diff options
Diffstat (limited to 'include/linux/skbuff.h')
| -rw-r--r-- | include/linux/skbuff.h | 454 |
1 files changed, 284 insertions, 170 deletions
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9d24aec064e8..bb2b751d274a 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> @@ -353,8 +354,6 @@ struct sk_buff; #define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS -extern int sysctl_max_skb_frags; - /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ @@ -527,6 +526,13 @@ enum { #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) +struct ubuf_info_ops { + void (*complete)(struct sk_buff *, struct ubuf_info *, + bool zerocopy_success); + /* has to be compatible with skb_zcopy_set() */ + int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); +}; + /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. @@ -536,8 +542,7 @@ enum { * The desc field is used to track userspace buffer index. */ struct ubuf_info { - void (*callback)(struct sk_buff *, struct ubuf_info *, - bool zerocopy_success); + const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; @@ -603,11 +608,19 @@ 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]; @@ -702,6 +715,13 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +enum skb_tstamp_type { + SKB_CLOCK_REALTIME, + SKB_CLOCK_MONOTONIC, + SKB_CLOCK_TAI, + __SKB_CLOCK_MAX = SKB_CLOCK_TAI, +}; + /** * DOC: Basic sk_buff geometry * @@ -816,13 +836,13 @@ typedef unsigned char *sk_buff_data_t; * @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 - * @mono_delivery_time: When set, skb->tstamp has the - * delivery_time in mono clock base (i.e. EDT). Otherwise, the - * skb->tstamp has the (rcv) timestamp at ingress and - * delivery_time at egress. + * @tstamp_type: When set, skb->tstamp has the + * delivery_time clock base of skb->tstamp. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. @@ -950,7 +970,7 @@ struct sk_buff { /* private: */ __u8 __mono_tc_offset[0]; /* public: */ - __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ + __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; @@ -992,14 +1012,14 @@ struct sk_buff { #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; #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 @@ -1080,15 +1100,16 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) -/* if you move tc_at_ingress or mono_delivery_time +/* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 7) -#define TC_AT_INGRESS_MASK (1 << 6) +#define SKB_TSTAMP_TYPE_MASK (3 << 6) +#define SKB_TSTAMP_TYPE_RSHIFT (6) +#define TC_AT_INGRESS_MASK (1 << 5) #else -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 0) -#define TC_AT_INGRESS_MASK (1 << 1) +#define SKB_TSTAMP_TYPE_MASK (3) +#define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) @@ -1121,7 +1142,7 @@ 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) { @@ -1174,15 +1195,6 @@ static inline bool skb_dst_is_noref(const struct sk_buff *skb) return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } -/** - * skb_rtable - Returns the skb &rtable - * @skb: buffer - */ -static inline struct rtable *skb_rtable(const struct sk_buff *skb) -{ - return (struct rtable *)skb_dst(skb); -} - /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. @@ -1218,13 +1230,13 @@ 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; @@ -1250,8 +1262,14 @@ static inline bool skb_data_unref(const struct sk_buff *skb, return true; } -void __fix_address -kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); +void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason reason); + +static inline void +kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) +{ + sk_skb_reason_drop(NULL, skb, reason); +} /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason @@ -1334,7 +1352,7 @@ 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. */ @@ -1426,6 +1444,7 @@ 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); @@ -1497,8 +1516,14 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) __skb_set_hash(skb, hash, true, is_l4); } -void __skb_get_hash(struct sk_buff *skb); -u32 __skb_get_hash_symmetric(const struct sk_buff *skb); +u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb); + +static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb) +{ + return __skb_get_hash_symmetric_net(NULL, skb); +} + +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); @@ -1577,10 +1602,18 @@ void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); +static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb) +{ + if (!skb->l4_hash && !skb->sw_hash) + __skb_get_hash_net(net, skb); + + return skb->hash; +} + static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) - __skb_get_hash(skb); + __skb_get_hash_net(NULL, skb); return skb->hash; } @@ -1615,17 +1648,26 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } +static inline bool skb_is_decrypted(const struct sk_buff *skb) +{ +#ifdef CONFIG_SKB_DECRYPTED + return skb->decrypted; +#else + return false; +#endif +} + static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } @@ -1662,18 +1704,20 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +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); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); -void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success); - int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length); +int zerocopy_fill_skb_from_iter(struct sk_buff *skb, + struct iov_iter *from, size_t length); + static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { @@ -1757,13 +1801,13 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) - uarg->callback(NULL, uarg, true); + uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { - if (uarg->callback == msg_zerocopy_callback) + if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); @@ -1777,7 +1821,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (uarg) { if (!skb_zcopy_is_nouarg(skb)) - uarg->callback(skb, uarg, zerocopy_success); + uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } @@ -1791,6 +1835,12 @@ 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; @@ -2507,10 +2557,17 @@ 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). @@ -2633,6 +2690,12 @@ 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 */ @@ -2733,6 +2796,7 @@ 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; @@ -2861,9 +2925,19 @@ 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 @@ -2879,7 +2953,10 @@ 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, @@ -2896,7 +2973,10 @@ 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, @@ -2918,7 +2998,10 @@ 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, @@ -2940,7 +3023,10 @@ 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; } static inline void skb_set_transport_header(struct sk_buff *skb, @@ -2957,7 +3043,10 @@ 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) @@ -2966,11 +3055,6 @@ 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)); @@ -2995,7 +3079,10 @@ 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) @@ -3031,6 +3118,21 @@ static inline void skb_mac_header_rebuild(struct sk_buff *skb) } } +/* Move the full mac header up to current network_header. + * Leaves skb->data pointing at offset skb->mac_len into the mac_header. + * Must be provided the complete mac header length. + */ +static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) +{ + if (skb_mac_header_was_set(skb)) { + const unsigned char *old_mac = skb_mac_header(skb); + + skb_set_mac_header(skb, -full_mac_len); + memmove(skb_mac_header(skb), old_mac, full_mac_len); + __skb_push(skb, full_mac_len - skb->mac_len); + } +} + static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); @@ -3067,9 +3169,15 @@ 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; } /* @@ -3147,6 +3255,7 @@ 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; } @@ -3350,13 +3459,7 @@ static inline void *napi_alloc_frag_align(unsigned int fragsz, return __napi_alloc_frag_align(fragsz, -align); } -struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, - unsigned int length, gfp_t gfp_mask); -static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, - unsigned int length) -{ - return __napi_alloc_skb(napi, length, GFP_ATOMIC); -} +struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); @@ -3371,7 +3474,7 @@ void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); * * %NULL is returned if there is no free memory. */ -static inline struct page *__dev_alloc_pages(gfp_t gfp_mask, +static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. @@ -3384,13 +3487,15 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask, */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; - return alloc_pages_node(NUMA_NO_NODE, gfp_mask, order); + return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order); } +#define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) -static inline struct page *dev_alloc_pages(unsigned int order) -{ - return __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, order); -} +/* + * 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) /** * __dev_alloc_page - allocate a page for network Rx @@ -3400,15 +3505,17 @@ static inline struct page *dev_alloc_pages(unsigned int order) * * %NULL is returned if there is no free memory. */ -static inline struct page *__dev_alloc_page(gfp_t gfp_mask) +static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) { - return __dev_alloc_pages(gfp_mask, 0); + return __dev_alloc_pages_noprof(gfp_mask, 0); } +#define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) -static inline struct page *dev_alloc_page(void) -{ - return dev_alloc_pages(0); -} +/* + * 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) /** * dev_page_is_reusable - check whether a page can be reused for network Rx @@ -3417,7 +3524,7 @@ static inline struct page *dev_alloc_page(void) * 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) @@ -3478,105 +3585,70 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto, fragto->offset = fragfrom->offset; } -/** - * skb_frag_page - retrieve the page referred to by a paged fragment - * @frag: the paged fragment - * - * Returns the &struct page associated with @frag. - */ -static inline struct page *skb_frag_page(const skb_frag_t *frag) +/* 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_to_page(frag->netmem); -} - -/** - * __skb_frag_ref - take an addition reference on a paged fragment. - * @frag: the paged fragment - * - * Takes an additional reference on the paged fragment @frag. - */ -static inline void __skb_frag_ref(skb_frag_t *frag) -{ - get_page(skb_frag_page(frag)); + return netmem_is_net_iov(frag->netmem); } /** - * skb_frag_ref - take an addition reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset. + * skb_frag_net_iov - retrieve the net_iov referred to by fragment + * @frag: the fragment * - * Takes an additional reference on the @f'th paged fragment of @skb. + * Return: the &struct net_iov associated with @frag. Returns NULL if this + * frag has no associated net_iov. */ -static inline void skb_frag_ref(struct sk_buff *skb, int f) -{ - __skb_frag_ref(&skb_shinfo(skb)->frags[f]); -} - -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); -bool napi_pp_put_page(struct page *page, bool napi_safe); - -static inline void -skb_page_unref(const struct sk_buff *skb, struct page *page, bool napi_safe) -{ -#ifdef CONFIG_PAGE_POOL - if (skb->pp_recycle && napi_pp_put_page(page, napi_safe)) - return; -#endif - put_page(page); -} - -static inline void -napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) +static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag) { - struct page *page = skb_frag_page(frag); + if (!skb_frag_is_net_iov(frag)) + return NULL; -#ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page, napi_safe)) - return; -#endif - put_page(page); + return netmem_to_net_iov(frag->netmem); } /** - * __skb_frag_unref - release a reference on a paged fragment. + * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment - * @recycle: recycle the page if allocated via page_pool * - * Releases a reference on the paged fragment @frag - * or recycles the page via the page_pool API. + * Return: the &struct page associated with @frag. Returns NULL if this frag + * has no associated page. */ -static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) +static inline struct page *skb_frag_page(const skb_frag_t *frag) { - napi_frag_unref(frag, recycle, false); + if (skb_frag_is_net_iov(frag)) + return NULL; + + return netmem_to_page(frag->netmem); } /** - * skb_frag_unref - release a reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset + * skb_frag_netmem - retrieve the netmem referred to by a fragment + * @frag: the fragment * - * Releases a reference on the @f'th paged fragment of @skb. + * Return: the &netmem_ref associated with @frag. */ -static inline void skb_frag_unref(struct sk_buff *skb, int f) +static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) { - struct skb_shared_info *shinfo = skb_shinfo(skb); - - if (!skb_zcopy_managed(skb)) - __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); + 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, + 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); } @@ -3584,7 +3656,7 @@ 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) @@ -3610,7 +3682,7 @@ 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 @@ -3620,15 +3692,36 @@ 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) { 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) { @@ -3826,7 +3919,7 @@ 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) @@ -3938,6 +4031,7 @@ 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); @@ -4058,12 +4152,6 @@ int skb_copy_datagram_from_iter(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); -void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len); -static inline void skb_free_datagram_locked(struct sock *sk, - struct sk_buff *skb) -{ - __skb_free_datagram_locked(sk, skb, 0); -} int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); @@ -4252,7 +4340,7 @@ static inline void skb_get_new_timestampns(const struct sk_buff *skb, static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); - skb->mono_delivery_time = 0; + skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline ktime_t net_timedelta(ktime_t t) @@ -4261,10 +4349,36 @@ static inline ktime_t net_timedelta(ktime_t t) } static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, - bool mono) + u8 tstamp_type) { skb->tstamp = kt; - skb->mono_delivery_time = kt && mono; + + if (kt) + skb->tstamp_type = tstamp_type; + else + skb->tstamp_type = SKB_CLOCK_REALTIME; +} + +static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, + ktime_t kt, clockid_t clockid) +{ + u8 tstamp_type = SKB_CLOCK_REALTIME; + + switch (clockid) { + case CLOCK_REALTIME: + break; + case CLOCK_MONOTONIC: + tstamp_type = SKB_CLOCK_MONOTONIC; + break; + case CLOCK_TAI: + tstamp_type = SKB_CLOCK_TAI; + break; + default: + WARN_ON_ONCE(1); + kt = 0; + } + + skb_set_delivery_time(skb, kt, tstamp_type); } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); @@ -4274,8 +4388,8 @@ DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); */ static inline void skb_clear_delivery_time(struct sk_buff *skb) { - if (skb->mono_delivery_time) { - skb->mono_delivery_time = 0; + if (skb->tstamp_type) { + skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); else @@ -4285,7 +4399,7 @@ static inline void skb_clear_delivery_time(struct sk_buff *skb) static inline void skb_clear_tstamp(struct sk_buff *skb) { - if (skb->mono_delivery_time) + if (skb->tstamp_type) return; skb->tstamp = 0; @@ -4293,7 +4407,7 @@ static inline void skb_clear_tstamp(struct sk_buff *skb) static inline ktime_t skb_tstamp(const struct sk_buff *skb) { - if (skb->mono_delivery_time) + if (skb->tstamp_type) return 0; return skb->tstamp; @@ -4301,7 +4415,7 @@ static inline ktime_t skb_tstamp(const struct sk_buff *skb) static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) { - if (!skb->mono_delivery_time && skb->tstamp) + if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; if (static_branch_unlikely(&netstamp_needed_key) || cond) @@ -4527,7 +4641,7 @@ 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, |