sk_buff: add skb extension infrastructure

This adds an optional extension infrastructure, with ispec (xfrm) and
bridge netfilter as first users.
objdiff shows no changes if kernel is built without xfrm and br_netfilter
support.

The third (planned future) user is Multipath TCP which is still
out-of-tree.
MPTCP needs to map logical mptcp sequence numbers to the tcp sequence
numbers used by individual subflows.

This DSS mapping is read/written from tcp option space on receive and
written to tcp option space on transmitted tcp packets that are part of
and MPTCP connection.

Extending skb_shared_info or adding a private data field to skb fclones
doesn't work for incoming skb, so a different DSS propagation method would
be required for the receive side.

mptcp has same requirements as secpath/bridge netfilter:

1. extension memory is released when the sk_buff is free'd.
2. data is shared after cloning an skb (clone inherits extension)
3. adding extension to an skb will COW the extension buffer if needed.

The "MPTCP upstreaming" effort adds SKB_EXT_MPTCP extension to store the
mapping for tx and rx processing.

Two new members are added to sk_buff:
1. 'active_extensions' byte (filling a hole), telling which extensions
   are available for this skb.
   This has two purposes.
   a) avoids the need to initialize the pointer.
   b) allows to "delete" an extension by clearing its bit
   value in ->active_extensions.

   While it would be possible to store the active_extensions byte
   in the extension struct instead of sk_buff, there is one problem
   with this:
    When an extension has to be disabled, we can always clear the
    bit in skb->active_extensions.  But in case it would be stored in the
    extension buffer itself, we might have to COW it first, if
    we are dealing with a cloned skb.  On kmalloc failure we would
    be unable to turn an extension off.

2. extension pointer, located at the end of the sk_buff.
   If the active_extensions byte is 0, the pointer is undefined,
   it is not initialized on skb allocation.

This adds extra code to skb clone and free paths (to deal with
refcount/free of extension area) but this replaces similar code that
manages skb->nf_bridge and skb->sp structs in the followup patches of
the series.

It is possible to add support for extensions that are not preseved on
clones/copies.

To do this, it would be needed to define a bitmask of all extensions that
need copy/cow semantics, and change __skb_ext_copy() to check
->active_extensions & SKB_EXT_PRESERVE_ON_CLONE, then just set
->active_extensions to 0 on the new clone.

This isn't done here because all extensions that get added here
need the copy/cow semantics.

v2:
Allocate entire extension space using kmem_cache.
Upside is that this allows better tracking of used memory,
downside is that we will allocate more space than strictly needed in
most cases (its unlikely that all extensions are active/needed at same
time for same skb).
The allocated memory (except the small extension header) is not cleared,
so no additonal overhead aside from memory usage.

Avoid atomic_dec_and_test operation on skb_ext_put()
by using similar trick as kfree_skbmem() does with fclone_ref:
If recount is 1, there is no concurrent user and we can free right away.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 110 insertions, 1 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b1831a5ca173..88f7541837e3 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -245,6 +245,7 @@ struct iov_iter;
 struct napi_struct;
 struct bpf_prog;
 union bpf_attr;
+struct skb_ext;
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 struct nf_conntrack {
@@ -636,6 +637,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@queue_mapping: Queue mapping for multiqueue devices
  *	@xmit_more: More SKBs are pending for this queue
  *	@pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
+ *	@active_extensions: active extensions (skb_ext_id types)
  *	@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
@@ -665,6 +667,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@data: Data head pointer
  *	@truesize: Buffer size
  *	@users: User count - see {datagram,tcp}.c
+ *	@extensions: allocated extensions, valid if active_extensions is nonzero
  */
 
 struct sk_buff {
@@ -747,7 +750,9 @@ struct sk_buff {
 				head_frag:1,
 				xmit_more:1,
 				pfmemalloc:1;
-
+#ifdef CONFIG_SKB_EXTENSIONS
+	__u8			active_extensions;
+#endif
 	/* fields enclosed in headers_start/headers_end are copied
 	 * using a single memcpy() in __copy_skb_header()
 	 */
@@ -869,6 +874,11 @@ struct sk_buff {
 				*data;
 	unsigned int		truesize;
 	refcount_t		users;
+
+#ifdef CONFIG_SKB_EXTENSIONS
+	/* only useable after checking ->active_extensions != 0 */
+	struct skb_ext		*extensions;
+#endif
 };
 
 #ifdef __KERNEL__
@@ -3896,6 +3906,105 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct)
 		atomic_inc(&nfct->use);
 }
 #endif
+
+#ifdef CONFIG_SKB_EXTENSIONS
+enum skb_ext_id {
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	SKB_EXT_BRIDGE_NF,
+#endif
+	SKB_EXT_NUM, /* must be last */
+};
+
+/**
+ *	struct skb_ext - sk_buff extensions
+ *	@refcnt: 1 on allocation, deallocated on 0
+ *	@offset: offset to add to @data to obtain extension address
+ *	@chunks: size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units
+ *	@data: start of extension data, variable sized
+ *
+ *	Note: offsets/lengths are stored in chunks of 8 bytes, this allows
+ *	to use 'u8' types while allowing up to 2kb worth of extension data.
+ */
+struct skb_ext {
+	refcount_t refcnt;
+	u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */
+	u8 chunks;		/* same */
+	char data[0] __aligned(8);
+};
+
+void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id);
+void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id);
+void __skb_ext_put(struct skb_ext *ext);
+
+static inline void skb_ext_put(struct sk_buff *skb)
+{
+	if (skb->active_extensions)
+		__skb_ext_put(skb->extensions);
+}
+
+static inline void skb_ext_get(struct sk_buff *skb)
+{
+	if (skb->active_extensions) {
+		struct skb_ext *ext = skb->extensions;
+
+		if (ext)
+			refcount_inc(&ext->refcnt);
+	}
+}
+
+static inline void __skb_ext_copy(struct sk_buff *dst,
+				  const struct sk_buff *src)
+{
+	dst->active_extensions = src->active_extensions;
+
+	if (src->active_extensions) {
+		struct skb_ext *ext = src->extensions;
+
+		refcount_inc(&ext->refcnt);
+		dst->extensions = ext;
+	}
+}
+
+static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src)
+{
+	skb_ext_put(dst);
+	__skb_ext_copy(dst, src);
+}
+
+static inline bool __skb_ext_exist(const struct skb_ext *ext, enum skb_ext_id i)
+{
+	return !!ext->offset[i];
+}
+
+static inline bool skb_ext_exist(const struct sk_buff *skb, enum skb_ext_id id)
+{
+	return skb->active_extensions & (1 << id);
+}
+
+static inline void skb_ext_del(struct sk_buff *skb, enum skb_ext_id id)
+{
+	if (skb_ext_exist(skb, id))
+		__skb_ext_del(skb, id);
+}
+
+static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id)
+{
+	if (skb_ext_exist(skb, id)) {
+		struct skb_ext *ext = skb->extensions;
+
+		return (void *)ext + (ext->offset[id] << 3);
+	}
+
+	return NULL;
+}
+#else
+static inline void skb_ext_put(struct sk_buff *skb) {}
+static inline void skb_ext_get(struct sk_buff *skb) {}
+static inline void skb_ext_del(struct sk_buff *skb, int unused) {}
+static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {}
+static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {}
+#endif /* CONFIG_SKB_EXTENSIONS */
+
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge)
 {