* @hash: the packet hash
* @queue_mapping: Queue mapping for multiqueue devices
* @xmit_more: More SKBs are pending for this queue
+ * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
* @ndisc_nodetype: router type (from link layer)
* @ooo_okay: allow the mapping of a socket to a queue to be changed
* @l4_hash: indicate hash is a canonical 4-tuple hash over transport
unsigned long dev_scratch;
};
};
- struct rb_node rbnode; /* used in netem & tcp stack */
+ struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */
+ struct list_head list;
+ };
+
+ union {
+ struct sock *sk;
+ int ip_defrag_offset;
};
- struct sock *sk;
union {
ktime_t tstamp;
peeked:1,
head_frag:1,
xmit_more:1,
- __unused:1; /* one bit hole */
+ pfmemalloc:1;
/* fields enclosed in headers_start/headers_end are copied
* using a single memcpy() in __copy_skb_header()
__u8 __pkt_type_offset[0];
__u8 pkt_type:3;
- __u8 pfmemalloc:1;
__u8 ignore_df:1;
-
__u8 nf_trace:1;
__u8 ip_summed:2;
__u8 ooo_okay:1;
+
__u8 l4_hash:1;
__u8 sw_hash:1;
__u8 wifi_acked_valid:1;
__u8 wifi_acked:1;
-
__u8 no_fcs:1;
/* Indicates the inner headers are valid in the skbuff. */
__u8 encapsulation:1;
__u8 encap_hdr_csum:1;
__u8 csum_valid:1;
+
__u8 csum_complete_sw:1;
__u8 csum_level:2;
__u8 csum_not_inet:1;
-
__u8 dst_pending_confirm:1;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
__u8 ndisc_nodetype:2;
#endif
__u8 ipvs_property:1;
+
__u8 inner_protocol_type:1;
__u8 remcsum_offload:1;
#ifdef CONFIG_NET_SWITCHDEV
return skb->hash;
}
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb);
+__u32 skb_get_hash_perturb(const struct sk_buff *skb,
+ const siphash_key_t *perturb);
static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
{
}
}
+static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val)
+{
+ skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL);
+ skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG;
+}
+
+static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb)
+{
+ return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL;
+}
+
+static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb)
+{
+ return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL);
+}
+
/* Release a reference on a zerocopy structure */
static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy)
{
struct ubuf_info *uarg = skb_zcopy(skb);
if (uarg) {
- if (uarg->callback == sock_zerocopy_callback) {
+ if (skb_zcopy_is_nouarg(skb)) {
+ /* no notification callback */
+ } else if (uarg->callback == sock_zerocopy_callback) {
uarg->zerocopy = uarg->zerocopy && zerocopy;
sock_zerocopy_put(uarg);
} else {
return list->next == (const struct sk_buff *) list;
}
+/**
+ * skb_queue_empty_lockless - check if a queue is empty
+ * @list: queue head
+ *
+ * Returns true if the queue is empty, false otherwise.
+ * This variant can be used in lockless contexts.
+ */
+static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list)
+{
+ return READ_ONCE(list->next) == (const struct sk_buff *) list;
+}
+
+
/**
* skb_queue_is_last - check if skb is the last entry in the queue
* @list: queue head
struct sk_buff *prev, struct sk_buff *next,
struct sk_buff_head *list)
{
- newsk->next = next;
- newsk->prev = prev;
- next->prev = prev->next = newsk;
+ /* see skb_queue_empty_lockless() for the opposite READ_ONCE() */
+ WRITE_ONCE(newsk->next, next);
+ WRITE_ONCE(newsk->prev, prev);
+ WRITE_ONCE(next->prev, newsk);
+ WRITE_ONCE(prev->next, newsk);
list->qlen++;
}
struct sk_buff *first = list->next;
struct sk_buff *last = list->prev;
- first->prev = prev;
- prev->next = first;
+ WRITE_ONCE(first->prev, prev);
+ WRITE_ONCE(prev->next, first);
- last->next = next;
- next->prev = last;
+ WRITE_ONCE(last->next, next);
+ WRITE_ONCE(next->prev, last);
}
/**
next = skb->next;
prev = skb->prev;
skb->next = skb->prev = NULL;
- next->prev = prev;
- prev->next = next;
+ WRITE_ONCE(next->prev, prev);
+ WRITE_ONCE(prev->next, next);
}
/**
return;
else if (skb_flow_dissect_flow_keys(skb, &keys, 0))
skb_set_transport_header(skb, keys.control.thoff);
- else
+ else if (offset_hint >= 0)
skb_set_transport_header(skb, offset_hint);
}
{
if (likely(!skb_zcopy(skb)))
return 0;
- if (skb_uarg(skb)->callback == sock_zerocopy_callback)
+ if (!skb_zcopy_is_nouarg(skb) &&
+ skb_uarg(skb)->callback == sock_zerocopy_callback)
return 0;
return skb_copy_ubufs(skb, gfp_mask);
}
kfree_skb(skb);
}
-void skb_rbtree_purge(struct rb_root *root);
+unsigned int skb_rbtree_purge(struct rb_root *root);
void *netdev_alloc_frag(unsigned int fragsz);
return skb->data;
}
+int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len);
/**
* pskb_trim_rcsum - trim received skb and update checksum
* @skb: buffer to trim
*
* This is exactly the same as pskb_trim except that it ensures the
* checksum of received packets are still valid after the operation.
+ * It can change skb pointers.
*/
static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len)
{
if (likely(len >= skb->len))
return 0;
- if (skb->ip_summed == CHECKSUM_COMPLETE)
- skb->ip_summed = CHECKSUM_NONE;
- return __pskb_trim(skb, len);
+ return pskb_trim_rcsum_slow(skb, len);
}
static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len)
void skb_scrub_packet(struct sk_buff *skb, bool xnet);
unsigned int skb_gso_transport_seglen(const struct sk_buff *skb);
bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu);
+bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len);
struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
int skb_ensure_writable(struct sk_buff *skb, int write_len);
return hdr_len + skb_gso_transport_seglen(skb);
}
+/**
+ * skb_gso_mac_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_mac_seglen is used to determine the real size of the
+ * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4
+ * headers (TCP/UDP).
+ */
+static inline unsigned int skb_gso_mac_seglen(const struct sk_buff *skb)
+{
+ unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
+ return hdr_len + skb_gso_transport_seglen(skb);
+}
+
/* Local Checksum Offload.
* Compute outer checksum based on the assumption that the
* inner checksum will be offloaded later.