums via CHECKSUM_UNNECESSARY */ + u8 csum_cnt:3; + + /* Used in foo-over-udp, set in udp[46]_gro_receive */ + u8 is_ipv6:1; /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; @@ -1910,7 +1927,6 @@ struct packet_type { struct offload_callbacks { struct sk_buff *(*gso_segment)(struct sk_buff *skb, netdev_features_t features); - int (*gso_send_check)(struct sk_buff *skb); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb, int nhoff); @@ -1924,6 +1940,7 @@ struct packet_offload { struct udp_offload { __be16 port; + u8 ipproto; struct offload_callbacks callbacks; }; @@ -1982,6 +1999,7 @@ struct pcpu_sw_netstats { #define NETDEV_CHANGEUPPER 0x0015 #define NETDEV_RESEND_IGMP 0x0016 #define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */ +#define NETDEV_CHANGEINFODATA 0x0018 int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); @@ -2074,8 +2092,8 @@ void __dev_remove_pack(struct packet_type *pt); void dev_add_offload(struct packet_offload *po); void dev_remove_offload(struct packet_offload *po); -struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags, - unsigned short mask); +struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, + unsigned short mask); 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); @@ -2153,11 +2171,97 @@ static inline void *skb_gro_network_header(struct sk_buff *skb) static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { - if (skb->ip_summed == CHECKSUM_COMPLETE) + 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_gro_checksum_validate_needed(struct sk_buff *skb, + bool zero_okay, + __sum16 check) +{ + return (skb->ip_summed != CHECKSUM_PARTIAL && + 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_mark_checksum_bad(skb); \ + else \ + 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) + static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, @@ -2261,12 +2365,7 @@ static inline void input_queue_tail_incr_save(struct softnet_data *sd, DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); void __netif_schedule(struct Qdisc *q); - -static inline void netif_schedule_queue(struct netdev_queue *txq) -{ - if (!(txq->state & QUEUE_STATE_ANY_XOFF)) - __netif_schedule(txq->qdisc); -} +void netif_schedule_queue(struct netdev_queue *txq); static inline void netif_tx_schedule_all(struct net_device *dev) { @@ -2302,11 +2401,7 @@ static inline void netif_tx_start_all_queues(struct net_device *dev) } } -static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue) -{ - if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) - __netif_schedule(dev_queue->qdisc); -} +void netif_tx_wake_queue(struct netdev_queue *dev_queue); /** * netif_wake_queue - restart transmit @@ -2394,6 +2489,34 @@ netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue) return dev_queue->state & QUEUE_STATE_DRV_XOFF_OR_FROZEN; } +/** + * netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write + * @dev_queue: pointer to transmit queue + * + * BQL enabled drivers might use this helper in their ndo_start_xmit(), + * to give appropriate hint to the cpu. + */ +static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_queue) +{ +#ifdef CONFIG_BQL + prefetchw(&dev_queue->dql.num_queued); +#endif +} + +/** + * netdev_txq_bql_complete_prefetchw - prefetch bql data for write + * @dev_queue: pointer to transmit queue + * + * BQL enabled drivers might use this helper in their TX completion path, + * to give appropriate hint to the cpu. + */ +static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_queue) +{ +#ifdef CONFIG_BQL + prefetchw(&dev_queue->dql.limit); +#endif +} + static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, unsigned int bytes) { @@ -2578,19 +2701,7 @@ static inline bool netif_subqueue_stopped(const struct net_device *dev, return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb)); } -/** - * netif_wake_subqueue - allow sending packets on subqueue - * @dev: network device - * @queue_index: sub queue index - * - * Resume individual transmit queue of a device with multiple transmit queues. - */ -static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) -{ - struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); - if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) - __netif_schedule(txq->qdisc); -} +void netif_wake_subqueue(struct net_device *dev, u16 queue_index); #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, @@ -2754,8 +2865,9 @@ int dev_set_mac_address(struct net_device *, struct sockaddr *); int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_port_id *ppid); -int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq); +struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); +struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, + struct netdev_queue *txq, int *ret); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb); @@ -3176,7 +3288,7 @@ static inline int __dev_uc_sync(struct net_device *dev, } /** - * __dev_uc_unsync - Remove synchonized addresses from device + * __dev_uc_unsync - Remove synchronized addresses from device * @dev: device to sync * @unsync: function to call if address should be removed * @@ -3220,7 +3332,7 @@ static inline int __dev_mc_sync(struct net_device *dev, } /** - * __dev_mc_unsync - Remove synchonized addresses from device + * __dev_mc_unsync - Remove synchronized addresses from device * @dev: device to sync * @unsync: function to call if address should be removed * @@ -3357,6 +3469,27 @@ int __init dev_proc_init(void); #define dev_proc_init() 0 #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; + return ops->ndo_start_xmit(skb, dev); +} + +static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, + struct netdev_queue *txq, bool more) +{ + const struct net_device_ops *ops = dev->netdev_ops; + int rc; + + rc = __netdev_start_xmit(ops, skb, dev, more); + if (rc == NETDEV_TX_OK) + txq_trans_update(txq); + + return rc; +} + int netdev_class_create_file_ns(struct class_attribute *class_attr, const void *ns); void netdev_class_remove_file_ns(struct class_attribute *class_attr, @@ -3447,10 +3580,12 @@ static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features) (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST)); } -static inline bool netif_needs_gso(struct sk_buff *skb, +static inline bool netif_needs_gso(struct net_device *dev, struct sk_buff *skb, netdev_features_t features) { return skb_is_gso(skb) && (!skb_gso_ok(skb, features) || + (dev->netdev_ops->ndo_gso_check && + !dev->netdev_ops->ndo_gso_check(skb, dev)) || unlikely((skb->ip_summed != CHECKSUM_PARTIAL) && (skb->ip_summed != CHECKSUM_UNNECESSARY))); } @@ -3494,6 +3629,12 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +/* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ +static inline void netif_keep_dst(struct net_device *dev) +{ + dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM); +} + extern struct pernet_operations __net_initdata loopback_net_ops; /* Logging, debugging and troubleshooting/diagnostic helpers. */ @@ -3523,22 +3664,22 @@ static inline const char *netdev_reg_state(const struct net_device *dev) } __printf(3, 4) -int netdev_printk(const char *level, const struct net_device *dev, - const char *format, ...); +void netdev_printk(const char *level, const struct net_device *dev, + const char *format, ...); __printf(2, 3) -int netdev_emerg(const struct net_device *dev, const char *format, ...); +void netdev_emerg(const struct net_device *dev, const char *format, ...); __printf(2, 3) -int netdev_alert(const struct net_device *dev, const char *format, ...); +void netdev_alert(const struct net_device *dev, const char *format, ...); __printf(2, 3) -int netdev_crit(const struct net_device *dev, const char *format, ...); +void netdev_crit(const struct net_device *dev, const char *format, ...); __printf(2, 3) -int netdev_err(const struct net_device *dev, const char *format, ...); +void netdev_err(const struct net_device *dev, const char *format, ...); __printf(2, 3) -int netdev_warn(const struct net_device *dev, const char *format, ...); +void netdev_warn(const struct net_device *dev, const char *format, ...); __printf(2, 3) -int netdev_notice(const struct net_device *dev, const char *format, ...); +void netdev_notice(const struct net_device *dev, const char *format, ...); __printf(2, 3) -int netdev_info(const struct net_device *dev, const char *format, ...); +void netdev_info(const struct net_device *dev, const char *format, ...); #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) @@ -3556,7 +3697,6 @@ do { \ ({ \ if (0) \ netdev_printk(KERN_DEBUG, __dev, format, ##args); \ - 0; \ }) #endif |