diff options
| -rw-r--r-- | Documentation/networking/index.rst | 1 | ||||
| -rw-r--r-- | Documentation/networking/skbuff.rst | 6 | ||||
| -rw-r--r-- | include/linux/skbuff.h | 42 |
3 files changed, 37 insertions, 12 deletions
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 72cf33579b78..a1c271fe484e 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -97,6 +97,7 @@ Contents: sctp secid seg6-sysctl + skbuff smc-sysctl statistics strparser diff --git a/Documentation/networking/skbuff.rst b/Documentation/networking/skbuff.rst index b4a008feceb4..94681523e345 100644 --- a/Documentation/networking/skbuff.rst +++ b/Documentation/networking/skbuff.rst @@ -23,3 +23,9 @@ skb_clone() allows for fast duplication of skbs. None of the data buffers get copied, but caller gets a new metadata struct (struct sk_buff). &skb_shared_info.refcount indicates the number of skbs pointing at the same packet data (i.e. clones). + +dataref and headerless skbs +--------------------------- + +.. kernel-doc:: include/linux/skbuff.h + :doc: dataref and headerless skbs diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 69802624276d..0e492f9bf532 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -727,16 +727,32 @@ struct skb_shared_info { skb_frag_t frags[MAX_SKB_FRAGS]; }; -/* We divide dataref into two halves. The higher 16 bits hold references - * to the payload part of skb->data. The lower 16 bits hold references to - * the entire skb->data. A clone of a headerless skb holds the length of - * the header in skb->hdr_len. - * - * All users must obey the rule that the skb->data reference count must be - * greater than or equal to the payload reference count. - * - * Holding a reference to the payload part means that the user does not - * care about modifications to the header part of skb->data. +/** + * DOC: dataref and headerless skbs + * + * Transport layers send out clones of payload skbs they hold for + * retransmissions. To allow lower layers of the stack to prepend their headers + * we split &skb_shared_info.dataref into two halves. + * The lower 16 bits count the overall number of references. + * The higher 16 bits indicate how many of the references are payload-only. + * skb_header_cloned() checks if skb is allowed to add / write the headers. + * + * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr + * (via __skb_header_release()). Any clone created from marked skb will get + * &sk_buff.hdr_len populated with the available headroom. + * If there's the only clone in existence it's able to modify the headroom + * at will. The sequence of calls inside the transport layer is:: + * + * <alloc skb> + * skb_reserve() + * __skb_header_release() + * skb_clone() + * // send the clone down the stack + * + * This is not a very generic construct and it depends on the transport layers + * doing the right thing. In practice there's usually only one payload-only skb. + * Having multiple payload-only skbs with different lengths of hdr_len is not + * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) @@ -2027,8 +2043,10 @@ static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) } /** - * __skb_header_release - release reference to header - * @skb: buffer to operate on + * __skb_header_release() - allow clones to use the headroom + * @skb: buffer to operate on + * + * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { |