netlink: remove mmapped netlink support

commit d1b4c689 upstream.

mmapped netlink has a number of unresolved issues:

- TX zerocopy support had to be disabled more than a year ago via
  commit 4682a035 ("netlink: Always copy on mmap TX.")
  because the content of the mmapped area can change after netlink
  attribute validation but before message processing.

- RX support was implemented mainly to speed up nfqueue dumping packet
  payload to userspace.  However, since commit ae08ce00
  ("netfilter: nfnetlink_queue: zero copy support") we avoid one copy
  with the socket-based interface too (via the skb_zerocopy helper).

The other problem is that skbs attached to mmaped netlink socket
behave different from normal skbs:

- they don't have a shinfo area, so all functions that use skb_shinfo()
(e.g. skb_clone) cannot be used.

- reserving headroom prevents userspace from seeing the content as
it expects message to start at skb->head.
See for instance
commit aa3a0220 ("netlink: not trim skb for mmaped socket when dump").

- skbs handed e.g. to netlink_ack must have non-NULL skb->sk, else we
crash because it needs the sk to check if a tx ring is attached.

Also not obvious, leads to non-intuitive bug fixes such as 7c7bdf35
("netfilter: nfnetlink: use original skbuff when acking batches").

mmaped netlink also didn't play nicely with the skb_zerocopy helper
used by nfqueue and openvswitch.  Daniel Borkmann fixed this via
commit 6bb0fef4 ("netlink, mmap: fix edge-case leakages in nf queue
zero-copy")' but at the cost of also needing to provide remaining
length to the allocation function.

nfqueue also has problems when used with mmaped rx netlink:
- mmaped netlink doesn't allow use of nfqueue batch verdict messages.
  Problem is that in the mmap case, the allocation time also determines
  the ordering in which the frame will be seen by userspace (A
  allocating before B means that A is located in earlier ring slot,
  but this also means that B might get a lower sequence number then A
  since seqno is decided later.  To fix this we would need to extend the
  spinlocked region to also cover the allocation and message setup which
  isn't desirable.
- nfqueue can now be configured to queue large (GSO) skbs to userspace.
  Queing GSO packets is faster than having to force a software segmentation
  in the kernel, so this is a desirable option.  However, with a mmap based
  ring one has to use 64kb per ring slot element, else mmap has to fall back
  to the socket path (NL_MMAP_STATUS_COPY) for all large packets.

To use the mmap interface, userspace not only has to probe for mmap netlink
support, it also has to implement a recv/socket receive path in order to
handle messages that exceed the size of an rx ring element.

Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Ken-ichirou MATSUZAWA <chamaken@gmail.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Shi Yuejie <shiyuejie@outlook.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

include/uapi/linux/netlink.h

@@ -107,8 +107,10 @@ struct nlmsgerr {
 #define NETLINK_PKTINFO			3
 #define NETLINK_BROADCAST_ERROR		4
 #define NETLINK_NO_ENOBUFS		5
+#ifndef __KERNEL__
 #define NETLINK_RX_RING			6
 #define NETLINK_TX_RING			7
+#endif
 #define NETLINK_LISTEN_ALL_NSID		8
 #define NETLINK_LIST_MEMBERSHIPS	9
 #define NETLINK_CAP_ACK			10
@@ -134,6 +136,7 @@ struct nl_mmap_hdr {
 	__u32		nm_gid;
 };
 
+#ifndef __KERNEL__
 enum nl_mmap_status {
 	NL_MMAP_STATUS_UNUSED,
 	NL_MMAP_STATUS_RESERVED,
@@ -145,6 +148,7 @@ enum nl_mmap_status {
 #define NL_MMAP_MSG_ALIGNMENT		NLMSG_ALIGNTO
 #define NL_MMAP_MSG_ALIGN(sz)		__ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT)
 #define NL_MMAP_HDRLEN			NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr))
+#endif
 
 #define NET_MAJOR 36		/* Major 36 is reserved for networking 						*/
 

include/uapi/linux/netlink_diag.h

@@ -48,6 +48,8 @@ enum {
 
 #define NDIAG_SHOW_MEMINFO	0x00000001 /* show memory info of a socket */
 #define NDIAG_SHOW_GROUPS	0x00000002 /* show groups of a netlink socket */
+#ifndef __KERNEL__
 #define NDIAG_SHOW_RING_CFG	0x00000004 /* show ring configuration */
+#endif
 
 #endif

net/netlink/Kconfig

@@ -2,15 +2,6 @@
 # Netlink Sockets
 #
 
-config NETLINK_MMAP
-	bool "NETLINK: mmaped IO"
-	---help---
-	  This option enables support for memory mapped netlink IO. This
-	  reduces overhead by avoiding copying data between kernel- and
-	  userspace.
-
-	  If unsure, say N.
-
 config NETLINK_DIAG
 	tristate "NETLINK: socket monitoring interface"
 	default n

net/netlink/af_netlink.h

@@ -45,12 +45,6 @@ struct netlink_sock {
 	int			(*netlink_bind)(struct net *net, int group);
 	void			(*netlink_unbind)(struct net *net, int group);
 	struct module		*module;
-#ifdef CONFIG_NETLINK_MMAP
-	struct mutex		pg_vec_lock;
-	struct netlink_ring	rx_ring;
-	struct netlink_ring	tx_ring;
-	atomic_t		mapped;
-#endif /* CONFIG_NETLINK_MMAP */
 
 	struct rhash_head	node;
 	struct rcu_head		rcu;
@@ -62,15 +56,6 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk)
 	return container_of(sk, struct netlink_sock, sk);
 }
 
-static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
-#ifdef CONFIG_NETLINK_MMAP
-	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-#else
-	return false;
-#endif /* CONFIG_NETLINK_MMAP */
-}
-
 struct netlink_table {
 	struct rhashtable	hash;
 	struct hlist_head	mc_list;

net/netlink/diag.c

@@ -8,41 +8,6 @@
 
 #include "af_netlink.h"
 
-#ifdef CONFIG_NETLINK_MMAP
-static int sk_diag_put_ring(struct netlink_ring *ring, int nl_type,
-			    struct sk_buff *nlskb)
-{
-	struct netlink_diag_ring ndr;
-
-	ndr.ndr_block_size = ring->pg_vec_pages << PAGE_SHIFT;
-	ndr.ndr_block_nr   = ring->pg_vec_len;
-	ndr.ndr_frame_size = ring->frame_size;
-	ndr.ndr_frame_nr   = ring->frame_max + 1;
-
-	return nla_put(nlskb, nl_type, sizeof(ndr), &ndr);
-}
-
-static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-	int ret;
-
-	mutex_lock(&nlk->pg_vec_lock);
-	ret = sk_diag_put_ring(&nlk->rx_ring, NETLINK_DIAG_RX_RING, nlskb);
-	if (!ret)
-		ret = sk_diag_put_ring(&nlk->tx_ring, NETLINK_DIAG_TX_RING,
-				       nlskb);
-	mutex_unlock(&nlk->pg_vec_lock);
-
-	return ret;
-}
-#else
-static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb)
-{
-	return 0;
-}
-#endif
-
 static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -87,10 +52,6 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 	    sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO))
 		goto out_nlmsg_trim;
 
-	if ((req->ndiag_show & NDIAG_SHOW_RING_CFG) &&
-	    sk_diag_put_rings_cfg(sk, skb))
-		goto out_nlmsg_trim;
-
 	nlmsg_end(skb, nlh);
 	return 0;