diff options
Diffstat (limited to 'include/linux/skbuff.h')
| -rw-r--r-- | include/linux/skbuff.h | 307 |
1 files changed, 256 insertions, 51 deletions
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b974a277975a..2bcf78a4de7b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -274,7 +274,6 @@ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) -struct ahash_request; struct net_device; struct scatterlist; struct pipe_inode_info; @@ -481,9 +480,6 @@ enum { /* generate software time stamp on packet tx completion */ SKBTX_COMPLETION_TSTAMP = 1 << 3, - /* generate wifi status information (where possible) */ - SKBTX_WIFI_STATUS = 1 << 4, - /* determine hardware time stamp based on time or cycles */ SKBTX_HW_TSTAMP_NETDEV = 1 << 5, @@ -678,7 +674,7 @@ enum { /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 2, - SKB_GSO_TCP_FIXEDID = 1 << 3, + __SKB_GSO_TCP_FIXEDID = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, @@ -711,6 +707,12 @@ enum { SKB_GSO_FRAGLIST = 1 << 18, SKB_GSO_TCP_ACCECN = 1 << 19, + + /* These indirectly map onto the same netdev feature. + * If NETIF_F_TSO_MANGLEID is set it may mangle both inner and outer IDs. + */ + SKB_GSO_TCP_FIXEDID = 1 << 30, + SKB_GSO_TCP_FIXEDID_INNER = 1 << 31, }; #if BITS_PER_LONG > 32 @@ -1163,6 +1165,45 @@ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK); } +static inline void skb_dst_check_unset(struct sk_buff *skb) +{ + DEBUG_NET_WARN_ON_ONCE((skb->_skb_refdst & SKB_DST_PTRMASK) && + !(skb->_skb_refdst & SKB_DST_NOREF)); +} + +/** + * skb_dstref_steal() - return current dst_entry value and clear it + * @skb: buffer + * + * Resets skb dst_entry without adjusting its reference count. Useful in + * cases where dst_entry needs to be temporarily reset and restored. + * Note that the returned value cannot be used directly because it + * might contain SKB_DST_NOREF bit. + * + * When in doubt, prefer skb_dst_drop() over skb_dstref_steal() to correctly + * handle dst_entry reference counting. + * + * Returns: original skb dst_entry. + */ +static inline unsigned long skb_dstref_steal(struct sk_buff *skb) +{ + unsigned long refdst = skb->_skb_refdst; + + skb->_skb_refdst = 0; + return refdst; +} + +/** + * skb_dstref_restore() - restore skb dst_entry removed via skb_dstref_steal() + * @skb: buffer + * @refdst: dst entry from a call to skb_dstref_steal() + */ +static inline void skb_dstref_restore(struct sk_buff *skb, unsigned long refdst) +{ + skb_dst_check_unset(skb); + skb->_skb_refdst = refdst; +} + /** * skb_dst_set - sets skb dst * @skb: buffer @@ -1173,6 +1214,7 @@ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { + skb_dst_check_unset(skb); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst; } @@ -1189,6 +1231,7 @@ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) */ static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { + skb_dst_check_unset(skb); WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; @@ -1710,13 +1753,16 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, - struct ubuf_info *uarg); + struct ubuf_info *uarg, bool devmem); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); +struct net_devmem_dmabuf_binding; + int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, - size_t length); + size_t length, + struct net_devmem_dmabuf_binding *binding); int zerocopy_fill_skb_from_iter(struct sk_buff *skb, struct iov_iter *from, size_t length); @@ -1724,12 +1770,14 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb, static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { - return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len); + return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len, + NULL); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, - struct ubuf_info *uarg); + struct ubuf_info *uarg, + struct net_devmem_dmabuf_binding *binding); /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) @@ -2557,8 +2605,9 @@ static inline void skb_len_add(struct sk_buff *skb, int delta) * * Does not take any additional reference on the fragment. */ -static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, - netmem_ref netmem, int off, int size) +static __always_inline void +__skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, + int off, int size) { struct page *page; @@ -2580,14 +2629,16 @@ static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, skb->pfmemalloc = true; } -static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, - struct page *page, int off, int size) +static __always_inline void +__skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, + int off, int size) { __skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } -static inline void skb_fill_netmem_desc(struct sk_buff *skb, int i, - netmem_ref netmem, int off, int size) +static __always_inline void +skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, + int off, int size) { __skb_fill_netmem_desc(skb, i, netmem, off, size); skb_shinfo(skb)->nr_frags = i + 1; @@ -2607,8 +2658,9 @@ static inline void skb_fill_netmem_desc(struct sk_buff *skb, int i, * * Does not take any additional reference on the fragment. */ -static inline void skb_fill_page_desc(struct sk_buff *skb, int i, - struct page *page, int off, int size) +static __always_inline void +skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, + int off, int size) { skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } @@ -2634,8 +2686,17 @@ static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i, shinfo->nr_frags = i + 1; } -void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, - int off, int size, unsigned int truesize); +static inline void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, + netmem_ref netmem, int off, + int size, unsigned int truesize) +{ + DEBUG_NET_WARN_ON_ONCE(size > truesize); + + skb_fill_netmem_desc(skb, i, netmem, off, size); + skb->len += size; + skb->data_len += size; + skb->truesize += truesize; +} static inline void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, @@ -2765,12 +2826,13 @@ static inline void *__skb_push(struct sk_buff *skb, unsigned int len) DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->data -= len; + DEBUG_NET_WARN_ON_ONCE(skb->data < skb->head); skb->len += len; return skb->data; } void *skb_pull(struct sk_buff *skb, unsigned int len); -static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) +static __always_inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); @@ -2795,7 +2857,7 @@ void *skb_pull_data(struct sk_buff *skb, size_t len); void *__pskb_pull_tail(struct sk_buff *skb, int delta); -static inline enum skb_drop_reason +static __always_inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); @@ -2813,12 +2875,13 @@ pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) return SKB_NOT_DROPPED_YET; } -static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) +static __always_inline bool +pskb_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } -static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) +static __always_inline void *pskb_pull(struct sk_buff *skb, unsigned int len) { if (!pskb_may_pull(skb, len)) return NULL; @@ -3032,6 +3095,29 @@ static inline void skb_reset_transport_header(struct sk_buff *skb) skb->transport_header = offset; } +/** + * skb_reset_transport_header_careful - conditionally reset transport header + * @skb: buffer to alter + * + * Hardened version of skb_reset_transport_header(). + * + * Returns: true if the operation was a success. + */ +static inline bool __must_check +skb_reset_transport_header_careful(struct sk_buff *skb) +{ + long offset = skb->data - skb->head; + + if (unlikely(offset != (typeof(skb->transport_header))offset)) + return false; + + if (unlikely(offset == (typeof(skb->transport_header))~0U)) + return false; + + skb->transport_header = offset; + return true; +} + static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { @@ -3256,7 +3342,7 @@ static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) return 0; } -static inline int pskb_trim(struct sk_buff *skb, unsigned int len) +static __always_inline int pskb_trim(struct sk_buff *skb, unsigned int len) { skb_might_realloc(skb); return (len < skb->len) ? __pskb_trim(skb, len) : 0; @@ -3299,7 +3385,7 @@ static inline int __skb_grow(struct sk_buff *skb, unsigned int len) * destructor function and make the @skb unowned. The buffer continues * to exist but is no longer charged to its former owner. */ -static inline void skb_orphan(struct sk_buff *skb) +static __always_inline void skb_orphan(struct sk_buff *skb) { if (skb->destructor) { skb->destructor(skb); @@ -3664,7 +3750,13 @@ static inline void *skb_frag_address(const skb_frag_t *frag) */ static inline void *skb_frag_address_safe(const skb_frag_t *frag) { - void *ptr = page_address(skb_frag_page(frag)); + struct page *page = skb_frag_page(frag); + void *ptr; + + if (!page) + return NULL; + + ptr = page_address(page); if (unlikely(!ptr)) return NULL; @@ -3672,6 +3764,17 @@ static inline void *skb_frag_address_safe(const skb_frag_t *frag) } /** + * skb_frag_phys - gets the physical address of the data in a paged fragment + * @frag: the paged fragment buffer + * + * Returns: the physical address of the data within @frag. + */ +static inline phys_addr_t skb_frag_phys(const skb_frag_t *frag) +{ + return page_to_phys(skb_frag_page(frag)) + skb_frag_off(frag); +} + +/** * skb_frag_page_copy() - sets the page in a fragment from another fragment * @fragto: skb fragment where page is set * @fragfrom: skb fragment page is copied from @@ -3700,6 +3803,10 @@ static inline dma_addr_t __skb_frag_dma_map(struct device *dev, size_t offset, size_t size, enum dma_data_direction dir) { + if (skb_frag_is_net_iov(frag)) { + return netmem_to_net_iov(frag->netmem)->desc.dma_addr + + offset + frag->offset; + } return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } @@ -3868,20 +3975,26 @@ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int l bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) __must_check; -static inline bool skb_can_coalesce(struct sk_buff *skb, int i, - const struct page *page, int off) +static inline bool skb_can_coalesce_netmem(struct sk_buff *skb, int i, + netmem_ref netmem, int off) { if (skb_zcopy(skb)) return false; if (i) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; - return page == skb_frag_page(frag) && + return netmem == skb_frag_netmem(frag) && off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } +static inline bool skb_can_coalesce(struct sk_buff *skb, int i, + const struct page *page, int off) +{ + return skb_can_coalesce_netmem(skb, i, page_to_netmem(page), off); +} + static inline int __skb_linearize(struct sk_buff *skb) { return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM; @@ -3947,8 +4060,8 @@ __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ -static inline void skb_postpull_rcsum(struct sk_buff *skb, - const void *start, unsigned int len) +static __always_inline void +skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = wsum_negate(csum_partial(start, len, @@ -4105,8 +4218,7 @@ static inline void skb_frag_list_init(struct sk_buff *skb) int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, int *err, long *timeo_p, const struct sk_buff *skb); -struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, - struct sk_buff_head *queue, +struct sk_buff *__skb_try_recv_from_queue(struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); @@ -4118,6 +4230,9 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); +__poll_t datagram_poll_queue(struct file *file, struct socket *sock, + struct poll_table_struct *wait, + struct sk_buff_head *rcv_queue); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, @@ -4129,11 +4244,12 @@ static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, } int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, struct msghdr *msg); -int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset, - struct iov_iter *to, int len, - struct ahash_request *hash); +int skb_copy_and_crc32c_datagram_iter(const struct sk_buff *skb, int offset, + struct iov_iter *to, int len, u32 *crcp); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); +int skb_copy_datagram_from_iter_full(struct sk_buff *skb, int offset, + struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); @@ -4146,6 +4262,8 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); +int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb, + int offset, int len, int flags); int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); @@ -4185,17 +4303,9 @@ static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } -struct skb_checksum_ops { - __wsum (*update)(const void *mem, int len, __wsum wsum); - __wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len); -}; - -extern const struct skb_checksum_ops *crc32c_csum_stub __read_mostly; - -__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, - __wsum csum, const struct skb_checksum_ops *ops); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); +u32 skb_crc32c(const struct sk_buff *skb, int offset, int len, u32 crc); static inline void * __must_check __skb_header_pointer(const struct sk_buff *skb, int offset, int len, @@ -4210,13 +4320,25 @@ __skb_header_pointer(const struct sk_buff *skb, int offset, int len, return buffer; } -static inline void * __must_check +static __always_inline void * __must_check skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { return __skb_header_pointer(skb, offset, len, skb->data, skb_headlen(skb), buffer); } +/* Variant of skb_header_pointer() where @offset is user-controlled + * and potentially negative. + */ +static inline void * __must_check +skb_header_pointer_careful(const struct sk_buff *skb, int offset, + int len, void *buffer) +{ + if (unlikely(offset < 0 && -offset > skb_headroom(skb))) + return NULL; + return skb_header_pointer(skb, offset, len, buffer); +} + static inline void * __must_check skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) { @@ -4370,7 +4492,7 @@ DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); /* It is used in the ingress path to clear the delivery_time. * If needed, set the skb->tstamp to the (rcv) timestamp. */ -static inline void skb_clear_delivery_time(struct sk_buff *skb) +static __always_inline void skb_clear_delivery_time(struct sk_buff *skb) { if (skb->tstamp_type) { skb->tstamp_type = SKB_CLOCK_REALTIME; @@ -4397,7 +4519,8 @@ static inline ktime_t skb_tstamp(const struct sk_buff *skb) return skb->tstamp; } -static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) +static __always_inline ktime_t +skb_tstamp_cond(const struct sk_buff *skb, bool cond) { if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; @@ -4480,6 +4603,81 @@ static inline void skb_metadata_clear(struct sk_buff *skb) skb_metadata_set(skb, 0); } +/** + * skb_data_move - Move packet data and metadata after skb_push() or skb_pull(). + * @skb: packet to operate on + * @len: number of bytes pushed or pulled from &sk_buff->data + * @n: number of bytes to memmove() from pre-push/pull &sk_buff->data + * + * Moves @n bytes of packet data, can be zero, and all bytes of skb metadata. + * + * Assumes metadata is located immediately before &sk_buff->data prior to the + * push/pull, and that sufficient headroom exists to hold it after an + * skb_push(). Otherwise, metadata is cleared and a one-time warning is issued. + * + * Prefer skb_postpull_data_move() or skb_postpush_data_move() to calling this + * helper directly. + */ +static inline void skb_data_move(struct sk_buff *skb, const int len, + const unsigned int n) +{ + const u8 meta_len = skb_metadata_len(skb); + u8 *meta, *meta_end; + + if (!len || (!n && !meta_len)) + return; + + if (!meta_len) + goto no_metadata; + + meta_end = skb_metadata_end(skb); + meta = meta_end - meta_len; + + if (WARN_ON_ONCE(meta_end + len != skb->data || + meta_len > skb_headroom(skb))) { + skb_metadata_clear(skb); + goto no_metadata; + } + + memmove(meta + len, meta, meta_len + n); + return; + +no_metadata: + memmove(skb->data, skb->data - len, n); +} + +/** + * skb_postpull_data_move - Move packet data and metadata after skb_pull(). + * @skb: packet to operate on + * @len: number of bytes pulled from &sk_buff->data + * @n: number of bytes to memmove() from pre-pull &sk_buff->data + * + * See skb_data_move() for details. + */ +static inline void skb_postpull_data_move(struct sk_buff *skb, + const unsigned int len, + const unsigned int n) +{ + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb_data_move(skb, len, n); +} + +/** + * skb_postpush_data_move - Move packet data and metadata after skb_push(). + * @skb: packet to operate on + * @len: number of bytes pushed onto &sk_buff->data + * @n: number of bytes to memmove() from pre-push &sk_buff->data + * + * See skb_data_move() for details. + */ +static inline void skb_postpush_data_move(struct sk_buff *skb, + const unsigned int len, + const unsigned int n) +{ + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb_data_move(skb, -len, n); +} + struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING @@ -4604,7 +4802,7 @@ static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb) } } -static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) +static __always_inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level < SKB_MAX_CSUM_LEVEL) @@ -4827,6 +5025,12 @@ enum skb_ext_id { #if IS_ENABLED(CONFIG_MCTP_FLOWS) SKB_EXT_MCTP, #endif +#if IS_ENABLED(CONFIG_INET_PSP) + SKB_EXT_PSP, +#endif +#if IS_ENABLED(CONFIG_CAN) + SKB_EXT_CAN, +#endif SKB_EXT_NUM, /* must be last */ }; @@ -4919,6 +5123,7 @@ static inline bool skb_has_extensions(struct sk_buff *skb) return unlikely(skb->active_extensions); } #else +static inline void __skb_ext_put(struct skb_ext *ext) {} static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} @@ -5105,7 +5310,7 @@ static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo, void __skb_warn_lro_forwarding(const struct sk_buff *skb); -static inline bool skb_warn_if_lro(const struct sk_buff *skb) +static __always_inline bool skb_warn_if_lro(const struct sk_buff *skb) { /* LRO sets gso_size but not gso_type, whereas if GSO is really * wanted then gso_type will be set. */ @@ -5256,7 +5461,7 @@ static inline void skb_mark_for_recycle(struct sk_buff *skb) } ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, - ssize_t maxsize, gfp_t gfp); + ssize_t maxsize); #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ |
