diff options
Diffstat (limited to 'include/linux/skbuff.h')
| -rw-r--r-- | include/linux/skbuff.h | 470 |
1 files changed, 374 insertions, 96 deletions
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9c29bdd5596d..86737076101d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -31,6 +31,7 @@ #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> +#include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> @@ -273,7 +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; @@ -469,7 +469,7 @@ struct skb_shared_hwtstamps { /* Definitions for tx_flags in struct skb_shared_info */ enum { /* generate hardware time stamp */ - SKBTX_HW_TSTAMP = 1 << 0, + SKBTX_HW_TSTAMP_NOBPF = 1 << 0, /* generate software time stamp when queueing packet to NIC */ SKBTX_SW_TSTAMP = 1 << 1, @@ -477,23 +477,26 @@ enum { /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, - /* generate hardware time stamp based on cycles if supported */ - SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3, - - /* generate wifi status information (where possible) */ - SKBTX_WIFI_STATUS = 1 << 4, + /* generate software time stamp on packet tx completion */ + SKBTX_COMPLETION_TSTAMP = 1 << 3, /* determine hardware time stamp based on time or cycles */ SKBTX_HW_TSTAMP_NETDEV = 1 << 5, /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, + + /* used for bpf extension when a bpf program is loaded */ + SKBTX_BPF = 1 << 7, }; +#define SKBTX_HW_TSTAMP (SKBTX_HW_TSTAMP_NOBPF | SKBTX_BPF) + #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ - SKBTX_SCHED_TSTAMP) + SKBTX_SCHED_TSTAMP | \ + SKBTX_BPF | \ + SKBTX_COMPLETION_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ - SKBTX_HW_TSTAMP_USE_CYCLES | \ SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ @@ -607,11 +610,19 @@ struct skb_shared_info { * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; - unsigned int xdp_frags_size; - /* Intermediate layers must ensure that destructor_arg - * remains valid until skb destructor */ - void * destructor_arg; + union { + struct { + u32 xdp_frags_size; + u32 xdp_frags_truesize; + }; + + /* + * Intermediate layers must ensure that destructor_arg + * remains valid until skb destructor. + */ + void *destructor_arg; + }; /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; @@ -663,7 +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, @@ -694,6 +705,14 @@ enum { SKB_GSO_UDP_L4 = 1 << 17, 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 @@ -827,6 +846,8 @@ enum skb_tstamp_type { * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) + * @unreadable: indicates that at least 1 of the fragments in this skb is + * unreadable. * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required @@ -1008,7 +1029,7 @@ struct sk_buff { #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif - + __u8 unreadable:1; #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif @@ -1131,7 +1152,7 @@ static inline bool skb_pfmemalloc(const struct sk_buff *skb) * skb_dst - returns skb dst_entry * @skb: buffer * - * Returns skb dst_entry, regardless of reference taken or not. + * Returns: skb dst_entry, regardless of reference taken or not. */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { @@ -1144,6 +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 @@ -1154,6 +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; } @@ -1170,6 +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; @@ -1219,13 +1281,13 @@ static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) * skb_unref - decrement the skb's reference count * @skb: buffer * - * Returns true if we can free the skb. + * Returns: true if we can free the skb. */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; - if (likely(refcount_read(&skb->users) == 1)) + if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; @@ -1304,6 +1366,7 @@ struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); void skb_attempt_defer_free(struct sk_buff *skb); +u32 napi_skb_cache_get_bulk(void **skbs, u32 n); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); struct sk_buff *slab_build_skb(void *data); @@ -1341,7 +1404,7 @@ struct sk_buff_fclones { * @sk: socket * @skb: buffer * - * Returns true if skb is a fast clone, and its clone is not freed. + * Returns: true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that didn't happen. */ @@ -1433,6 +1496,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st); void skb_abort_seq_read(struct skb_seq_state *st); +int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config); @@ -1515,14 +1579,8 @@ void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); -__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, - const void *data, int hlen_proto); - -static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, - int thoff, u8 ip_proto) -{ - return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); -} +__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, + const void *data, int hlen_proto); void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, @@ -1695,13 +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); @@ -1709,12 +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))) @@ -1823,6 +1886,12 @@ static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) __skb_zcopy_downgrade_managed(skb); } +/* Return true if frags in this skb are readable by the host. */ +static inline bool skb_frags_readable(const struct sk_buff *skb) +{ + return !skb->unreadable; +} + static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; @@ -2539,10 +2608,17 @@ static inline void skb_len_add(struct sk_buff *skb, int delta) static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { - struct page *page = netmem_to_page(netmem); + struct page *page; __skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size); + if (netmem_is_net_iov(netmem)) { + skb->unreadable = true; + return; + } + + page = netmem_to_page(netmem); + /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). @@ -2665,6 +2741,12 @@ static inline void skb_assert_len(struct sk_buff *skb) #endif /* CONFIG_DEBUG_NET */ } +#if defined(CONFIG_FAIL_SKB_REALLOC) +void skb_might_realloc(struct sk_buff *skb); +#else +static inline void skb_might_realloc(struct sk_buff *skb) {} +#endif + /* * Add data to an sk_buff */ @@ -2765,6 +2847,7 @@ static inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb_might_realloc(skb); if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; @@ -2893,9 +2976,19 @@ static inline void skb_reset_inner_headers(struct sk_buff *skb) skb->inner_transport_header = skb->transport_header; } +static inline int skb_mac_header_was_set(const struct sk_buff *skb) +{ + return skb->mac_header != (typeof(skb->mac_header))~0U; +} + static inline void skb_reset_mac_len(struct sk_buff *skb) { - skb->mac_len = skb->network_header - skb->mac_header; + if (!skb_mac_header_was_set(skb)) { + DEBUG_NET_WARN_ON_ONCE(1); + skb->mac_len = 0; + } else { + skb->mac_len = skb->network_header - skb->mac_header; + } } static inline unsigned char *skb_inner_transport_header(const struct sk_buff @@ -2911,7 +3004,10 @@ static inline int skb_inner_transport_offset(const struct sk_buff *skb) static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { - skb->inner_transport_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_transport_header))offset); + skb->inner_transport_header = offset; } static inline void skb_set_inner_transport_header(struct sk_buff *skb, @@ -2928,7 +3024,10 @@ static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) static inline void skb_reset_inner_network_header(struct sk_buff *skb) { - skb->inner_network_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_network_header))offset); + skb->inner_network_header = offset; } static inline void skb_set_inner_network_header(struct sk_buff *skb, @@ -2950,7 +3049,10 @@ static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) static inline void skb_reset_inner_mac_header(struct sk_buff *skb) { - skb->inner_mac_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_mac_header))offset); + skb->inner_mac_header = offset; } static inline void skb_set_inner_mac_header(struct sk_buff *skb, @@ -2972,7 +3074,33 @@ static inline unsigned char *skb_transport_header(const struct sk_buff *skb) static inline void skb_reset_transport_header(struct sk_buff *skb) { - skb->transport_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->transport_header))offset); + 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, @@ -2989,7 +3117,10 @@ static inline unsigned char *skb_network_header(const struct sk_buff *skb) static inline void skb_reset_network_header(struct sk_buff *skb) { - skb->network_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->network_header))offset); + skb->network_header = offset; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) @@ -2998,11 +3129,6 @@ static inline void skb_set_network_header(struct sk_buff *skb, const int offset) skb->network_header += offset; } -static inline int skb_mac_header_was_set(const struct sk_buff *skb) -{ - return skb->mac_header != (typeof(skb->mac_header))~0U; -} - static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); @@ -3027,7 +3153,10 @@ static inline void skb_unset_mac_header(struct sk_buff *skb) static inline void skb_reset_mac_header(struct sk_buff *skb) { - skb->mac_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->mac_header))offset); + skb->mac_header = offset; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) @@ -3114,9 +3243,15 @@ static inline int skb_inner_network_offset(const struct sk_buff *skb) return skb_inner_network_header(skb) - skb->data; } +static inline enum skb_drop_reason +pskb_network_may_pull_reason(struct sk_buff *skb, unsigned int len) +{ + return pskb_may_pull_reason(skb, skb_network_offset(skb) + len); +} + static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) { - return pskb_may_pull(skb, skb_network_offset(skb) + len); + return pskb_network_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } /* @@ -3194,6 +3329,7 @@ static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) static inline int pskb_trim(struct sk_buff *skb, unsigned int len) { + skb_might_realloc(skb); return (len < skb->len) ? __pskb_trim(skb, len) : 0; } @@ -3429,6 +3565,10 @@ static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, } #define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). + */ #define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** @@ -3445,6 +3585,10 @@ static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) } #define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). + */ #define dev_alloc_page() dev_alloc_pages(0) /** @@ -3454,7 +3598,7 @@ static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) * A page shouldn't be considered for reusing/recycling if it was allocated * under memory pressure or at a distant memory node. * - * Returns false if this page should be returned to page allocator, true + * Returns: false if this page should be returned to page allocator, true * otherwise. */ static inline bool dev_page_is_reusable(const struct page *page) @@ -3515,30 +3659,70 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto, fragto->offset = fragfrom->offset; } +/* Return: true if the skb_frag contains a net_iov. */ +static inline bool skb_frag_is_net_iov(const skb_frag_t *frag) +{ + return netmem_is_net_iov(frag->netmem); +} + +/** + * skb_frag_net_iov - retrieve the net_iov referred to by fragment + * @frag: the fragment + * + * Return: the &struct net_iov associated with @frag. Returns NULL if this + * frag has no associated net_iov. + */ +static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag) +{ + if (!skb_frag_is_net_iov(frag)) + return NULL; + + return netmem_to_net_iov(frag->netmem); +} + /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * - * Returns the &struct page associated with @frag. + * Return: the &struct page associated with @frag. Returns NULL if this frag + * has no associated page. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { + if (skb_frag_is_net_iov(frag)) + return NULL; + return netmem_to_page(frag->netmem); } +/** + * skb_frag_netmem - retrieve the netmem referred to by a fragment + * @frag: the fragment + * + * Return: the &netmem_ref associated with @frag. + */ +static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) +{ + return frag->netmem; +} + int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, - struct bpf_prog *prog); + const struct bpf_prog *prog); + /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * - * Returns the address of the data within @frag. The page must already + * Returns: the address of the data within @frag. The page must already * be mapped. */ static inline void *skb_frag_address(const skb_frag_t *frag) { + if (!skb_frag_page(frag)) + return NULL; + return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } @@ -3546,12 +3730,18 @@ static inline void *skb_frag_address(const skb_frag_t *frag) * skb_frag_address_safe - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * - * Returns the address of the data within @frag. Checks that the page + * Returns: the address of the data within @frag. Checks that the page * is mapped and returns %NULL otherwise. */ 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; @@ -3572,7 +3762,7 @@ static inline void skb_frag_page_copy(skb_frag_t *fragto, bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** - * skb_frag_dma_map - maps a paged fragment via the DMA API + * __skb_frag_dma_map - maps a paged fragment via the DMA API * @dev: the device to map the fragment to * @frag: the paged fragment to map * @offset: the offset within the fragment (starting at the @@ -3582,15 +3772,40 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); * * Maps the page associated with @frag to @device. */ -static inline dma_addr_t skb_frag_dma_map(struct device *dev, - const skb_frag_t *frag, - size_t offset, size_t size, - enum dma_data_direction dir) +static inline dma_addr_t __skb_frag_dma_map(struct device *dev, + const skb_frag_t *frag, + 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); } +#define skb_frag_dma_map(dev, frag, ...) \ + CONCATENATE(_skb_frag_dma_map, \ + COUNT_ARGS(__VA_ARGS__))(dev, frag, ##__VA_ARGS__) + +#define __skb_frag_dma_map1(dev, frag, offset, uf, uo) ({ \ + const skb_frag_t *uf = (frag); \ + size_t uo = (offset); \ + \ + __skb_frag_dma_map(dev, uf, uo, skb_frag_size(uf) - uo, \ + DMA_TO_DEVICE); \ +}) +#define _skb_frag_dma_map1(dev, frag, offset) \ + __skb_frag_dma_map1(dev, frag, offset, __UNIQUE_ID(frag_), \ + __UNIQUE_ID(offset_)) +#define _skb_frag_dma_map0(dev, frag) \ + _skb_frag_dma_map1(dev, frag, 0) +#define _skb_frag_dma_map2(dev, frag, offset, size) \ + __skb_frag_dma_map(dev, frag, offset, size, DMA_TO_DEVICE) +#define _skb_frag_dma_map3(dev, frag, offset, size, dir) \ + __skb_frag_dma_map(dev, frag, offset, size, dir) + static inline struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { @@ -3734,39 +3949,26 @@ 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 int skb_add_data(struct sk_buff *skb, - struct iov_iter *from, int copy) -{ - const int off = skb->len; - - if (skb->ip_summed == CHECKSUM_NONE) { - __wsum csum = 0; - if (csum_and_copy_from_iter_full(skb_put(skb, copy), copy, - &csum, from)) { - skb->csum = csum_block_add(skb->csum, csum, off); - return 0; - } - } else if (copy_from_iter_full(skb_put(skb, copy), copy, from)) - return 0; - - __skb_trim(skb, off); - return -EFAULT; -} - -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; @@ -3788,7 +3990,7 @@ static inline int skb_linearize(struct sk_buff *skb) * skb_has_shared_frag - can any frag be overwritten * @skb: buffer to test * - * Return true if the skb has at least one frag that might be modified + * Return: true if the skb has at least one frag that might be modified * by an external entity (as in vmsplice()/sendfile()) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) @@ -3900,6 +4102,7 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { + skb_might_realloc(skb); if (likely(len >= skb->len)) return 0; return pskb_trim_rcsum_slow(skb, len); @@ -3989,8 +4192,7 @@ 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); @@ -4002,6 +4204,9 @@ 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, @@ -4013,11 +4218,12 @@ 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); @@ -4030,6 +4236,8 @@ 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); @@ -4069,17 +4277,9 @@ 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, @@ -4364,6 +4564,81 @@ 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 @@ -4432,7 +4707,7 @@ void skb_tstamp_tx(struct sk_buff *orig_skb, static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); - if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP) + if (skb_shinfo(skb)->tx_flags & (SKBTX_SW_TSTAMP | SKBTX_BPF)) skb_tstamp_tx(skb, NULL); } @@ -4509,7 +4784,7 @@ static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) /* Check if we need to perform checksum complete validation. * - * Returns true if checksum complete is needed, false otherwise + * Returns: true if checksum complete is needed, false otherwise * (either checksum is unnecessary or zero checksum is allowed). */ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, @@ -4711,6 +4986,9 @@ enum skb_ext_id { #if IS_ENABLED(CONFIG_MCTP_FLOWS) SKB_EXT_MCTP, #endif +#if IS_ENABLED(CONFIG_INET_PSP) + SKB_EXT_PSP, +#endif SKB_EXT_NUM, /* must be last */ }; @@ -5140,7 +5418,7 @@ 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 */ |