diff options
Diffstat (limited to 'include/linux/skbuff.h')
-rw-r--r-- | include/linux/skbuff.h | 277 |
1 files changed, 76 insertions, 201 deletions
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d3d10556f0fa..ca8afa382bf2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -43,6 +43,7 @@ #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> +#include <net/dropreason.h> /** * DOC: skb checksums @@ -337,184 +338,6 @@ struct sk_buff_head { struct sk_buff; -/* The reason of skb drop, which is used in kfree_skb_reason(). - * en...maybe they should be splited by group? - * - * Each item here should also be in 'TRACE_SKB_DROP_REASON', which is - * used to translate the reason to string. - */ -enum skb_drop_reason { - SKB_NOT_DROPPED_YET = 0, - SKB_DROP_REASON_NOT_SPECIFIED, /* drop reason is not specified */ - SKB_DROP_REASON_NO_SOCKET, /* socket not found */ - SKB_DROP_REASON_PKT_TOO_SMALL, /* packet size is too small */ - SKB_DROP_REASON_TCP_CSUM, /* TCP checksum error */ - SKB_DROP_REASON_SOCKET_FILTER, /* dropped by socket filter */ - SKB_DROP_REASON_UDP_CSUM, /* UDP checksum error */ - SKB_DROP_REASON_NETFILTER_DROP, /* dropped by netfilter */ - SKB_DROP_REASON_OTHERHOST, /* packet don't belong to current - * host (interface is in promisc - * mode) - */ - SKB_DROP_REASON_IP_CSUM, /* IP checksum error */ - SKB_DROP_REASON_IP_INHDR, /* there is something wrong with - * IP header (see - * IPSTATS_MIB_INHDRERRORS) - */ - SKB_DROP_REASON_IP_RPFILTER, /* IP rpfilter validate failed. - * see the document for rp_filter - * in ip-sysctl.rst for more - * information - */ - SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, /* destination address of L2 - * is multicast, but L3 is - * unicast. - */ - SKB_DROP_REASON_XFRM_POLICY, /* xfrm policy check failed */ - SKB_DROP_REASON_IP_NOPROTO, /* no support for IP protocol */ - SKB_DROP_REASON_SOCKET_RCVBUFF, /* socket receive buff is full */ - SKB_DROP_REASON_PROTO_MEM, /* proto memory limition, such as - * udp packet drop out of - * udp_memory_allocated. - */ - SKB_DROP_REASON_TCP_MD5NOTFOUND, /* no MD5 hash and one - * expected, corresponding - * to LINUX_MIB_TCPMD5NOTFOUND - */ - SKB_DROP_REASON_TCP_MD5UNEXPECTED, /* MD5 hash and we're not - * expecting one, corresponding - * to LINUX_MIB_TCPMD5UNEXPECTED - */ - SKB_DROP_REASON_TCP_MD5FAILURE, /* MD5 hash and its wrong, - * corresponding to - * LINUX_MIB_TCPMD5FAILURE - */ - SKB_DROP_REASON_SOCKET_BACKLOG, /* failed to add skb to socket - * backlog (see - * LINUX_MIB_TCPBACKLOGDROP) - */ - SKB_DROP_REASON_TCP_FLAGS, /* TCP flags invalid */ - SKB_DROP_REASON_TCP_ZEROWINDOW, /* TCP receive window size is zero, - * see LINUX_MIB_TCPZEROWINDOWDROP - */ - SKB_DROP_REASON_TCP_OLD_DATA, /* the TCP data reveived is already - * received before (spurious retrans - * may happened), see - * LINUX_MIB_DELAYEDACKLOST - */ - SKB_DROP_REASON_TCP_OVERWINDOW, /* the TCP data is out of window, - * the seq of the first byte exceed - * the right edges of receive - * window - */ - SKB_DROP_REASON_TCP_OFOMERGE, /* the data of skb is already in - * the ofo queue, corresponding to - * LINUX_MIB_TCPOFOMERGE - */ - SKB_DROP_REASON_TCP_RFC7323_PAWS, /* PAWS check, corresponding to - * LINUX_MIB_PAWSESTABREJECTED - */ - SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */ - SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */ - SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */ - SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */ - SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */ - SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ - SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ - SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ - SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */ - SKB_DROP_REASON_TCP_OFO_DROP, /* data already in receive queue */ - SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ - SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by - * BPF_PROG_TYPE_CGROUP_SKB - * eBPF program - */ - SKB_DROP_REASON_IPV6DISABLED, /* IPv6 is disabled on the device */ - SKB_DROP_REASON_NEIGH_CREATEFAIL, /* failed to create neigh - * entry - */ - SKB_DROP_REASON_NEIGH_FAILED, /* neigh entry in failed state */ - SKB_DROP_REASON_NEIGH_QUEUEFULL, /* arp_queue for neigh - * entry is full - */ - SKB_DROP_REASON_NEIGH_DEAD, /* neigh entry is dead */ - SKB_DROP_REASON_TC_EGRESS, /* dropped in TC egress HOOK */ - SKB_DROP_REASON_QDISC_DROP, /* dropped by qdisc when packet - * outputting (failed to enqueue to - * current qdisc) - */ - SKB_DROP_REASON_CPU_BACKLOG, /* failed to enqueue the skb to - * the per CPU backlog queue. This - * can be caused by backlog queue - * full (see netdev_max_backlog in - * net.rst) or RPS flow limit - */ - SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ - SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */ - SKB_DROP_REASON_UNHANDLED_PROTO, /* protocol not implemented - * or not supported - */ - SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation - * error - */ - SKB_DROP_REASON_SKB_GSO_SEG, /* gso segmentation error */ - SKB_DROP_REASON_SKB_UCOPY_FAULT, /* failed to copy data from - * user space, e.g., via - * zerocopy_sg_from_iter() - * or skb_orphan_frags_rx() - */ - SKB_DROP_REASON_DEV_HDR, /* device driver specific - * header/metadata is invalid - */ - /* the device is not ready to xmit/recv due to any of its data - * structure that is not up/ready/initialized, e.g., the IFF_UP is - * not set, or driver specific tun->tfiles[txq] is not initialized - */ - SKB_DROP_REASON_DEV_READY, - SKB_DROP_REASON_FULL_RING, /* ring buffer is full */ - SKB_DROP_REASON_NOMEM, /* error due to OOM */ - SKB_DROP_REASON_HDR_TRUNC, /* failed to trunc/extract the header - * from networking data, e.g., failed - * to pull the protocol header from - * frags via pskb_may_pull() - */ - SKB_DROP_REASON_TAP_FILTER, /* dropped by (ebpf) filter directly - * attached to tun/tap, e.g., via - * TUNSETFILTEREBPF - */ - SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented - * at tun/tap, e.g., check_filter() - */ - SKB_DROP_REASON_ICMP_CSUM, /* ICMP checksum error */ - SKB_DROP_REASON_INVALID_PROTO, /* the packet doesn't follow RFC - * 2211, such as a broadcasts - * ICMP_TIMESTAMP - */ - SKB_DROP_REASON_IP_INADDRERRORS, /* host unreachable, corresponding - * to IPSTATS_MIB_INADDRERRORS - */ - SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding - * to IPSTATS_MIB_INADDRERRORS - */ - SKB_DROP_REASON_PKT_TOO_BIG, /* packet size is too big (maybe exceed - * the MTU) - */ - SKB_DROP_REASON_MAX, -}; - -#define SKB_DR_INIT(name, reason) \ - enum skb_drop_reason name = SKB_DROP_REASON_##reason -#define SKB_DR(name) \ - SKB_DR_INIT(name, NOT_SPECIFIED) -#define SKB_DR_SET(name, reason) \ - (name = SKB_DROP_REASON_##reason) -#define SKB_DR_OR(name, reason) \ - do { \ - if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ - name == SKB_NOT_DROPPED_YET) \ - SKB_DR_SET(name, reason); \ - } while (0) - /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. @@ -686,10 +509,18 @@ enum { * charged to the kernel memory. */ SKBFL_PURE_ZEROCOPY = BIT(2), + + SKBFL_DONT_ORPHAN = BIT(3), + + /* page references are managed by the ubuf_info, so it's safe to + * use frags only up until ubuf_info is released + */ + SKBFL_MANAGED_FRAG_REFS = BIT(4), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) -#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY) +#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ + SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) /* * The callback notifies userspace to release buffers when skb DMA is done in @@ -1773,13 +1604,14 @@ 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 sock *sk, struct sk_buff *skb, - struct iov_iter *from, size_t length); +int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, + 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) { - return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len); + return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, @@ -1806,6 +1638,11 @@ static inline bool skb_zcopy_pure(const struct sk_buff *skb) return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; } +static inline bool skb_zcopy_managed(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS; +} + static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, const struct sk_buff *skb2) { @@ -1880,6 +1717,14 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) } } +void __skb_zcopy_downgrade_managed(struct sk_buff *skb); + +static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) +{ + if (unlikely(skb_zcopy_managed(skb))) + __skb_zcopy_downgrade_managed(skb); +} + static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; @@ -2528,6 +2373,34 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) return skb_headlen(skb) + __skb_pagelen(skb); } +static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, + int i, struct page *page, + int off, int size) +{ + skb_frag_t *frag = &shinfo->frags[i]; + + /* + * 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). + */ + frag->bv_page = page; + frag->bv_offset = off; + skb_frag_size_set(frag, size); +} + +/** + * skb_len_add - adds a number to len fields of skb + * @skb: buffer to add len to + * @delta: number of bytes to add + */ +static inline void skb_len_add(struct sk_buff *skb, int delta) +{ + skb->len += delta; + skb->data_len += delta; + skb->truesize += delta; +} + /** * __skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised @@ -2544,17 +2417,7 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - - /* - * 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). - */ - frag->bv_page = page; - frag->bv_offset = off; - skb_frag_size_set(frag, size); - + __skb_fill_page_desc_noacc(skb_shinfo(skb), i, page, off, size); page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; @@ -2624,6 +2487,14 @@ static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) #endif /* NET_SKBUFF_DATA_USES_OFFSET */ +static inline void skb_assert_len(struct sk_buff *skb) +{ +#ifdef CONFIG_DEBUG_NET + if (WARN_ONCE(!skb->len, "%s\n", __func__)) + DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); +#endif /* CONFIG_DEBUG_NET */ +} + /* * Add data to an sk_buff */ @@ -2940,8 +2811,14 @@ 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)); return skb->head + skb->mac_header; } @@ -2952,14 +2829,10 @@ static inline int skb_mac_offset(const struct sk_buff *skb) static inline u32 skb_mac_header_len(const struct sk_buff *skb) { + DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->network_header - skb->mac_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_unset_mac_header(struct sk_buff *skb) { skb->mac_header = (typeof(skb->mac_header))~0U; @@ -3182,8 +3055,7 @@ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; - if (!skb_zcopy_is_nouarg(skb) && - skb_uarg(skb)->callback == msg_zerocopy_callback) + if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN) return 0; return skb_copy_ubufs(skb, gfp_mask); } @@ -3496,7 +3368,10 @@ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { - __skb_frag_unref(&skb_shinfo(skb)->frags[f], skb->pp_recycle); + struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (!skb_zcopy_managed(skb)) + __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); } /** |