diff options
Diffstat (limited to 'include/linux/skbuff.h')
| -rw-r--r-- | include/linux/skbuff.h | 342 |
1 files changed, 268 insertions, 74 deletions
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f69b3f914fb..08074a810164 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -32,13 +32,85 @@ #include <linux/hrtimer.h> #include <linux/dma-mapping.h> #include <linux/netdev_features.h> +#include <linux/sched.h> #include <net/flow_keys.h> +/* A. Checksumming of received packets by device. + * + * CHECKSUM_NONE: + * + * Device failed to checksum this packet e.g. due to lack of capabilities. + * The packet contains full (though not verified) checksum in packet but + * not in skb->csum. Thus, skb->csum is undefined in this case. + * + * CHECKSUM_UNNECESSARY: + * + * The hardware you're dealing with doesn't calculate the full checksum + * (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums + * for specific protocols e.g. TCP/UDP/SCTP, then, for such packets it will + * set CHECKSUM_UNNECESSARY if their checksums are okay. skb->csum is still + * undefined in this case though. It is a bad option, but, unfortunately, + * nowadays most vendors do this. Apparently with the secret goal to sell + * you new devices, when you will add new protocol to your host, f.e. IPv6 8) + * + * CHECKSUM_COMPLETE: + * + * This is the most generic way. The device supplied checksum of the _whole_ + * packet as seen by netif_rx() and fills out in skb->csum. Meaning, the + * hardware doesn't need to parse L3/L4 headers to implement this. + * + * Note: Even if device supports only some protocols, but is able to produce + * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. + * + * CHECKSUM_PARTIAL: + * + * This is identical to the case for output below. This may occur on a packet + * received directly from another Linux OS, e.g., a virtualized Linux kernel + * on the same host. The packet can be treated in the same way as + * CHECKSUM_UNNECESSARY, except that on output (i.e., forwarding) the + * checksum must be filled in by the OS or the hardware. + * + * B. Checksumming on output. + * + * CHECKSUM_NONE: + * + * The skb was already checksummed by the protocol, or a checksum is not + * required. + * + * CHECKSUM_PARTIAL: + * + * The device is required to checksum the packet as seen by hard_start_xmit() + * from skb->csum_start up to the end, and to record/write the checksum at + * offset skb->csum_start + skb->csum_offset. + * + * The device must show its capabilities in dev->features, set up at device + * setup time, e.g. netdev_features.h: + * + * NETIF_F_HW_CSUM - It's a clever device, it's able to checksum everything. + * NETIF_F_IP_CSUM - Device is dumb, it's able to checksum only TCP/UDP over + * IPv4. Sigh. Vendors like this way for an unknown reason. + * Though, see comment above about CHECKSUM_UNNECESSARY. 8) + * NETIF_F_IPV6_CSUM - About as dumb as the last one but does IPv6 instead. + * NETIF_F_... - Well, you get the picture. + * + * CHECKSUM_UNNECESSARY: + * + * Normally, the device will do per protocol specific checksumming. Protocol + * implementations that do not want the NIC to perform the checksum + * calculation should use this flag in their outgoing skbs. + * + * NETIF_F_FCOE_CRC - This indicates that the device can do FCoE FC CRC + * offload. Correspondingly, the FCoE protocol driver + * stack should use CHECKSUM_UNNECESSARY. + * + * Any questions? No questions, good. --ANK + */ + /* Don't change this without changing skb_csum_unnecessary! */ -#define CHECKSUM_NONE 0 -#define CHECKSUM_UNNECESSARY 1 -#define CHECKSUM_COMPLETE 2 -#define CHECKSUM_PARTIAL 3 +#define CHECKSUM_NONE 0 +#define CHECKSUM_UNNECESSARY 1 +#define CHECKSUM_COMPLETE 2 +#define CHECKSUM_PARTIAL 3 #define SKB_DATA_ALIGN(X) (((X) + (SMP_CACHE_BYTES - 1)) & \ ~(SMP_CACHE_BYTES - 1)) @@ -54,58 +126,6 @@ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) -/* A. Checksumming of received packets by device. - * - * NONE: device failed to checksum this packet. - * skb->csum is undefined. - * - * UNNECESSARY: device parsed packet and wouldbe verified checksum. - * skb->csum is undefined. - * It is bad option, but, unfortunately, many of vendors do this. - * Apparently with secret goal to sell you new device, when you - * will add new protocol to your host. F.e. IPv6. 8) - * - * COMPLETE: the most generic way. Device supplied checksum of _all_ - * the packet as seen by netif_rx in skb->csum. - * NOTE: Even if device supports only some protocols, but - * is able to produce some skb->csum, it MUST use COMPLETE, - * not UNNECESSARY. - * - * PARTIAL: identical to the case for output below. This may occur - * on a packet received directly from another Linux OS, e.g., - * a virtualised Linux kernel on the same host. The packet can - * be treated in the same way as UNNECESSARY except that on - * output (i.e., forwarding) the checksum must be filled in - * by the OS or the hardware. - * - * B. Checksumming on output. - * - * NONE: skb is checksummed by protocol or csum is not required. - * - * PARTIAL: device is required to csum packet as seen by hard_start_xmit - * from skb->csum_start to the end and to record the checksum - * at skb->csum_start + skb->csum_offset. - * - * Device must show its capabilities in dev->features, set - * at device setup time. - * NETIF_F_HW_CSUM - it is clever device, it is able to checksum - * everything. - * NETIF_F_IP_CSUM - device is dumb. It is able to csum only - * TCP/UDP over IPv4. Sigh. Vendors like this - * way by an unknown reason. Though, see comment above - * about CHECKSUM_UNNECESSARY. 8) - * NETIF_F_IPV6_CSUM about as dumb as the last one but does IPv6 instead. - * - * UNNECESSARY: device will do per protocol specific csum. Protocol drivers - * that do not want net to perform the checksum calculation should use - * this flag in their outgoing skbs. - * NETIF_F_FCOE_CRC this indicates the device can do FCoE FC CRC - * offload. Correspondingly, the FCoE protocol driver - * stack should use CHECKSUM_UNNECESSARY. - * - * Any questions? No questions, good. --ANK - */ - struct net_device; struct scatterlist; struct pipe_inode_info; @@ -337,11 +357,62 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +/** + * struct skb_mstamp - multi resolution time stamps + * @stamp_us: timestamp in us resolution + * @stamp_jiffies: timestamp in jiffies + */ +struct skb_mstamp { + union { + u64 v64; + struct { + u32 stamp_us; + u32 stamp_jiffies; + }; + }; +}; + +/** + * skb_mstamp_get - get current timestamp + * @cl: place to store timestamps + */ +static inline void skb_mstamp_get(struct skb_mstamp *cl) +{ + u64 val = local_clock(); + + do_div(val, NSEC_PER_USEC); + cl->stamp_us = (u32)val; + cl->stamp_jiffies = (u32)jiffies; +} + +/** + * skb_mstamp_delta - compute the difference in usec between two skb_mstamp + * @t1: pointer to newest sample + * @t0: pointer to oldest sample + */ +static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, + const struct skb_mstamp *t0) +{ + s32 delta_us = t1->stamp_us - t0->stamp_us; + u32 delta_jiffies = t1->stamp_jiffies - t0->stamp_jiffies; + + /* If delta_us is negative, this might be because interval is too big, + * or local_clock() drift is too big : fallback using jiffies. + */ + if (delta_us <= 0 || + delta_jiffies >= (INT_MAX / (USEC_PER_SEC / HZ))) + + delta_us = jiffies_to_usecs(delta_jiffies); + + return delta_us; +} + + /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list - * @tstamp: Time we arrived + * @tstamp: Time we arrived/left * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by * @cb: Control buffer. Free for use by every layer. Put private vars here @@ -373,11 +444,11 @@ typedef unsigned char *sk_buff_data_t; * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @tc_verd: traffic control verdict - * @rxhash: the packet hash computed on receive + * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed - * @l4_rxhash: indicate rxhash is a canonical 4-tuple hash over transport + * @l4_hash: indicate hash is a canonical 4-tuple hash over transport * ports. * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not @@ -410,7 +481,10 @@ struct sk_buff { struct sk_buff *next; struct sk_buff *prev; - ktime_t tstamp; + union { + ktime_t tstamp; + struct skb_mstamp skb_mstamp; + }; struct sock *sk; struct net_device *dev; @@ -463,7 +537,7 @@ struct sk_buff { int skb_iif; - __u32 rxhash; + __u32 hash; __be16 vlan_proto; __u16 vlan_tci; @@ -482,7 +556,7 @@ struct sk_buff { #endif __u8 pfmemalloc:1; __u8 ooo_okay:1; - __u8 l4_rxhash:1; + __u8 l4_hash:1; __u8 wifi_acked_valid:1; __u8 wifi_acked:1; __u8 no_fcs:1; @@ -672,6 +746,8 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); +int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len); int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); @@ -703,15 +779,78 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config, struct ts_state *state); -void __skb_get_rxhash(struct sk_buff *skb); -static inline __u32 skb_get_rxhash(struct sk_buff *skb) +/* + * Packet hash types specify the type of hash in skb_set_hash. + * + * Hash types refer to the protocol layer addresses which are used to + * construct a packet's hash. The hashes are used to differentiate or identify + * flows of the protocol layer for the hash type. Hash types are either + * layer-2 (L2), layer-3 (L3), or layer-4 (L4). + * + * Properties of hashes: + * + * 1) Two packets in different flows have different hash values + * 2) Two packets in the same flow should have the same hash value + * + * A hash at a higher layer is considered to be more specific. A driver should + * set the most specific hash possible. + * + * A driver cannot indicate a more specific hash than the layer at which a hash + * was computed. For instance an L3 hash cannot be set as an L4 hash. + * + * A driver may indicate a hash level which is less specific than the + * actual layer the hash was computed on. For instance, a hash computed + * at L4 may be considered an L3 hash. This should only be done if the + * driver can't unambiguously determine that the HW computed the hash at + * the higher layer. Note that the "should" in the second property above + * permits this. + */ +enum pkt_hash_types { + PKT_HASH_TYPE_NONE, /* Undefined type */ + PKT_HASH_TYPE_L2, /* Input: src_MAC, dest_MAC */ + PKT_HASH_TYPE_L3, /* Input: src_IP, dst_IP */ + PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ +}; + +static inline void +skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) +{ + skb->l4_hash = (type == PKT_HASH_TYPE_L4); + skb->hash = hash; +} + +void __skb_get_hash(struct sk_buff *skb); +static inline __u32 skb_get_hash(struct sk_buff *skb) +{ + if (!skb->l4_hash) + __skb_get_hash(skb); + + return skb->hash; +} + +static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) +{ + return skb->hash; +} + +static inline void skb_clear_hash(struct sk_buff *skb) { - if (!skb->l4_rxhash) - __skb_get_rxhash(skb); + skb->hash = 0; + skb->l4_hash = 0; +} - return skb->rxhash; +static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) +{ + if (!skb->l4_hash) + skb_clear_hash(skb); } +static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) +{ + to->hash = from->hash; + to->l4_hash = from->l4_hash; +}; + #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { @@ -750,7 +889,7 @@ static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) */ static inline int skb_queue_empty(const struct sk_buff_head *list) { - return list->next == (struct sk_buff *)list; + return list->next == (const struct sk_buff *) list; } /** @@ -763,7 +902,7 @@ static inline int skb_queue_empty(const struct sk_buff_head *list) static inline bool skb_queue_is_last(const struct sk_buff_head *list, const struct sk_buff *skb) { - return skb->next == (struct sk_buff *)list; + return skb->next == (const struct sk_buff *) list; } /** @@ -776,7 +915,7 @@ static inline bool skb_queue_is_last(const struct sk_buff_head *list, static inline bool skb_queue_is_first(const struct sk_buff_head *list, const struct sk_buff *skb) { - return skb->prev == (struct sk_buff *)list; + return skb->prev == (const struct sk_buff *) list; } /** @@ -1956,7 +2095,7 @@ static inline void skb_propagate_pfmemalloc(struct page *page, } /** - * skb_frag_page - retrieve the page refered to by a paged fragment + * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * * Returns the &struct page associated with @frag. @@ -2368,9 +2507,13 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); +unsigned int skb_zerocopy_headlen(const struct sk_buff *from); +int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, + int len, int hlen); void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); +unsigned int skb_gso_transport_seglen(const struct sk_buff *skb); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct skb_checksum_ops { @@ -2397,6 +2540,24 @@ static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, return buffer; } +/** + * skb_needs_linearize - check if we need to linearize a given skb + * depending on the given device features. + * @skb: socket buffer to check + * @features: net device features + * + * Returns true if either: + * 1. skb has frag_list and the device doesn't support FRAGLIST, or + * 2. skb is fragmented and the device does not support SG. + */ +static inline bool skb_needs_linearize(struct sk_buff *skb, + netdev_features_t features) +{ + return skb_is_nonlinear(skb) && + ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || + (skb_shinfo(skb)->nr_frags && !(features & NETIF_F_SG))); +} + static inline void skb_copy_from_linear_data(const struct sk_buff *skb, void *to, const unsigned int len) @@ -2469,8 +2630,6 @@ static inline ktime_t net_invalid_timestamp(void) return ktime_set(0, 0); } -void skb_timestamping_init(void); - #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING void skb_clone_tx_timestamp(struct sk_buff *skb); @@ -2621,7 +2780,7 @@ static inline void nf_reset(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -2638,6 +2797,9 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src) dst->nf_bridge = src->nf_bridge; nf_bridge_get(src->nf_bridge); #endif +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) + dst->nf_trace = src->nf_trace; +#endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) @@ -2669,6 +2831,19 @@ static inline void skb_init_secmark(struct sk_buff *skb) { } #endif +static inline bool skb_irq_freeable(const struct sk_buff *skb) +{ + return !skb->destructor && +#if IS_ENABLED(CONFIG_XFRM) + !skb->sp && +#endif +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + !skb->nfct && +#endif + !skb->_skb_refdst && + !skb_has_frag_list(skb); +} + static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) { skb->queue_mapping = queue_mapping; @@ -2795,6 +2970,8 @@ static inline void skb_checksum_none_assert(const struct sk_buff *skb) bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); +int skb_checksum_setup(struct sk_buff *skb, bool recalculate); + u32 __skb_get_poff(const struct sk_buff *skb); /** @@ -2810,5 +2987,22 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } + +/** + * skb_gso_network_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_network_seglen is used to determine the real size of the + * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). + * + * The MAC/L2 header is not accounted for. + */ +static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - + skb_network_header(skb); + return hdr_len + skb_gso_transport_seglen(skb); +} #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ |